You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/09/26 23:03:45 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@e1f3f90588aa2d9bb71e0ca8ebc5baab865e054d)
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a commit to branch asf-site
in repository https://gitbox.apache.org/repos/asf/tvm-site.git
The following commit(s) were added to refs/heads/asf-site by this push:
new 4509b2999f deploying docs (apache/tvm@e1f3f90588aa2d9bb71e0ca8ebc5baab865e054d)
4509b2999f is described below
commit 4509b2999f9133c1771d6d93b9f709a2bdb53914
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Mon Sep 26 23:03:38 2022 +0000
deploying docs (apache/tvm@e1f3f90588aa2d9bb71e0ca8ebc5baab865e054d)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 335230 -> 331892 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 23974 -> 23825 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 6 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1558 ++++++++++++++++----
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 82 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 8 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 361 +----
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 10 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 16 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 13 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 57 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 47 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 14 +-
docs/how_to/compile_models/from_pytorch.html | 6 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 47 +-
docs/how_to/deploy_models/deploy_prequantized.html | 9 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 36 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 6 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1558 ++++++++++++++++----
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 82 +-
.../tune_with_autotvm/sg_execution_times.html | 8 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 361 +----
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 10 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 16 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/install/nnpack.html | 12 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 8 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 265 ++--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 43 +-
126 files changed, 3435 insertions(+), 2176 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 4730ebaecb..9ba43750df 100644
Binary files a/docs/_images/sphx_glr_micro_train_001.png and b/docs/_images/sphx_glr_micro_train_001.png differ
diff --git a/docs/_images/sphx_glr_micro_train_thumb.png b/docs/_images/sphx_glr_micro_train_thumb.png
index 4f63c99e35..d025dae545 100644
Binary files a/docs/_images/sphx_glr_micro_train_thumb.png and b/docs/_images/sphx_glr_micro_train_thumb.png differ
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index 309892d84f..a707e1d81b 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -315,7 +315,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 3.741 seconds)
+ **Total running time of the script:** ( 1 minutes 5.158 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_keras.rst.txt b/docs/_sources/how_to/compile_models/from_keras.rst.txt
index 595ac3a7a0..3b5236b8f0 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -228,7 +228,7 @@ Look up prediction top 1 index in 1000 class synset.
.. code-block:: none
Relay top-1 id: 285, class name: Egyptian cat
-
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 964ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 990ms/step
Keras top-1 id: 285, class name: Egyptian cat
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 4926b6fda0..1551852cb3 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -115,7 +115,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipb88ea9aa-58d1-4187-8dc8-4e4c1a95ed62 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip201fb619-2e31-4b70-b621-164130366954 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
diff --git a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
index 943437b7da..fe3083ad0e 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -116,7 +116,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 45.0MB/s]
26%|##5 | 10.6M/41.5M [00:00<00:00, 37.1MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 35.8MB/s]
43%|####2 | 17.7M/41.5M [00:00<00:00, 34.6MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 35.6MB/s]
62%|######1 | 25.7M/41.5M [00:00<00:00, 34.2MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 40.1MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 44.1MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 41.0MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 57.5MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 47.1MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 55.4MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 53.6MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 52.2MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index 78991a2a96..add1168423 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -94,7 +94,7 @@ Load a pretrained PyTorch model
.. code-block:: none
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
38%|###8 | 17.1M/44.7M [00:00<00:00, 179MB/s]
94%|#########4| 42.0M/44.7M [00:00<00:00, 227MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 222MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
38%|###7 | 16.8M/44.7M [00:00<00:00, 176MB/s]
92%|#########2| 41.2M/44.7M [00:00<00:00, 223MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 220MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
index bd1c56a09e..062f558207 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -416,7 +416,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.186 seconds)
+ **Total running time of the script:** ( 1 minutes 5.618 seconds)
.. _sphx_glr_download_how_to_compile_models_from_tensorflow.py:
diff --git a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
index 085284c5a9..58a6191340 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**05:11.822** total execution time for **how_to_compile_models** files:
+**05:13.816** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:07.186 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:05.618 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:03.741 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:05.158 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:39.846 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:40.721 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:28.484 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:28.289 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:25.441 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:26.998 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.392 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.238 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:21.630 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:23.016 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.720 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.655 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.875 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.455 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.506 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.667 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 89345aee3b..6ff74755e9 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -434,7 +434,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.6996 15.6853 15.8359 15.6105 0.0685
+ 16.1807 16.2024 16.2717 16.0010 0.0771
diff --git a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
index dcc8d66767..fe46cbf8ba 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -123,7 +123,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
3%|3 | 5.44M/170M [00:00<00:03, 56.8MB/s]
6%|6 | 10.9M/170M [00:00<00:02, 56.6MB/s]
10%|9 | 16.3M/170M [00:00<00:02, 56.8MB/s]
13%|#2 | 21.7M/170M [00:00<00:03, 50.7MB/s]
16%|#5 | 26.7M/170M [00:00<00:03, 45.2MB/s]
18%|#8 | 31.2M/170M [00:00<00:03, 46.0MB/s]
22%|##1 | 37.4M/170M [00:00<00:02, 51.3MB/s]
25%|##4 | 42.4M/170M [00:00<00:02, 49.1MB/s]
28%|##7 | 47.1M/170M [00:00<00:02, 48.8MB/s]
31%|###1 | 52.9M/170M [00:01<00:02, 52.1MB/s]
34%|###4 | 57.9M/170M [00:01<00:02, 52.1MB/s]
37%|###7 | 63.1M/170M [00:01<00:02, 52.7MB/s]
40%|#### | 68.1M/170M [00:01<00:02, 47.9MB/s]
43%|####2 | 72.8M/170M [00:01<00:02, 47.4MB/s]
46%|####5 | 77.4M/170M [00:01<00:02, 42.0MB/s]
48%|####8 | 82.2M/170M [00:01<00:02, 44.2MB/s]
51%|##### | 86.5M/170M [00:01<00:01, 43.8MB/
s]
54%|#####4 | 92.3M/170M [00:01<00:01, 48.4MB/s]
58%|#####7 | 97.7M/170M [00:02<00:01, 49.8MB/s]
60%|###### | 102M/170M [00:02<00:01, 47.9MB/s]
63%|######3 | 107M/170M [00:02<00:01, 43.8MB/s]
66%|######5 | 112M/170M [00:02<00:01, 45.5MB/s]
69%|######9 | 117M/170M [00:02<00:01, 48.3MB/s]
72%|#######2 | 122M/170M [00:02<00:00, 50.1MB/s]
75%|#######4 | 127M/170M [00:02<00:01, 43.3MB/s]
78%|#######7 | 132M/170M [00:02<00:00, 40.2MB/s]
80%|#######9 | 136M/170M [00:03<00:00, 38.3MB/s]
82%|########2 | 139M/170M [00:03<00:00, 34.5MB/s]
84%|########4 | 143M/170M [00:03<00:00, 36.1MB/s]
86%|########6 | 147M/170M [00:03<00:00, 31.1MB/s]
88%|########8 | 150M/170M [00:03<00:00, 30.8MB/s]
91%|######### | 154M/170M [00:03<00:00, 33.2MB/s]
93%|#########3| 158M/170M [00:03<00:00, 37.0MB/s]
95%|#########5| 162M/170M [00:03<00:00, 36.9MB/s]
99%|#########8| 167M/170M [00:03<00:00, 41.8MB/s]
100%|##########| 170M/170M [00:04<00:00, 44.2MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
11%|#1 | 19.4M/170M [00:00<00:00, 204MB/s]
27%|##6 | 45.5M/170M [00:00<00:00, 245MB/s]
41%|#### | 68.9M/170M [00:00<00:00, 221MB/s]
53%|#####3 | 90.2M/170M [00:00<00:00, 183MB/s]
64%|######3 | 108M/170M [00:00<00:00, 175MB/s]
74%|#######4 | 126M/170M [00:00<00:00, 179MB/s]
85%|########4 | 144M/170M [00:00<00:00, 160MB/s]
97%|#########7| 165M/170M [00:00<00:00, 176MB/s]
100%|##########| 170M/170M [00:00<00:00, 184MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -288,7 +288,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 1.771 seconds)
+ **Total running time of the script:** ( 3 minutes 2.909 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_object_detection_pytorch.py:
diff --git a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
index 3d2e98f6e3..3cba2f026c 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -232,7 +232,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
43%|####3 | 5.86M/13.6M [00:00<00:00, 61.3MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 71.4MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
26%|##5 | 3.50M/13.6M [00:00<00:00, 36.7MB/s]
52%|#####1 | 7.00M/13.6M [00:00<00:00, 35.6MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 59.5MB/s]
@@ -405,7 +405,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3669 90.3087 92.7059 90.1362 0.2949
+ 90.3164 90.2595 91.5742 90.1201 0.2217
@@ -454,7 +454,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.708 seconds)
+ **Total running time of the script:** ( 1 minutes 11.305 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_prequantized.py:
diff --git a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
index 34f0654e0c..844153c008 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -432,7 +432,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.7184 120.5215 126.8395 119.8450 0.8031
+ 118.9824 118.9099 122.4330 118.1992 0.5684
@@ -469,7 +469,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 51.550 seconds)
+ **Total running time of the script:** ( 1 minutes 52.627 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_prequantized_tflite.py:
diff --git a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
index 4583458f97..198b432c10 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -253,7 +253,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 28.689 seconds)
+ **Total running time of the script:** ( 1 minutes 28.331 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_quantized.py:
diff --git a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
index df7791ecbf..eb2040509b 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -158,7 +158,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6575/132723 [00:00<00:01, 65742.38KB/s]
11%|#1 | 14940/132723 [00:00<00:01, 76273.68KB/s]
17%|#7 | 22568/132723 [00:00<00:01, 62426.81KB/s]
23%|##3 | 31001/132723 [00:00<00:01, 70046.20KB/s]
30%|##9 | 39446/132723 [00:00<00:01, 74827.99KB/s]
36%|###6 | 47994/132723 [00:00<00:01, 78251.67KB/s]
43%|####2 | 56474/132723 [00:00<00:00, 80310.70KB/s]
49%|####8 | 64917/132723 [00:00<00:00, 81584.51KB/s]
55%|#####5 | 73451/132723 [00:00<00:00, 82735.79KB/s]
62%|######1 | 82012/132723 [00:01<00:00, 83610.66KB/s]
68%|######8 | 90538/132723 [00:01<00:00, 84109.32KB/s]
75%|#######4 | 99085/132723 [00:01<00:00, 84516.41KB/s]
81%|########1 | 107557/132723 [00:01<00:00, 84447.82KB/s]
87%|########7 | 116016/132723 [00:01<00:00, 81439.18KB/s]
94%|#########3| 124581/132723 [00:01<00:00, 82668.72KB/s]
100%|########
##| 132723/132723 [00:01<00:00, 80017.01KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|4 | 5918/132723 [00:00<00:02, 59162.00KB/s]
11%|# | 14177/132723 [00:00<00:01, 72938.53KB/s]
16%|#6 | 21471/132723 [00:00<00:01, 61649.58KB/s]
22%|##2 | 29767/132723 [00:00<00:01, 69220.19KB/s]
28%|##7 | 36880/132723 [00:00<00:01, 67668.24KB/s]
34%|###4 | 45224/132723 [00:00<00:01, 72675.89KB/s]
40%|###9 | 52606/132723 [00:00<00:01, 64401.48KB/s]
46%|####5 | 60925/132723 [00:00<00:01, 69703.92KB/s]
51%|#####1 | 68111/132723 [00:01<00:01, 62558.62KB/s]
56%|#####6 | 74620/132723 [00:01<00:00, 60467.28KB/s]
62%|######2 | 82931/132723 [00:01<00:00, 66523.24KB/s]
69%|######8 | 91302/132723 [00:01<00:00, 71274.97KB/s]
74%|#######4 | 98619/132723 [00:01<00:00, 71027.31KB/s]
81%|######## | 106942/132723 [00:01<00:00, 74513.42KB/s]
86%|########6 | 114680/132723 [00:01<00:00, 68066.71KB/s]
92%|#########
2| 122529/132723 [00:01<00:00, 70902.87KB/s]
98%|#########7| 129776/132723 [00:01<00:00, 55166.91KB/s]
100%|##########| 132723/132723 [00:02<00:00, 64690.75KB/s]
@@ -234,7 +234,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 37.498 seconds)
+ **Total running time of the script:** ( 2 minutes 41.829 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_ssd_gluoncv.py:
diff --git a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
index 93c6c4eb23..c3b833fb0c 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**11:22.580** total execution time for **how_to_deploy_models** files:
+**11:32.995** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:01.771 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:02.909 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:37.498 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:41.829 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:51.550 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:52.627 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:28.689 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:28.331 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:08.708 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:11.305 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.972 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:30.470 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.366 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:23.101 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.019 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.416 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 674b800540..5693460eea 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -472,7 +472,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip59233f65-95eb-4c88-bd6d-dfcc99963730 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipadbdcc30-1499-4142-881c-575dcde9156d from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
diff --git a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
index 9c1f7260e8..d255fb7185 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:41.757** total execution time for **how_to_extend_tvm** files:
+**00:42.495** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:38.499 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:39.241 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.306 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.302 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.945 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 533daf8945..a68c2b9078 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -216,10 +216,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6922us [6922us] (46.23%; 46.23%)
- FoldScaleAxis: 8050us [6us] (53.77%; 53.77%)
- FoldConstant: 8044us [1668us] (53.73%; 99.92%)
- InferType: 6376us [6376us] (42.59%; 79.26%)
+ InferType: 7816us [7816us] (48.37%; 48.37%)
+ FoldScaleAxis: 8343us [9us] (51.63%; 51.63%)
+ FoldConstant: 8334us [1794us] (51.57%; 99.89%)
+ InferType: 6540us [6540us] (40.47%; 78.47%)
@@ -258,10 +258,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6393us [6393us] (44.70%; 44.70%)
- FoldScaleAxis: 7910us [5us] (55.30%; 55.30%)
- FoldConstant: 7905us [1672us] (55.27%; 99.94%)
- InferType: 6233us [6233us] (43.58%; 78.85%)
+ InferType: 6499us [6499us] (44.88%; 44.88%)
+ FoldScaleAxis: 7983us [6us] (55.12%; 55.12%)
+ FoldConstant: 7977us [1639us] (55.08%; 99.92%)
+ InferType: 6338us [6338us] (43.76%; 79.45%)
diff --git a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
index f144ab3f10..686575b6e3 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.123455 ms
+ Convolution: 50.563518 ms
diff --git a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
index 8c92ec93a3..c89ad76eee 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -671,7 +671,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 7.605078 ms
+ conv2d with tensor core: 6.696150 ms
diff --git a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
index 21e3d93f72..909c85b9e8 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -143,8 +143,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.019227
- Baseline: 3.254608
+ Numpy running time: 0.019119
+ Baseline: 3.411100
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.296242
+ Opt1: 0.312324
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.335836
+ Opt2: 0.348305
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.116821
+ Opt3: 0.121853
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110008
+ Opt4: 0.109916
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111670
+ Opt5: 0.110952
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.148761
+ Opt6: 0.146768
diff --git a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
index f4921715b7..9f397d10a9 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.402** total execution time for **how_to_optimize_operators** files:
+**00:34.879** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.954 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.637 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.320 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.228 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.129 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.014 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
index cd64930db6..4fd2f887eb 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**06:25.646** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:40.525** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:25.506 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:37.041 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:23.690 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:23.537 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:56.965 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:57.406 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:21.465 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:24.013 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:09.116 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:09.413 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.904 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:09.115 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
index 5b65b05fba..641271c09e 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -240,187 +240,707 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 128;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [768]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_4: int32 = (rc.outer.outer*1568)
- let cse_var_3: int32 = (ry.outer.outer*7)
- let cse_var_2: int32 = (rc.outer.outer*288)
- let cse_var_1: int32 = (ry.outer.outer*3)
+ for (rc.outer.outer: int32, 0, 8) {
+ for (rx.outer.outer: int32, 0, 3) {
+ let cse_var_1: int32 = (rc.outer.outer*3136)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 560), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 672), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 784), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 896), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 776)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1120), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1232), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1344)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1344), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1456)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1456), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1568), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1680)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1680), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1792)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1792), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1904)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1904), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 896), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1008), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1120), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1232), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1456), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1680), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1792), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1904), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[(((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 96768)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2128), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2240), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2464), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2576), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2800), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2912), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_2 < 48), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3024), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 16)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 28)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 20)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 56), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 84)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 84), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 112), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 140)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 140), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 168), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 196), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 224), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 252)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 188)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 280), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 308)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 308), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 336), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 364)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 364), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 392), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 420)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 420), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 448), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 476)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 476), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 384)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 532)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 532), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 560), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 588), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 616), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 644)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 644), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 672), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 700)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 700), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 728)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 728), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 756)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 580)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 784), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 812)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 812), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 840)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 840), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 868)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 868), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 896), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 924)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 924), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 952)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 952), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 980), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 776)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1036)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1036), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1064)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1064), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1092)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1092), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1120), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1148)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1148), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1176), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1204)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1204), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1232), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1260)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 972)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1288)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1288), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1316)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1316), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1344)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1344), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1372), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1400)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1400), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1428)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1428), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1456)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1456), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1484)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1484), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1512)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 1168)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1540)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1540), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1568), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1596)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1596), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1624)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1624), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1652)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1652), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1680)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1680), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1708)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1708), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1736)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1736), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 1364)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1792)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1792), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1820)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1820), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1848)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1848), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1876)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1876), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1904)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1904), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1932)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1932), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1960), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1988)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1988), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2016)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 1560)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2044)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2044), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2072)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2072), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2100)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2100), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2128)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2128), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2156)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2156), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2184)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2184), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2212)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2212), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2240)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2240), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2268)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 1756)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2296)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2296), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2324)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2324), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2352), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2380)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2380), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2408)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2408), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2436)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2436), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2464)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2464), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2492)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2492), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2520)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 1952)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2548)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2548), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2576)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2576), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2604)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2604), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2632)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2632), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2660)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2660), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2688)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2688), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2716)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2716), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2744)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2744), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2772)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 2148)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2800)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2800), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2828)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2828), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2856)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2856), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2884)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2884), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2912)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2912), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2940)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2940), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2968)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2968), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2996)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2996), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3024)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 2344)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3052)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3052), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3080)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3080), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3108)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3108), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3136), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3164)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3164), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3192)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3192), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3220)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3220), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3248)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3248), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3276)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 2540)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3304)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3304), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3332)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3332), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3360)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3360), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3388)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3388), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3416)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3416), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3444)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3444), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3472)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3472), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3500)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3500), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3528)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 2736)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3556)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3556), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3584)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3584), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3612)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3612), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3640)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3640), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3668)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3668), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3696)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3696), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3724)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3724), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3752)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3752), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3780)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 2932)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3808)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3808), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3836)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3836), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3864)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3864), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3892)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3892), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3920), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3948)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3948), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3976)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3976), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 4004)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 4004), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28 {
+ kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[(threadIdx.x_2*24)] = kernel[(((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer)]
+ kernel.shared_1[((threadIdx.x_2*24) + 1)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 3)]
+ kernel.shared_1[((threadIdx.x_2*24) + 2)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 6)]
+ kernel.shared_1[((threadIdx.x_2*24) + 3)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 9)]
+ kernel.shared_1[((threadIdx.x_2*24) + 4)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 12)]
+ kernel.shared_1[((threadIdx.x_2*24) + 5)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 15)]
+ kernel.shared_1[((threadIdx.x_2*24) + 6)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 18)]
+ kernel.shared_1[((threadIdx.x_2*24) + 7)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 21)]
+ kernel.shared_1[((threadIdx.x_2*24) + 8)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 24)]
+ kernel.shared_1[((threadIdx.x_2*24) + 9)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 27)]
+ kernel.shared_1[((threadIdx.x_2*24) + 10)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 30)]
+ kernel.shared_1[((threadIdx.x_2*24) + 11)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 33)]
+ kernel.shared_1[((threadIdx.x_2*24) + 12)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 36)]
+ kernel.shared_1[((threadIdx.x_2*24) + 13)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 39)]
+ kernel.shared_1[((threadIdx.x_2*24) + 14)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 42)]
+ kernel.shared_1[((threadIdx.x_2*24) + 15)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 45)]
+ kernel.shared_1[((threadIdx.x_2*24) + 16)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 48)]
+ kernel.shared_1[((threadIdx.x_2*24) + 17)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 51)]
+ kernel.shared_1[((threadIdx.x_2*24) + 18)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 54)]
+ kernel.shared_1[((threadIdx.x_2*24) + 19)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 57)]
+ kernel.shared_1[((threadIdx.x_2*24) + 20)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 60)]
+ kernel.shared_1[((threadIdx.x_2*24) + 21)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 63)]
+ kernel.shared_1[((threadIdx.x_2*24) + 22)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 66)]
+ kernel.shared_1[((threadIdx.x_2*24) + 23)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 69)]
}
- for (rc.outer.inner: int32, 0, 32) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1536)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1536)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1536)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1536)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1536)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1536)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1536)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1537)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1537)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1537)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1537)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1537)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1537)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1537)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1538)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1538)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1538)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1538)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1538)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1538)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1538)]))
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ if @tir.likely((threadIdx.x_2 < 4), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*24) + 672)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 32)*9)) + rx.outer.outer) + 13824)]
+ kernel.shared_1[((threadIdx.x_2*24) + 673)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 32)*9)) + rx.outer.outer) + 13827)]
+ kernel.shared_1[((threadIdx.x_2*24) + 674)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 32)*9)) + rx.outer.outer) + 13830)]
+ kernel.shared_1[((threadIdx.x_2*24) + 675)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 33)*9)) + rx.outer.outer) + 13824)]
+ kernel.shared_1[((threadIdx.x_2*24) + 676)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 33)*9)) + rx.outer.outer) + 13827)]
+ kernel.shared_1[((threadIdx.x_2*24) + 677)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 33)*9)) + rx.outer.outer) + 13830)]
+ kernel.shared_1[((threadIdx.x_2*24) + 678)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 34)*9)) + rx.outer.outer) + 13824)]
+ kernel.shared_1[((threadIdx.x_2*24) + 679)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 34)*9)) + rx.outer.outer) + 13827)]
+ kernel.shared_1[((threadIdx.x_2*24) + 680)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 34)*9)) + rx.outer.outer) + 13830)]
+ kernel.shared_1[((threadIdx.x_2*24) + 681)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 35)*9)) + rx.outer.outer) + 13824)]
+ kernel.shared_1[((threadIdx.x_2*24) + 682)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 35)*9)) + rx.outer.outer) + 13827)]
+ kernel.shared_1[((threadIdx.x_2*24) + 683)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 35)*9)) + rx.outer.outer) + 13830)]
+ kernel.shared_1[((threadIdx.x_2*24) + 684)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 36)*9)) + rx.outer.outer) + 13824)]
+ kernel.shared_1[((threadIdx.x_2*24) + 685)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 36)*9)) + rx.outer.outer) + 13827)]
+ kernel.shared_1[((threadIdx.x_2*24) + 686)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 36)*9)) + rx.outer.outer) + 13830)]
+ kernel.shared_1[((threadIdx.x_2*24) + 687)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 37)*9)) + rx.outer.outer) + 13824)]
+ kernel.shared_1[((threadIdx.x_2*24) + 688)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 37)*9)) + rx.outer.outer) + 13827)]
+ kernel.shared_1[((threadIdx.x_2*24) + 689)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 37)*9)) + rx.outer.outer) + 13830)]
+ kernel.shared_1[((threadIdx.x_2*24) + 690)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 38)*9)) + rx.outer.outer) + 13824)]
+ kernel.shared_1[((threadIdx.x_2*24) + 691)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 38)*9)) + rx.outer.outer) + 13827)]
+ kernel.shared_1[((threadIdx.x_2*24) + 692)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 38)*9)) + rx.outer.outer) + 13830)]
+ kernel.shared_1[((threadIdx.x_2*24) + 693)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 39)*9)) + rx.outer.outer) + 13824)]
+ kernel.shared_1[((threadIdx.x_2*24) + 694)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 39)*9)) + rx.outer.outer) + 13827)]
+ kernel.shared_1[((threadIdx.x_2*24) + 695)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 39)*9)) + rx.outer.outer) + 13830)]
+ }
+ for (rc.outer.inner: int32, 0, 4) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*1008) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48))]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48))]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 45)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48))]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 147)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 210)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 273)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 336)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 399)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 462)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 525)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 588)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 651)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 714)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 777)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 36)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 840)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 39)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 903)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 42)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 966)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 532)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 595)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 658)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 721)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 784)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 847)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 910)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48))]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 98)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 161)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 224)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 287)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 350)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 413)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 476)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 539)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 602)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 665)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 728)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 791)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 36)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 854)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 39)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 917)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 980)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48))]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 231)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 294)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 357)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 420)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 483)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 546)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 609)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 672)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 735)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 798)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 861)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 924)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 987)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 46)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 37)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 40)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 43)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 147)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 210)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 273)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 336)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 399)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 462)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 525)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 588)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 651)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 714)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 777)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 840)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 903)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 966)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 46)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 532)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 595)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 658)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 721)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 784)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 37)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 847)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 40)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 910)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 43)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 98)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 161)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 224)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 287)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 350)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 413)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 476)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 539)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 602)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 665)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 728)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 791)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 854)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 40)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 917)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 43)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 980)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 231)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 294)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 357)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 420)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 483)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 546)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 609)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 672)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 735)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 798)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 37)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 861)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 924)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 987)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 46)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 49)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 112)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 238)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 301)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 364)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 427)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 490)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 553)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 616)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 679)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 742)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 805)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 37)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 868)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 40)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 931)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 43)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 994)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 47)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 147)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 210)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 273)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 336)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 399)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 462)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 525)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 588)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 651)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 714)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 777)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 38)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 840)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 41)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 903)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 44)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 966)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 532)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 595)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 658)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 721)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 784)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 847)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 910)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 47)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 98)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 161)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 224)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 287)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 350)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 413)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 476)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 539)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 602)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 665)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 728)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 791)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 38)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 854)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 41)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 917)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 44)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 980)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 231)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 294)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 357)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 420)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 483)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 546)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 609)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 672)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 735)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 798)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 861)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 41)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 924)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 44)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 987)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 49)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 112)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 238)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 301)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 364)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 427)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 490)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 553)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 616)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 679)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 742)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 805)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 38)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 868)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 931)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 994)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 47)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 371)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 434)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 560)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 623)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 686)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 749)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 38)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 875)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 41)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 938)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 44)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 1001)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 47)]))
}
}
}
}
- compute[((blockIdx.x*1568) + (threadIdx.x*7))] = max((conv2d_nchw_1[0] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 1)] = max((conv2d_nchw_1[1] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 2)] = max((conv2d_nchw_1[2] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 3)] = max((conv2d_nchw_1[3] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 4)] = max((conv2d_nchw_1[4] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 5)] = max((conv2d_nchw_1[5] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 6)] = max((conv2d_nchw_1[6] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 784)] = max((conv2d_nchw_1[7] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 785)] = max((conv2d_nchw_1[8] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 786)] = max((conv2d_nchw_1[9] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 787)] = max((conv2d_nchw_1[10] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 788)] = max((conv2d_nchw_1[11] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 789)] = max((conv2d_nchw_1[12] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 790)] = max((conv2d_nchw_1[13] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
+ for (i2.inner: int32, 0, 7) {
+ compute[((((blockIdx.x*196) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((blockIdx.x*4) + floordiv(threadIdx.x, 7))]), 0f32)
+ }
}
}
@@ -474,7 +994,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.213 ms
+ Execution time of this operator: 0.306 ms
@@ -524,35 +1044,35 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
- conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+ conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=7)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=7)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=32)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+ conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
- compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
- compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+ compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -569,16 +1089,16 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=24)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=28)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=28)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -596,10 +1116,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[2016];
- __shared__ float kernel_shared[3072];
+ extern "C" __global__ void __launch_bounds__(28) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[7];
+ __shared__ float pad_temp_shared[4032];
+ __shared__ float kernel_shared[768];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -607,125 +1127,547 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 112) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 336) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 448) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 560) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 672) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 896) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 776)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1120) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1232)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1232) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1344) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1456)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1456) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1680)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1680) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1904)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1904) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1008) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 96768)];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2576) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2800) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 48) {
- kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3024) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 144)];
+ pad_temp_shared[((int)threadIdx.x)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 28)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 56) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 84)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 84) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 112) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 140)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 140) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 168) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 196) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 224) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 252)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 188)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 280) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 308)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 308) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 336) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 364)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 364) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 392) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 420)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 420) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 448) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 476)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 476) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 504)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 384)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 532)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 532) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 560) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 588) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 616) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 644)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 644) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 672) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 700)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 700) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 728)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 728) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 756)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 580)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 812)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 812) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 840)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 840) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 868)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 868) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 896)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 896) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 924)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 924) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 952)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 952) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 980) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1008)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 776)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1036)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1036) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1064)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1064) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1092)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1092) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1120) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1148)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1148) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1176) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1204)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1204) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1232)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1232) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1260)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 972)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1288)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1288) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1316)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1316) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1344) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1372) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1400)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1400) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1428)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1428) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1456)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1456) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1484)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1484) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1512)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1168)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1540)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1540) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1596)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1596) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1624)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1624) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1652)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1652) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1680)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1680) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1708)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1708) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1736)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1736) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1764)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1364)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1792) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1820)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1820) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1848)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1848) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1876)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1876) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1904)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1904) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1932)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1932) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1960) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1988)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1988) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2016)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1560)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2044)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2044) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2072)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2072) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2100)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2100) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2128)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2128) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2156)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2156) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2184)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2184) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2212)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2212) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2240)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2240) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2268)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1756)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2296)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2296) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2324)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2324) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2380)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2380) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2408)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2408) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2436)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2436) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2464)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2464) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2492)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2492) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2520)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1952)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2548)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2548) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2576)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2576) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2604)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2604) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2632)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2632) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2660)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2660) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2688)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2688) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2716)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2716) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2744)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2744) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2772)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2148)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2800)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2800) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2828)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2828) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2856)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2856) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2884)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2884) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2912)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2912) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2940)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2940) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2968)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2968) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2996)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2996) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3024)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2344)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3052)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3052) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3080)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3080) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3108)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3108) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3164)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3164) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3192)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3192) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3220)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3220) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3248)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3248) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3276)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2540)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3304)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3304) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3332)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3332) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3360)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3360) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3388)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3388) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3416)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3416) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3444)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3444) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3472)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3472) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3500)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3500) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3528)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2736)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3556)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3556) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3584)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3584) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3612)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3612) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3640)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3640) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3668)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3668) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3696)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3696) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3724)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3724) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3752)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3752) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3780)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2932)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3808)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3808) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3836)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3836) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3864)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3864) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3892)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3892) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3920)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3948)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3948) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3976)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3976) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 4004)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 4004) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ kernel_shared[(((int)threadIdx.x) * 24)] = kernel[(((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 1)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 3)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 2)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 6)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 3)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 9)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 4)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 12)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 5)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 15)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 6)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 18)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 7)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 21)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 8)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 24)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 9)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 27)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 10)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 30)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 11)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 33)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 12)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 36)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 13)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 39)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 14)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 42)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 15)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 45)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 16)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 48)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 17)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 51)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 18)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 54)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 19)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 57)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 20)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 60)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 21)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 63)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 22)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 66)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 23)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 69)];
+ if (((int)threadIdx.x) < 4) {
+ kernel_shared[((((int)threadIdx.x) * 24) + 672)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14112)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 673)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14115)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 674)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14118)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 675)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14121)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 676)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14124)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 677)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14127)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 678)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14130)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 679)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14133)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 680)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14136)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 681)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14139)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 682)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14142)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 683)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14145)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 684)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14148)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 685)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14151)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 686)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14154)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 687)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14157)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 688)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14160)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 689)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14163)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 690)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14166)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 691)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14169)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 692)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14172)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 693)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14175)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 694)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14178)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 695)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14181)];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 32; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1538)]));
+ for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 147)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 210)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 273)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 336)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 399)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 462)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 525)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 588)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 651)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 714)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 777)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 840)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 903)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 966)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 532)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 595)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 658)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 721)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 784)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 847)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 910)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 161)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 224)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 287)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 350)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 413)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 476)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 539)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 602)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 665)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 728)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 791)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 854)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 917)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 980)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 231)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 294)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 357)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 420)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 483)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 546)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 609)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 672)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 735)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 798)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 861)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 924)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 987)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 147)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 210)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 273)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 336)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 399)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 462)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 525)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 588)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 651)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 714)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 777)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 840)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 903)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 966)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 532)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 595)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 658)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 721)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 784)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 847)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 910)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 161)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 224)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 287)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 350)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 413)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 476)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 539)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 602)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 665)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 728)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 791)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 854)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 917)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 980)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 231)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 294)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 357)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 420)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 483)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 546)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 609)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 672)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 735)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 798)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 861)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 924)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 987)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 112)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 238)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 301)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 364)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 427)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 490)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 553)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 616)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 679)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 742)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 805)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 868)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 931)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 994)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 147)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 210)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 273)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 336)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 399)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 462)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 525)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 588)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 651)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 714)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 777)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 840)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 903)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 966)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 532)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 595)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 658)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 721)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 784)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 847)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 910)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 161)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 224)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 287)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 350)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 413)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 476)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 539)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 602)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 665)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 728)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 791)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 854)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 917)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 980)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 231)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 294)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 357)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 420)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 483)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 546)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 609)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 672)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 735)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 798)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 861)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 924)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 987)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 112)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 238)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 301)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 364)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 427)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 490)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 553)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 616)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 679)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 742)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 805)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 868)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 931)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 994)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 560)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 623)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 686)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 749)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 875)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 938)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 1001)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
}
}
}
- compute[((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 1)] = max((conv2d_nchw[1] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 2)] = max((conv2d_nchw[2] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 3)] = max((conv2d_nchw[3] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 4)] = max((conv2d_nchw[4] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 5)] = max((conv2d_nchw[5] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 6)] = max((conv2d_nchw[6] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 784)] = max((conv2d_nchw[7] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 785)] = max((conv2d_nchw[8] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 786)] = max((conv2d_nchw[9] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 787)] = max((conv2d_nchw[10] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 788)] = max((conv2d_nchw[11] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 789)] = max((conv2d_nchw[12] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 790)] = max((conv2d_nchw[13] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[((((((int)blockIdx.x) * 196) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 4) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ }
}
@@ -786,7 +1728,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 25.506 seconds)
+ **Total running time of the script:** ( 3 minutes 37.041 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
index c8d5d5126a..63477b54a4 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -643,7 +643,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.2480 8.2498 8.2512 8.2430 0.0036
+ 8.2647 8.2636 8.2699 8.2605 0.0039
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
index f130866510..c6a217ee30 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -662,7 +662,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 755.0323 755.0186 755.1288 754.9493 0.0739
+ 751.9946 752.1492 752.2620 751.5727 0.3019
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 23.690 seconds)
+ **Total running time of the script:** ( 1 minutes 23.537 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_x86.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
index 571578aa66..e2ae37e59b 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -397,76 +397,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 16) {
- let cse_var_1: int32 = ((i.inner.init*32) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [512], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
- }
+ for (i.inner.init: int32, 0, 32) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [512], [])[((i.inner.init*16) + j.init)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 16) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((i.inner*32) + (nb_j.inner*16))
- let cse_var_19: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_18: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i.inner*256))
- let cse_var_17: int32 = (cse_var_20 + 9)
- let cse_var_16: int32 = (cse_var_20 + 8)
- let cse_var_15: int32 = (cse_var_20 + 7)
- let cse_var_14: int32 = (cse_var_20 + 6)
- let cse_var_13: int32 = (cse_var_20 + 5)
- let cse_var_12: int32 = (cse_var_20 + 4)
- let cse_var_11: int32 = (cse_var_20 + 3)
- let cse_var_10: int32 = (cse_var_20 + 2)
- let cse_var_9: int32 = (cse_var_20 + 15)
- let cse_var_8: int32 = (cse_var_20 + 14)
- let cse_var_7: int32 = (cse_var_20 + 13)
- let cse_var_6: int32 = (cse_var_20 + 12)
- let cse_var_5: int32 = (cse_var_20 + 11)
- let cse_var_4: int32 = (cse_var_20 + 10)
- let cse_var_3: int32 = (cse_var_20 + 1)
- {
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[((placeholder_3[cse_var_19]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 32) {
+ for (j: int32, 0, 16) {
+ let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_3: int32 = ((i.inner*16) + j)
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 32) {
+ for (i1.inner: int32, 0, 16) {
+ let cse_var_4: int32 = ((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16)) + i1.inner)
+ compute[cse_var_4] = max((compute_5[((i0.inner*16) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
+ }
}
}
}
@@ -522,7 +476,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.675 ms
+ Execution time of this operator: 1.687 ms
diff --git a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
index 8e1ae8fd48..1a72a1724b 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:50.538** total execution time for **how_to_tune_with_autotvm** files:
+**00:40.300** total execution time for **how_to_tune_with_autotvm** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:50.499 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:40.264 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.024 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.006 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 9bc95decf3..e07a7abc7b 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -277,7 +277,8 @@ for this template
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ No: 1 GFLOPS: 770.17/770.17 result: MeasureResult(costs=(0.0003005842727272727,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.060486316680908, timestamp=1664229055.7021487) [('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8752720
+ No: 2 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -399,8 +400,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6796719
- No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7849843
+ No: 3 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -522,8 +523,10 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10029485
- No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7548392
+ No: 4 GFLOPS: 179.15/770.17 result: MeasureResult(costs=(0.0012922108846153847,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.834754705429077, timestamp=1664229058.745547) [('tile_f', [-1, 1, 16, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9400465
+ No: 5 GFLOPS: 63.54/770.17 result: MeasureResult(costs=(0.003643244534883721,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.53425931930542, timestamp=1664229069.9642303) [('tile_f', [-1, 2, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,434580
+ No: 6 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -645,9 +648,27 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,804032
- No: 4 GFLOPS: 155.19/155.19 result: MeasureResult(costs=(0.001491721361111111,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7438592910766602, timestamp=1664222304.0532215) [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1554894
- No: 5 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5367848
+ No: 7 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 404, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 373, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 297, in recv
+ raise TimeoutError()
+ TimeoutError
+
+ [('tile_f', [-1, 8, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1169851
+ No: 8 GFLOPS: 2.91/770.17 result: MeasureResult(costs=(0.07967788675,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.544188499450684, timestamp=1664229072.4680457) [('tile_f', [-1, 16, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9943784
+ No: 9 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -769,8 +790,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3604200
- No: 6 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6646888
+ No: 10 GFLOPS: 20.32/770.17 result: MeasureResult(costs=(0.011393937777777778,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1761364936828613, timestamp=1664229074.8046503) [('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,88001
+ No: 11 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -892,284 +914,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6080790
- No: 7 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
- blob = feval(*args)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 4: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1009
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:801
- File "../src/runtime/rpc/rpc_endpoint.cc", line 801
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
- During handling of the above exception, another exception occurred:
-
- Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
- costs = time_f(*args).results
- File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
- self.gen.throw(type, value, traceback)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 143, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 71, in get_function
- return self._sess.get_function(name)
- File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCallKeywords
- 18: _PyEval_EvalFrameDefault
- 17: _PyFunction_FastCallKeywords
- 16: _PyEval_EvalCodeWithName
- 15: _PyEval_EvalFrameDefault
- 14: 0x0000000000537c30
- 13: _PyObject_FastCallKeywords
- 12: 0x00007f5fe8c0ffa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:181
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1004
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:211
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/rpc/rpc_endpoint.cc:681
- File "../src/runtime/rpc/rpc_endpoint.cc", line 681
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
-
- Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 16, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5295354
- No: 8 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:379
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:365
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:260
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
- Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:379
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:365
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:260
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9097487
- No: 9 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 128, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7703791
+ No: 12 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1291,8 +1037,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5761087
- No: 10 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1290051
+ No: 13 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1414,9 +1160,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4791294
- No: 11 GFLOPS: 7.05/155.19 result: MeasureResult(costs=(0.0328588865,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.200226306915283, timestamp=1664222321.1937656) [('tile_f', [-1, 4, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3176250
- No: 12 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8924276
+ No: 14 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1538,9 +1283,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2537592
- No: 13 GFLOPS: 1.14/155.19 result: MeasureResult(costs=(0.2039020385,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.5208611488342285, timestamp=1664222328.9082692) [('tile_f', [-1, 2, 2, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7005234
- No: 14 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7519690
+ No: 15 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1662,8 +1406,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2872418
- No: 15 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4358846
+ No: 16 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1785,9 +1529,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9050097
- No: 16 GFLOPS: 2.14/155.19 result: MeasureResult(costs=(0.10805158225,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.197701692581177, timestamp=1664222330.6675668) [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7939073
- No: 17 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9732405
+ No: 17 GFLOPS: 77.72/770.17 result: MeasureResult(costs=(0.002978497742857143,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.431480884552002, timestamp=1664229077.624446) [('tile_f', [-1, 1, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8726470
+ No: 18 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1909,9 +1653,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5715521
- No: 18 GFLOPS: 7.05/155.19 result: MeasureResult(costs=(0.0328462485,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.154347896575928, timestamp=1664222335.0020185) [('tile_f', [-1, 2, 8, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8748718
- No: 19 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8073236
+ No: 19 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2033,8 +1776,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10435185
- No: 20 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6224286
+ No: 20 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2156,7 +1899,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,517853
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7923132
@@ -2211,9 +1954,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1554894
+ [('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8752720
Finish loading 20 records
- Time cost of this operator: 0.001856
+ Time cost of this operator: 0.000588
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
index 180885c51c..96ba6e32c8 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -327,10 +327,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.8 98.725 (1, 2, 10, 10, 3) 2 1 [311.8]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.059 0.969 (1, 6, 10, 10) 1 1 [3.059]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.307 (1, 1, 10, 10, 3) 1 1 [0.969]
- Total_time - 315.828 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.5 98.731 (1, 2, 10, 10, 3) 2 1 [311.5]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.043 0.965 (1, 6, 10, 10) 1 1 [3.043]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.961 0.305 (1, 1, 10, 10, 3) 1 1 [0.961]
+ Total_time - 315.505 - - - - -
@@ -394,10 +394,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.1 97.217 (1, 6, 10, 10, 1) 2 1 [100.1]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.908 1.853 (1, 6, 10, 10) 1 1 [1.908]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.958 0.93 (1, 1, 10, 10, 3) 1 1 [0.958]
- Total_time - 102.966 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.5 97.306 (1, 6, 10, 10, 1) 2 1 [100.5]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.783 1.727 (1, 6, 10, 10) 1 1 [1.783]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.999 0.968 (1, 1, 10, 10, 3) 1 1 [0.999]
+ Total_time - 103.283 - - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index aee170a73c..8d1b7ca664 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -225,7 +225,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmp9bcbxakb/images/random'
+ '/tmp/tmpjmh5en02/images/random'
@@ -316,7 +316,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0]
+ :alt: [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp9bcbxakb/images/target contains 8144 images
- /tmp/tmp9bcbxakb/images/random contains 5000 images
+ /tmp/tmpjmh5en02/images/target contains 8144 images
+ /tmp/tmpjmh5en02/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2169 - accuracy: 0.9224 - val_loss: 0.1190 - val_accuracy: 0.9615 - 47s/epoch - 144ms/step
+ 328/328 - 47s - loss: 0.3341 - accuracy: 0.9054 - val_loss: 0.2128 - val_accuracy: 0.9279 - 47s/epoch - 144ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.0982 - accuracy: 0.9638 - val_loss: 0.1383 - val_accuracy: 0.9535 - 43s/epoch - 132ms/step
+ 328/328 - 44s - loss: 0.1163 - accuracy: 0.9587 - val_loss: 0.1727 - val_accuracy: 0.9483 - 44s/epoch - 133ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0621 - accuracy: 0.9764 - val_loss: 0.1719 - val_accuracy: 0.9479 - 43s/epoch - 131ms/step
+ 328/328 - 44s - loss: 0.0665 - accuracy: 0.9749 - val_loss: 0.1130 - val_accuracy: 0.9641 - 44s/epoch - 133ms/step
- <keras.callbacks.History object at 0x7f63621e2e10>
+ <keras.callbacks.History object at 0x7fa703bfc450>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 40.144 seconds)
+ **Total running time of the script:** ( 4 minutes 31.974 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_train.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
index 4f5342cf80..86f465d007 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**05:50.563** total execution time for **how_to_work_with_microtvm** files:
+**05:42.183** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:40.144 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:31.974 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:57.167 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:56.913 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:09.090 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:09.128 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:04.159 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:04.166 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 2d9ead350e..c1fdf98978 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:44.357** total execution time for **how_to_work_with_relay** files:
+**00:44.049** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.006 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.504 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.720 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.016 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.625 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.523 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index 6b424d5e2c..d387b81cdd 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -261,7 +261,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f63405b38c0>
+ <function my_cuda_math_rule at 0x7fa69d763d40>
diff --git a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
index 1b43c985d6..51d96d3d21 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:07.981** total execution time for **how_to_work_with_schedules** files:
+**00:08.568** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.526 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:06.286 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.180 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.969 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.557 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.594 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.535 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.534 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.099 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.101 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.040 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.031 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.028 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.014 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.015 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index ebc1a7e027..b5e4fca535 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp0hrqtxso/input0.cc'\nsource_filename = \"/tmp/tmp0hrqtxso/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp_y938ge8/input0.cc'\nsource_filename = \"/tmp/tmp_y938ge8/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index 820e322089..ec8ed1f773 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:21.987** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:22.672** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.980 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:22.665 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 18ef9898a8..edcd3bb78b 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -289,7 +289,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 23.60s!
+ resnet18_v1 inference graph built in 24.27s!
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
index c988cf9c75..ccbda2d0a4 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -333,7 +333,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 16.53s!
+ yolov3-tiny inference graph built in 16.75s!
diff --git a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
index 39a565bf33..13d81c4b87 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**01:34.438** total execution time for **topic_vta_tutorials_frontend** files:
+**01:33.907** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.802 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.362 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:44.636 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:44.544 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
index 71867f2dd2..ad96a15903 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:03.048** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.072** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.633 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.662 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.416 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.410 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
index c191eefd95..456d00b878 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:00.743** total execution time for **topic_vta_tutorials** files:
+**00:00.745** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.391 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.397 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.352 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.349 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 1085c036dc..463fcee210 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -203,6 +203,13 @@ trials, we can load the best schedule from the log file and apply it.
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+
+ *E
+
@@ -326,7 +333,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 96.325 ms
+ Execution time of this operator: 93.814 ms
@@ -426,7 +433,7 @@ resume the status and do more 5 trials.
Resume search:
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
- *E
+
@@ -444,7 +451,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.597 seconds)
+ **Total running time of the script:** ( 1 minutes 14.488 seconds)
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index bef65668b0..71d7a6500f 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 12.58/12.58 result: MeasureResult(costs=(0.021346469200000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5053350925445557, timestamp=1664221080.281347) [('tile_y', [-1, 32]), ('tile_x', [-1, 128])],None,75
- No: 2 GFLOPS: 10.10/12.58 result: MeasureResult(costs=(0.0265824112,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5982592105865479, timestamp=1664221080.9241135) [('tile_y', [-1, 512]), ('tile_x', [-1, 512])],None,99
- No: 3 GFLOPS: 1.97/12.58 result: MeasureResult(costs=(0.136568222,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3049232959747314, timestamp=1664221084.218269) [('tile_y', [-1, 512]), ('tile_x', [-1, 8])],None,39
- No: 4 GFLOPS: 3.09/12.58 result: MeasureResult(costs=(0.0868321444,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5004169940948486, timestamp=1664221085.7739544) [('tile_y', [-1, 128]), ('tile_x', [-1, 8])],None,37
- No: 5 GFLOPS: 1.53/12.58 result: MeasureResult(costs=(0.175027406,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.939075231552124, timestamp=1664221088.9318147) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
- No: 6 GFLOPS: 13.81/13.81 result: MeasureResult(costs=(0.0194402746,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.48528003692626953, timestamp=1664221090.3495922) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
- No: 7 GFLOPS: 4.58/13.81 result: MeasureResult(costs=(0.0585868598,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.0872364044189453, timestamp=1664221092.376788) [('tile_y', [-1, 16]), ('tile_x', [-1, 16])],None,44
- No: 8 GFLOPS: 12.44/13.81 result: MeasureResult(costs=(0.021586282199999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6239986419677734, timestamp=1664221092.9347243) [('tile_y', [-1, 256]), ('tile_x', [-1, 128])],None,78
- No: 9 GFLOPS: 4.52/13.81 result: MeasureResult(costs=(0.059432939,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1062226295471191, timestamp=1664221094.294028) [('tile_y', [-1, 8]), ('tile_x', [-1, 16])],None,43
- No: 10 GFLOPS: 8.41/13.81 result: MeasureResult(costs=(0.0319145958,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8026306629180908, timestamp=1664221094.9684076) [('tile_y', [-1, 16]), ('tile_x', [-1, 64])],None,64
+ No: 1 GFLOPS: 10.08/10.08 result: MeasureResult(costs=(0.0266191396,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.663262128829956, timestamp=1664227814.8990576) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
+ No: 2 GFLOPS: 10.37/10.37 result: MeasureResult(costs=(0.0258787292,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7077369689941406, timestamp=1664227815.5305746) [('tile_y', [-1, 1]), ('tile_x', [-1, 128])],None,70
+ No: 3 GFLOPS: 3.93/10.37 result: MeasureResult(costs=(0.068234874,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2401442527770996, timestamp=1664227817.7171843) [('tile_y', [-1, 16]), ('tile_x', [-1, 8])],None,34
+ No: 4 GFLOPS: 12.68/12.68 result: MeasureResult(costs=(0.021162052,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6068720817565918, timestamp=1664227819.1688583) [('tile_y', [-1, 64]), ('tile_x', [-1, 128])],None,76
+ No: 5 GFLOPS: 1.69/12.68 result: MeasureResult(costs=(0.15863106580000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6720221042633057, timestamp=1664227821.9962373) [('tile_y', [-1, 1]), ('tile_x', [-1, 8])],None,30
+ No: 6 GFLOPS: 11.61/12.68 result: MeasureResult(costs=(0.0231142084,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5251588821411133, timestamp=1664227822.5337727) [('tile_y', [-1, 32]), ('tile_x', [-1, 32])],None,55
+ No: 7 GFLOPS: 10.52/12.68 result: MeasureResult(costs=(0.0255183186,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5874519348144531, timestamp=1664227824.0467129) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
+ No: 8 GFLOPS: 11.40/12.68 result: MeasureResult(costs=(0.0235384858,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5579280853271484, timestamp=1664227824.6405678) [('tile_y', [-1, 4]), ('tile_x', [-1, 512])],None,92
+ No: 9 GFLOPS: 9.86/12.68 result: MeasureResult(costs=(0.027221641799999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.543665885925293, timestamp=1664227825.3016732) [('tile_y', [-1, 1]), ('tile_x', [-1, 512])],None,90
+ No: 10 GFLOPS: 10.94/12.68 result: MeasureResult(costs=(0.024541742,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.500617504119873, timestamp=1664227825.866088) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 3aa4030da6..32074bd39f 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -320,7 +320,7 @@ standard deviation.
.. code-block:: none
- {'mean': 518.8625257100057, 'median': 519.0639800500094, 'std': 1.3911651244158252}
+ {'mean': 521.1109951399976, 'median': 520.7685348999973, 'std': 0.9562144510221742}
@@ -554,30 +554,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 9.61/ 22.80 GFLOPS | Progress: (4/20) | 8.60 s
[Task 1/25] Current/Best: 11.06/ 22.80 GFLOPS | Progress: (8/20) | 16.22 s
[Task 1/25] Current/Best: 19.12/ 22.80 GFLOPS | Progress: (12/20) | 19.73 s
[Task 1/25] Current/Best: 5.60/ 22.80 GFLOPS | Progress: (16/20) | 24.88 s
[Task 1/25] Current/Best: 22.67/ 22.80 GFLOPS | Progress: (20/20) | 26.78 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 11.72/ 15.73 GFLOPS | Progress: (4/20) | 3.53 s
[Task 2/25] Current/Best: 6.38/ 15.73 GFLOPS | Progress: (8/20) | 4.90 s
[Task 2/25] Current/Best: 9.80/ 18.27 GFLOPS | Progress: (12/20) | 6.66 s
[Task 2/25] Current/Best: 6.87/ 18.27 GFLOPS | Progress: (16/20) | 7.71 s
[Task 2/25] Current/Best: 12.78/ 18.27 GFLOPS | Progress: (20/20) | 9.34 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 20.01/ 20.01 GFLOPS | Progress: (4/20) | 3.77 s
[Task 3/25] Current/Best: 12.24/ 20.01 GFLOPS | Progress: (8/20) | 5.72 s
[Task 3/25] Current/Best: 14.94/ 20.01 GFLOPS | Progress: (12/20) | 7.94 s
[Task 3/25] Current/Best: 7.02/ 20.04 GFLOPS | Progress: (16/20) | 10.37 s
[Task 3/25] Current/Best: 11.26/ 22.05 GFLOPS | Progress: (20/20) | 12.50 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 19.64/ 19.64 GFLOPS | Progress: (4/20) | 4.24 s
[Task 4/25] Current/Best: 15.30/ 19.64 GFLOPS | Progress: (8/20) | 5.90 s
[Task 4/25] Current/Best: 11.00/ 21.91 GFLOPS | Progress: (12/20) | 9.74 s
[Task 4/25] Current/Best: 13.56/ 21.91 GFLOPS | Progress: (16/20) | 12.41 s
[Task 4/25] Current/Best: 9.61/ 21.91 GFLOPS | Progress: (20/20) | 14.17 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 17.29/ 17.98 GFLOPS | Progress: (4/20) | 3.68 s
[Task 5/25] Current/Best: 13.07/ 18.60 GFLOPS | Progress: (8/20) | 5.19 s
[Task 5/25] Current/Best: 11.44/ 18.60 GFLOPS | Progress: (12/20) | 7.04 s
[Task 5/25] Current/Best: 14.91/ 21.52 GFLOPS | Progress: (16/20) | 8.51 s
[Task 5/25] Current/Best: 4.88/ 21.52 GFLOPS | Progress: (20/20) | 10.63 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 9.49/ 12.36 GFLOPS | Progress: (4/20) | 4.14 s
[Task 6/25] Current/Best: 12.50/ 13.66 GFLOPS | Progress: (8/20) | 6.42 s
[Task 6/25] Current/Best: 11.40/ 17.97 GFLOPS | Progress: (12/20) | 10.20 s
[Task 6/25] Current/Best: 11.66/ 17.97 GFLOPS | Progress: (16/20) | 12.44 s
[Task 6/25] Current/Best: 8.52/ 17.97 GFLOPS | Progress: (20/20) | 15.61 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 6.38/ 15.10 GFLOPS | Progress: (4/20) | 4.01 s
[Task 7/25] Current/Best: 17.83/ 18.27 GFLOPS | Progress: (8/20) | 5.64 s
[Task 7/25] Current/Best: 8.43/ 19.21 GFLOPS | Progress: (12/20) | 7.80 s
[Task 7/25] Current/Best: 20.30/ 20.30 GFLOPS | Progress: (16/20) | 10.29 s
[Task 7/25] Current/Best: 14.98/ 20.30 GFLOPS | Progress: (20/20) | 12.34 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.80/ 11.79 GFLOPS | Progress: (4/20) | 8.23 s
[Task 8/25] Current/Best: 8.24/ 21.11 GFLOPS | Progress: (8/20) | 19.14 s
[Task 8/25] Current/Best: 13.74/ 21.11 GFLOPS | Progress: (12/20) | 22.94 s
[Task 8/25] Current/Best: 8.38/ 21.11 GFLOPS | Progress: (16/20) | 26.73 s
[Task 8/25] Current/Best: 11.33/ 21.11 GFLOPS | Progress: (20/20) | 28.90 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 8.84/ 18.55 GFLOPS | Progress: (4/20) | 3.54 s
[Task 9/25] Current/Best: 19.09/ 21.00 GFLOPS | Progress: (8/20) | 4.92 s
[Task 9/25] Current/Best: 17.64/ 21.00 GFLOPS | Progress: (12/20) | 11.75 s
[Task 9/25] Current/Best: 6.57/ 21.00 GFLOPS | Progress: (16/20) | 13.10 s
[Task 9/25] Current/Best: 10.80/ 21.00 GFLOPS | Progress: (20/20) | 19.64 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 3.82/ 13.77 GFLOPS | Progress: (4/20) | 4.02 s
[Task 10/25] Current/Best: 3.33/ 13.77 GFLOPS | Progress: (8/20) | 7.44 s
[Task 10/25] Current/Best: 12.21/ 15.67 GFLOPS | Progress: (12/20) | 8.77 s
[Task 10/25] Current/Best: 12.38/ 15.67 GFLOPS | Progress: (16/20) | 10.83 s
[Task 10/25] Current/Best: 10.59/ 22.20 GFLOPS | Progress: (20/20) | 14.39 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 16.92/ 21.35 GFLOPS | Progress: (4/20) | 3.83 s
[Task 11/25] Current/Best: 6.71/ 23.65 GFLOPS | Progress: (8/20) | 5.79 s
[Task 11/25] Current/Best: 18.87/ 23.65 GFLOPS | Progress: (12/20) | 8.42 s
[Task 11/25] Current/Best: 7.25/ 23.65 GFLOPS | Progress: (16/20) | 10.75 s
[Task 11/25] Current/Best: 10.98/ 23.65 GFLOPS | Progress: (20/20) | 13.10 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 15.88/ 20.51 GFLOPS | Progress: (4/20) | 4.37 s
[Task 12/25] Current/Best: 12.54/ 20.51 GFLOPS | Progress: (8/20) | 6.68 s
[Task 12/25] Current/Best: 21.77/ 21.77 GFLOPS | Progress: (12/20) | 8.35 s
[Task 12/25] Current/Best: 19.95/ 21.77 GFLOPS | Progress: (16/20) | 11.06 s
[Task 12/25] Current/Best: 10.01/ 21.77 GFLOPS | Progress: (20/20) | 14.00 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 17.17/ 17.17 GFLOPS | Progress: (4/20) | 5.47 s
[Task 13/25] Current/Best: 15.63/ 17.17 GFLOPS | Progress: (8/20) | 8.27 s
[Task 13/25] Current/Best: 9.95/ 17.17 GFLOPS | Progress: (12/20) | 10.34 s
[Task 13/25] Current/Best: 6.88/ 19.28 GFLOPS | Progress: (16/20) | 13.90 s
[Task 13/25] Current/Best: 3.09/ 19.28 GFLOPS | Progress: (20/20) | 18.41 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 12.27/ 16.05 GFLOPS | Progress: (4/20) | 4.16 s
[Task 14/25] Current/Best: 14.59/ 16.05 GFLOPS | Progress: (8/20) | 6.89 s
[Task 14/25] Current/Best: 12.74/ 16.05 GFLOPS | Progress: (12/20) | 10.00 s
[Task 14/25] Current/Best: 10.47/ 16.05 GFLOPS | Progress: (16/20) | 14.25 s
[Task 14/25] Current/Best: 7.49/ 16.05 GFLOPS | Progress: (20/20) | 17.56 s Done.
-
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 3.19/ 21.12 GFLOPS | Progress: (4/20) | 3.36 s
[Task 15/25] Current/Best: 17.92/ 21.12 GFLOPS | Progress: (8/20) | 5.24 s
[Task 15/25] Current/Best: 6.19/ 21.12 GFLOPS | Progress: (12/20) | 6.60 s
[Task 15/25] Current/Best: 15.21/ 21.12 GFLOPS | Progress: (16/20) | 8.00 s
[Task 15/25] Current/Best: 21.08/ 21.12 GFLOPS | Progress: (20/20) | 10.24 s Done.
-
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 9.46/ 17.85 GFLOPS | Progress: (4/20) | 3.81 s
[Task 16/25] Current/Best: 16.08/ 17.85 GFLOPS | Progress: (8/20) | 5.71 s
[Task 16/25] Current/Best: 14.28/ 17.85 GFLOPS | Progress: (12/20) | 6.99 s
[Task 16/25] Current/Best: 18.67/ 21.93 GFLOPS | Progress: (16/20) | 8.16 s
[Task 16/25] Current/Best: 12.60/ 21.93 GFLOPS | Progress: (20/20) | 11.13 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 17.01/ 17.01 GFLOPS | Progress: (4/20) | 4.26 s
[Task 17/25] Current/Best: 17.31/ 22.72 GFLOPS | Progress: (8/20) | 6.01 s
[Task 17/25] Current/Best: 15.27/ 22.72 GFLOPS | Progress: (12/20) | 8.10 s
[Task 17/25] Current/Best: 6.61/ 22.72 GFLOPS | Progress: (16/20) | 10.66 s
[Task 17/25] Current/Best: 10.50/ 22.72 GFLOPS | Progress: (20/20) | 13.13 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 19.54/ 19.54 GFLOPS | Progress: (4/20) | 3.92 s
[Task 18/25] Current/Best: 9.00/ 19.56 GFLOPS | Progress: (8/20) | 7.15 s
[Task 18/25] Current/Best: 5.81/ 19.85 GFLOPS | Progress: (12/20) | 9.21 s
[Task 18/25] Current/Best: 17.39/ 19.85 GFLOPS | Progress: (16/20) | 11.29 s
[Task 18/25] Current/Best: 9.64/ 19.85 GFLOPS | Progress: (20/20) | 15.92 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 18.99/ 18.99 GFLOPS | Progress: (4/20) | 4.50 s
[Task 19/25] Current/Best: 17.90/ 18.99 GFLOPS | Progress: (8/20) | 7.66 s
[Task 19/25] Current/Best: 10.15/ 18.99 GFLOPS | Progress: (12/20) | 11.53 s
[Task 19/25] Current/Best: 16.93/ 19.88 GFLOPS | Progress: (16/20) | 14.50 s
[Task 19/25] Current/Best: 9.44/ 23.30 GFLOPS | Progress: (20/20) | 17.86 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 14.01/ 18.33 GFLOPS | Progress: (4/20) | 4.81 s
[Task 20/25] Current/Best: 8.08/ 18.33 GFLOPS | Progress: (8/20) | 7.91 s
[Task 20/25] Current/Best: 17.40/ 18.33 GFLOPS | Progress: (12/20) | 10.51 s
[Task 20/25] Current/Best: 7.91/ 18.90 GFLOPS | Progress: (16/20) | 13.34 s
[Task 20/25] Current/Best: 13.28/ 18.90 GFLOPS | Progress: (20/20) | 14.98 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 16.49/ 16.87 GFLOPS | Progress: (4/20) | 4.10 s Done.
-
[Task 21/25] Current/Best: 10.64/ 19.52 GFLOPS | Progress: (8/20) | 5.72 s
[Task 21/25] Current/Best: 2.29/ 19.52 GFLOPS | Progress: (12/20) | 7.80 s
[Task 21/25] Current/Best: 8.61/ 21.28 GFLOPS | Progress: (16/20) | 11.10 s
[Task 21/25] Current/Best: 18.57/ 21.28 GFLOPS | Progress: (20/20) | 12.10 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 14.18/ 14.57 GFLOPS | Progress: (4/20) | 4.51 s
[Task 22/25] Current/Best: 9.51/ 16.04 GFLOPS | Progress: (8/20) | 7.08 s
[Task 22/25] Current/Best: 8.58/ 21.48 GFLOPS | Progress: (12/20) | 9.68 s
[Task 22/25] Current/Best: 16.72/ 21.48 GFLOPS | Progress: (16/20) | 11.98 s
[Task 22/25] Current/Best: 5.33/ 21.48 GFLOPS | Progress: (20/20) | 13.55 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 6.31/ 19.95 GFLOPS | Progress: (4/20) | 5.31 s
[Task 23/25] Current/Best: 11.13/ 19.95 GFLOPS | Progress: (8/20) | 7.62 s
[Task 23/25] Current/Best: 23.60/ 23.60 GFLOPS | Progress: (12/20) | 10.28 s
[Task 23/25] Current/Best: 12.15/ 23.60 GFLOPS | Progress: (16/20) | 13.42 s
[Task 23/25] Current/Best: 6.49/ 23.60 GFLOPS | Progress: (20/20) | 15.55 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 6.46/ 6.46 GFLOPS | Progress: (4/20) | 7.36 s
[Task 24/25] Current/Best: 1.88/ 7.79 GFLOPS | Progress: (8/20) | 18.09 s
[Task 24/25] Current/Best: 3.01/ 8.99 GFLOPS | Progress: (12/20) | 28.77 s
[Task 24/25] Current/Best: 9.96/ 9.96 GFLOPS | Progress: (16/20) | 30.69 s
[Task 24/25] Current/Best: 2.09/ 9.96 GFLOPS | Progress: (20/20) | 40.97 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 25/25] Current/Best: 8.73/ 8.73 GFLOPS | Progress: (4/20) | 13.96 s
[Task 25/25] Current/Best: 3.43/ 8.73 GFLOPS | Progress: (8/20) | 25.67 s
[Task 25/25] Current/Best: 5.09/ 8.73 GFLOPS | Progress: (12/20) | 30.31 s
[Task 25/25] Current/Best: 7.15/ 8.73 GFLOPS | Progress: (16/20) | 40.83 s
[Task 25/25] Current/Best: 1.56/ 8.73 GFLOPS | Progress: (20/20) | 51.52 s
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 8.36/ 14.79 GFLOPS | Progress: (4/20) | 7.32 s
[Task 1/25] Current/Best: 21.99/ 21.99 GFLOPS | Progress: (8/20) | 11.49 s
[Task 1/25] Current/Best: 11.66/ 21.99 GFLOPS | Progress: (12/20) | 13.73 s
[Task 1/25] Current/Best: 17.19/ 21.99 GFLOPS | Progress: (16/20) | 15.63 s
[Task 1/25] Current/Best: 10.62/ 21.99 GFLOPS | Progress: (20/20) | 17.68 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 21.52/ 21.52 GFLOPS | Progress: (4/20) | 3.55 s
[Task 2/25] Current/Best: 21.37/ 21.52 GFLOPS | Progress: (8/20) | 4.49 s
[Task 2/25] Current/Best: 16.26/ 21.52 GFLOPS | Progress: (12/20) | 5.61 s
[Task 2/25] Current/Best: 12.36/ 21.52 GFLOPS | Progress: (16/20) | 6.71 s
[Task 2/25] Current/Best: 14.67/ 21.52 GFLOPS | Progress: (20/20) | 8.91 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 8.01/ 18.03 GFLOPS | Progress: (4/20) | 4.51 s
[Task 3/25] Current/Best: 15.69/ 18.03 GFLOPS | Progress: (8/20) | 6.93 s
[Task 3/25] Current/Best: 12.38/ 18.03 GFLOPS | Progress: (12/20) | 8.97 s
[Task 3/25] Current/Best: 16.75/ 18.52 GFLOPS | Progress: (16/20) | 11.18 s
[Task 3/25] Current/Best: 6.60/ 23.79 GFLOPS | Progress: (20/20) | 13.06 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 19.70/ 19.70 GFLOPS | Progress: (4/20) | 5.50 s
[Task 4/25] Current/Best: 16.79/ 19.70 GFLOPS | Progress: (8/20) | 11.95 s
[Task 4/25] Current/Best: 9.19/ 19.70 GFLOPS | Progress: (12/20) | 13.89 s
[Task 4/25] Current/Best: 16.01/ 19.70 GFLOPS | Progress: (16/20) | 18.31 s
[Task 4/25] Current/Best: 13.92/ 19.70 GFLOPS | Progress: (20/20) | 20.91 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 18.60/ 18.60 GFLOPS | Progress: (4/20) | 3.53 s
[Task 5/25] Current/Best: 20.15/ 20.15 GFLOPS | Progress: (8/20) | 5.08 s
[Task 5/25] Current/Best: 10.77/ 21.43 GFLOPS | Progress: (12/20) | 6.82 s
[Task 5/25] Current/Best: 14.48/ 21.43 GFLOPS | Progress: (16/20) | 9.16 s
[Task 5/25] Current/Best: 14.56/ 21.43 GFLOPS | Progress: (20/20) | 10.91 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 3.84/ 14.94 GFLOPS | Progress: (4/20) | 4.79 s
[Task 6/25] Current/Best: 7.87/ 16.02 GFLOPS | Progress: (8/20) | 6.91 s
[Task 6/25] Current/Best: 4.17/ 16.02 GFLOPS | Progress: (12/20) | 9.36 s
[Task 6/25] Current/Best: 9.72/ 18.03 GFLOPS | Progress: (16/20) | 12.42 s
[Task 6/25] Current/Best: 16.51/ 18.03 GFLOPS | Progress: (20/20) | 14.36 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.30/ 18.45 GFLOPS | Progress: (4/20) | 4.02 s
[Task 7/25] Current/Best: 15.27/ 18.45 GFLOPS | Progress: (8/20) | 5.94 s
[Task 7/25] Current/Best: 11.86/ 18.45 GFLOPS | Progress: (12/20) | 8.19 s
[Task 7/25] Current/Best: 5.87/ 18.45 GFLOPS | Progress: (16/20) | 11.31 s
[Task 7/25] Current/Best: 16.22/ 21.88 GFLOPS | Progress: (20/20) | 13.55 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 12.82/ 12.82 GFLOPS | Progress: (4/20) | 7.36 s
[Task 8/25] Current/Best: 14.20/ 14.62 GFLOPS | Progress: (8/20) | 10.07 s
[Task 8/25] Current/Best: 4.61/ 14.62 GFLOPS | Progress: (12/20) | 15.55 s
[Task 8/25] Current/Best: 10.83/ 18.82 GFLOPS | Progress: (16/20) | 17.52 s
[Task 8/25] Current/Best: 2.49/ 18.82 GFLOPS | Progress: (20/20) | 20.17 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 13.51/ 20.53 GFLOPS | Progress: (4/20) | 3.62 s
[Task 9/25] Current/Best: 14.62/ 20.53 GFLOPS | Progress: (8/20) | 8.91 s
[Task 9/25] Current/Best: 9.50/ 20.53 GFLOPS | Progress: (12/20) | 11.02 s
[Task 9/25] Current/Best: 12.73/ 20.53 GFLOPS | Progress: (16/20) | 13.41 s
[Task 9/25] Current/Best: 8.16/ 20.53 GFLOPS | Progress: (20/20) | 15.33 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 20.49/ 20.49 GFLOPS | Progress: (4/20) | 3.16 s
[Task 10/25] Current/Best: 14.28/ 20.49 GFLOPS | Progress: (8/20) | 4.47 s
[Task 10/25] Current/Best: 17.97/ 20.49 GFLOPS | Progress: (12/20) | 5.95 s
[Task 10/25] Current/Best: 12.29/ 20.49 GFLOPS | Progress: (16/20) | 8.33 s
[Task 10/25] Current/Best: 16.32/ 20.49 GFLOPS | Progress: (20/20) | 10.01 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 6.24/ 17.16 GFLOPS | Progress: (4/20) | 3.83 s
[Task 11/25] Current/Best: 11.39/ 20.80 GFLOPS | Progress: (8/20) | 7.53 s
[Task 11/25] Current/Best: 17.78/ 23.37 GFLOPS | Progress: (12/20) | 9.41 s
[Task 11/25] Current/Best: 22.03/ 23.37 GFLOPS | Progress: (16/20) | 11.22 s
[Task 11/25] Current/Best: 9.93/ 23.37 GFLOPS | Progress: (20/20) | 13.35 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 10.30/ 13.95 GFLOPS | Progress: (4/20) | 10.44 s
[Task 12/25] Current/Best: 8.53/ 14.08 GFLOPS | Progress: (8/20) | 14.80 s
[Task 12/25] Current/Best: 18.13/ 18.13 GFLOPS | Progress: (12/20) | 18.03 s
[Task 12/25] Current/Best: 5.66/ 19.02 GFLOPS | Progress: (16/20) | 20.53 s
[Task 12/25] Current/Best: 21.23/ 21.23 GFLOPS | Progress: (20/20) | 22.64 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 12.50/ 12.50 GFLOPS | Progress: (4/20) | 4.65 s
[Task 13/25] Current/Best: 8.43/ 15.81 GFLOPS | Progress: (8/20) | 8.11 s
[Task 13/25] Current/Best: 9.26/ 17.80 GFLOPS | Progress: (12/20) | 10.86 s
[Task 13/25] Current/Best: 16.79/ 17.80 GFLOPS | Progress: (16/20) | 13.25 s
[Task 13/25] Current/Best: 16.69/ 21.28 GFLOPS | Progress: (20/20) | 16.17 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 14.08/ 15.92 GFLOPS | Progress: (4/20) | 3.61 s
[Task 14/25] Current/Best: 19.14/ 21.44 GFLOPS | Progress: (8/20) | 5.95 s
[Task 14/25] Current/Best: 11.44/ 21.44 GFLOPS | Progress: (12/20) | 8.42 s
[Task 14/25] Current/Best: 9.53/ 21.55 GFLOPS | Progress: (16/20) | 11.21 s
[Task 14/25] Current/Best: 2.68/ 21.55 GFLOPS | Progress: (20/20) | 14.10 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 9.08/ 16.25 GFLOPS | Progress: (4/20) | 4.42 s
[Task 15/25] Current/Best: 5.13/ 16.25 GFLOPS | Progress: (8/20) | 9.66 s
[Task 15/25] Current/Best: 12.28/ 16.25 GFLOPS | Progress: (12/20) | 12.75 s
[Task 15/25] Current/Best: 12.99/ 18.42 GFLOPS | Progress: (16/20) | 14.40 s
[Task 15/25] Current/Best: 9.11/ 18.42 GFLOPS | Progress: (20/20)
| 17.77 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+ Done.
+
[Task 16/25] Current/Best: 9.06/ 14.01 GFLOPS | Progress: (4/20) | 5.79 s
[Task 16/25] Current/Best: 14.64/ 14.64 GFLOPS | Progress: (8/20) | 7.21 s
[Task 16/25] Current/Best: 5.78/ 18.34 GFLOPS | Progress: (12/20) | 8.79 s
[Task 16/25] Current/Best: 10.24/ 18.34 GFLOPS | Progress: (16/20) | 10.04 s
[Task 16/25] Current/Best: 14.35/ 20.50 GFLOPS | Progress: (20/20) | 11.37 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 22.56/ 22.56 GFLOPS | Progress: (4/20) | 3.81 s
[Task 17/25] Current/Best: 19.77/ 22.56 GFLOPS | Progress: (8/20) | 6.09 s
[Task 17/25] Current/Best: 9.74/ 22.56 GFLOPS | Progress: (12/20) | 8.22 s
[Task 17/25] Current/Best: 18.63/ 22.56 GFLOPS | Progress: (16/20) | 11.90 s
[Task 17/25] Current/Best: 20.31/ 22.56 GFLOPS | Progress: (20/20) | 13.53 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 13.64/ 16.16 GFLOPS | Progress: (4/20) | 3.70 s
[Task 18/25] Current/Best: 19.82/ 19.82 GFLOPS | Progress: (8/20) | 7.21 s
[Task 18/25] Current/Best: 13.94/ 19.82 GFLOPS | Progress: (12/20) | 12.63 s
[Task 18/25] Current/Best: 10.57/ 19.82 GFLOPS | Progress: (16/20) | 14.41 s
[Task 18/25] Current/Best: 17.01/ 19.82 GFLOPS | Progress: (20/20) | 19.56 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 3.08/ 12.30 GFLOPS | Progress: (4/20) | 5.67 s
[Task 19/25] Current/Best: 4.04/ 19.44 GFLOPS | Progress: (8/20) | 9.09 s
[Task 19/25] Current/Best: 14.04/ 19.44 GFLOPS | Progress: (12/20) | 12.81 s
[Task 19/25] Current/Best: 15.85/ 19.44 GFLOPS | Progress: (16/20) | 15.85 s
[Task 19/25] Current/Best: 11.54/ 20.92 GFLOPS | Progress: (20/20) | 18.17 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 13.64/ 16.80 GFLOPS | Progress: (4/20) | 5.01 s
[Task 20/25] Current/Best: 13.25/ 16.80 GFLOPS | Progress: (8/20) | 6.81 s
[Task 20/25] Current/Best: 19.61/ 19.94 GFLOPS | Progress: (12/20) | 8.68 s
[Task 20/25] Current/Best: 19.99/ 19.99 GFLOPS | Progress: (16/20) | 12.64 s
[Task 20/25] Current/Best: 6.20/ 19.99 GFLOPS | Progress: (20/20) | 16.48 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 21.85/ 21.85 GFLOPS | Progress: (4/20) | 4.12 s
[Task 21/25] Current/Best: 13.20/ 21.85 GFLOPS | Progress: (8/20) | 5.59 s
[Task 21/25] Current/Best: 4.71/ 21.85 GFLOPS | Progress: (12/20) | 7.51 s
[Task 21/25] Current/Best: 5.33/ 21.85 GFLOPS | Progress: (16/20) | 11.48 s Done.
+
[Task 21/25] Current/Best: 15.40/ 21.85 GFLOPS | Progress: (20/20) | 13.65 s Done.
+
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 20.80/ 21.02 GFLOPS | Progress: (4/20) | 4.47 s
[Task 22/25] Current/Best: 16.86/ 21.02 GFLOPS | Progress: (8/20) | 5.89 s
[Task 22/25] Current/Best: 16.29/ 21.02 GFLOPS | Progress: (12/20) | 7.47 s
[Task 22/25] Current/Best: 20.64/ 21.02 GFLOPS | Progress: (16/20) | 9.12 s
[Task 22/25] Current/Best: 9.55/ 21.02 GFLOPS | Progress: (20/20) | 11.18 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 14.66/ 17.83 GFLOPS | Progress: (4/20) | 4.23 s
[Task 23/25] Current/Best: 19.11/ 20.46 GFLOPS | Progress: (8/20) | 6.36 s
[Task 23/25] Current/Best: 15.40/ 20.90 GFLOPS | Progress: (12/20) | 8.99 s
[Task 23/25] Current/Best: 10.15/ 20.90 GFLOPS | Progress: (16/20) | 11.44 s
[Task 23/25] Current/Best: 18.33/ 20.90 GFLOPS | Progress: (20/20) | 13.84 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 9.87/ 9.87 GFLOPS | Progress: (4/20) | 12.63 s
[Task 24/25] Current/Best: 3.01/ 9.87 GFLOPS | Progress: (8/20) | 24.38 s
[Task 24/25] Current/Best: 6.84/ 9.87 GFLOPS | Progress: (12/20) | 34.91 s
[Task 24/25] Current/Best: 1.61/ 9.87 GFLOPS | Progress: (16/20) | 39.55 s
[Task 24/25] Current/Best: 6.30/ 9.87 GFLOPS | Progress: (20/20) | 50.29 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 25/25] Current/Best: 8.95/ 9.19 GFLOPS | Progress: (4/20) | 3.94 s
[Task 25/25] Current/Best: 1.54/ 9.19 GFLOPS | Progress: (8/20) | 5.09 s
[Task 25/25] Current/Best: 3.51/ 9.19 GFLOPS | Progress: (12/20) | 15.84 s
[Task 25/25] Current/Best: 5.43/ 9.19 GFLOPS | Progress: (16/20) | 20.67 s
[Task 25/25] Current/Best: 5.81/ 9.34 GFLOPS | Progress: (20/20) | 31.39 s
@@ -731,8 +732,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 404.8580872799903, 'median': 404.96806209998795, 'std': 0.46157520536385244}
- unoptimized: {'mean': 518.8625257100057, 'median': 519.0639800500094, 'std': 1.3911651244158252}
+ optimized: {'mean': 418.28373845000215, 'median': 418.4676126499994, 'std': 1.1869006065156673}
+ unoptimized: {'mean': 521.1109951399976, 'median': 520.7685348999973, 'std': 0.9562144510221742}
@@ -755,7 +756,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 33.706 seconds)
+ **Total running time of the script:** ( 10 minutes 22.455 seconds)
.. _sphx_glr_download_tutorial_autotvm_relay_x86.py:
diff --git a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
index 5027a33454..2d2b829f30 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -282,7 +282,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.25e-07 secs/op
+ 1.246e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index d0c7d5fb40..e9eb080c4e 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0xdf95f00)), stage(b, placeholder(b, 0x20c2c900)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
+ [stage(a, placeholder(a, 0x5d6f790)), stage(b, placeholder(b, 0x21e33fd0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 39812d57a2..1f31112831 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
Computation times
=================
-**13:32.721** total execution time for **tutorial** files:
+**13:29.886** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:33.706 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:22.455 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:06.597 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:14.488 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.746 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:02.964 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:31.404 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:31.309 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:19.863 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:16.480 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.707 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.299 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.532 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.717 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.156 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.165 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 962a28fdeb..85cf2d87f2 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -295,7 +295,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
Numpy running time: 0.000007
- naive: 0.000009
+ naive: 0.000007
@@ -394,7 +394,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000006
+ parallel: 0.000009
@@ -501,10 +501,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 6.98187000125472e-06 1.0
- naive 8.8585e-06 1.268786155916399
- parallel 6.0335e-06 0.8641667631903363
- vector 2.46081e-05 3.5245714966875137
+ numpy 6.686270000955119e-06 1.0
+ naive 6.705800000000001e-06 1.0029209109177601
+ parallel 9.4853e-06 1.4186235372853693
+ vector 2.4708899999999996e-05 3.695468474421521
@@ -925,7 +925,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018330
+ Numpy running time: 0.019211
@@ -983,7 +983,7 @@ optimizations.
.. code-block:: none
- none: 3.310748
+ none: 3.556556
@@ -1086,7 +1086,7 @@ schedule.
.. code-block:: none
- blocking: 0.313165
+ blocking: 0.305761
@@ -1182,7 +1182,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.343321
+ vectorization: 0.341216
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1256,7 +1256,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.117550
+ loop permutation: 0.120383
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1355,7 +1355,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.108263
+ array packing: 0.110394
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1448,7 +1448,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110844
+ block caching: 0.111210
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1534,7 +1534,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.146597
+ parallelization: 0.147729
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1615,13 +1615,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.3107479534 1.0
- blocking 0.31316510859999996 0.09459044089369366
- vectorization 0.3433210997 0.10369895399238217
- loop permutation 0.1175499892 0.035505568788249516
- array packing 0.10826314970000002 0.032700510949140144
- block caching 0.11084393239999998 0.03348002746212314
- parallelization 0.1465966933 0.04427902557470475
+ none 3.5565555567000002 1.0
+ blocking 0.3057613949 0.08597121288432928
+ vectorization 0.3412164364 0.09594013954237296
+ loop permutation 0.12038301329999998 0.033848202672728395
+ array packing 0.1103942814 0.031039661728897855
+ block caching 0.11121035220000001 0.03126911710699891
+ parallelization 0.147728771 0.041537034539416054
@@ -1661,6 +1661,11 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 2.964 seconds)
+
+
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 00223f0a72..78c4b77c49 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-fd268137237d2f6fbff4aa4517449284330c3cd8
+e1f3f90588aa2d9bb71e0ca8ebc5baab865e054d
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index d6b92400b0..1ac7ede6f3 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -572,7 +572,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.741 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.158 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_keras.html b/docs/how_to/compile_models/from_keras.html
index d25eef5b4d..f8ce9277e0 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -493,7 +493,7 @@ pip install -U tensorflow --user
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 964ms/step
+1/1 [==============================] - 1s 990ms/step
Keras top-1 id: 285, class name: Egyptian cat
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index e3f95339b6..0061d9d43b 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -427,7 +427,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipb88ea9aa-58d1-4187-8dc8-4e4c1a95ed62 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip201fb619-2e31-4b70-b621-164130366954 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_oneflow.html b/docs/how_to/compile_models/from_oneflow.html
index d45a3bfa25..90ca7a6955 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -435,14 +435,12 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 15%|#5 | 6.33M/41.5M [00:00<00:00, 45.0MB/s]
- 26%|##5 | 10.6M/41.5M [00:00<00:00, 37.1MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:00, 35.8MB/s]
- 43%|####2 | 17.7M/41.5M [00:00<00:00, 34.6MB/s]
- 54%|#####3 | 22.3M/41.5M [00:00<00:00, 35.6MB/s]
- 62%|######1 | 25.7M/41.5M [00:00<00:00, 34.2MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 40.1MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 44.1MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 41.0MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 57.5MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 47.1MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 55.4MB/s]
+ 92%|#########2| 38.3M/41.5M [00:00<00:00, 53.6MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 52.2MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 07bf0ad933..2b4468d12a 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,9 +414,9 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 38%|###8 | 17.1M/44.7M [00:00<00:00, 179MB/s]
- 94%|#########4| 42.0M/44.7M [00:00<00:00, 227MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 222MB/s]
+ 38%|###7 | 16.8M/44.7M [00:00<00:00, 176MB/s]
+ 92%|#########2| 41.2M/44.7M [00:00<00:00, 223MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 220MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_tensorflow.html b/docs/how_to/compile_models/from_tensorflow.html
index ad835b63f7..6ba342a688 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -632,7 +632,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.186 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.618 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7f1d3d1b878694c201c614c807cdebc8/from_tensorflow.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_tensorflow.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index f7f1a37da0..adbd1200c7 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:11.822</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:13.816</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -336,43 +336,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:07.186</p></td>
+<td><p>01:05.618</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:03.741</p></td>
+<td><p>01:05.158</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:39.846</p></td>
+<td><p>00:40.721</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:28.484</p></td>
+<td><p>00:28.289</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:25.441</p></td>
+<td><p>00:26.998</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:25.392</p></td>
+<td><p>00:24.238</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:21.630</p></td>
+<td><p>00:23.016</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:19.720</p></td>
+<td><p>00:19.655</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:17.875</p></td>
+<td><p>00:17.455</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></td>
-<td><p>00:02.506</p></td>
+<td><p>00:02.667</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index 6b1e694ea3..2e4d51a238 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -649,7 +649,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.6996 15.6853 15.8359 15.6105 0.0685
+ 16.1807 16.2024 16.2717 16.0010 0.0771
</pre></div>
</div>
</div>
diff --git a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
index 6199874485..32199861ea 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,42 +436,15 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 3%|3 | 5.44M/170M [00:00<00:03, 56.8MB/s]
- 6%|6 | 10.9M/170M [00:00<00:02, 56.6MB/s]
- 10%|9 | 16.3M/170M [00:00<00:02, 56.8MB/s]
- 13%|#2 | 21.7M/170M [00:00<00:03, 50.7MB/s]
- 16%|#5 | 26.7M/170M [00:00<00:03, 45.2MB/s]
- 18%|#8 | 31.2M/170M [00:00<00:03, 46.0MB/s]
- 22%|##1 | 37.4M/170M [00:00<00:02, 51.3MB/s]
- 25%|##4 | 42.4M/170M [00:00<00:02, 49.1MB/s]
- 28%|##7 | 47.1M/170M [00:00<00:02, 48.8MB/s]
- 31%|###1 | 52.9M/170M [00:01<00:02, 52.1MB/s]
- 34%|###4 | 57.9M/170M [00:01<00:02, 52.1MB/s]
- 37%|###7 | 63.1M/170M [00:01<00:02, 52.7MB/s]
- 40%|#### | 68.1M/170M [00:01<00:02, 47.9MB/s]
- 43%|####2 | 72.8M/170M [00:01<00:02, 47.4MB/s]
- 46%|####5 | 77.4M/170M [00:01<00:02, 42.0MB/s]
- 48%|####8 | 82.2M/170M [00:01<00:02, 44.2MB/s]
- 51%|##### | 86.5M/170M [00:01<00:01, 43.8MB/s]
- 54%|#####4 | 92.3M/170M [00:01<00:01, 48.4MB/s]
- 58%|#####7 | 97.7M/170M [00:02<00:01, 49.8MB/s]
- 60%|###### | 102M/170M [00:02<00:01, 47.9MB/s]
- 63%|######3 | 107M/170M [00:02<00:01, 43.8MB/s]
- 66%|######5 | 112M/170M [00:02<00:01, 45.5MB/s]
- 69%|######9 | 117M/170M [00:02<00:01, 48.3MB/s]
- 72%|#######2 | 122M/170M [00:02<00:00, 50.1MB/s]
- 75%|#######4 | 127M/170M [00:02<00:01, 43.3MB/s]
- 78%|#######7 | 132M/170M [00:02<00:00, 40.2MB/s]
- 80%|#######9 | 136M/170M [00:03<00:00, 38.3MB/s]
- 82%|########2 | 139M/170M [00:03<00:00, 34.5MB/s]
- 84%|########4 | 143M/170M [00:03<00:00, 36.1MB/s]
- 86%|########6 | 147M/170M [00:03<00:00, 31.1MB/s]
- 88%|########8 | 150M/170M [00:03<00:00, 30.8MB/s]
- 91%|######### | 154M/170M [00:03<00:00, 33.2MB/s]
- 93%|#########3| 158M/170M [00:03<00:00, 37.0MB/s]
- 95%|#########5| 162M/170M [00:03<00:00, 36.9MB/s]
- 99%|#########8| 167M/170M [00:03<00:00, 41.8MB/s]
-100%|##########| 170M/170M [00:04<00:00, 44.2MB/s]
+ 11%|#1 | 19.4M/170M [00:00<00:00, 204MB/s]
+ 27%|##6 | 45.5M/170M [00:00<00:00, 245MB/s]
+ 41%|#### | 68.9M/170M [00:00<00:00, 221MB/s]
+ 53%|#####3 | 90.2M/170M [00:00<00:00, 183MB/s]
+ 64%|######3 | 108M/170M [00:00<00:00, 175MB/s]
+ 74%|#######4 | 126M/170M [00:00<00:00, 179MB/s]
+ 85%|########4 | 144M/170M [00:00<00:00, 160MB/s]
+ 97%|#########7| 165M/170M [00:00<00:00, 176MB/s]
+100%|##########| 170M/170M [00:00<00:00, 184MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -565,7 +538,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 1.771 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 2.909 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7795da4b258c8feff986668b95ef57ad/deploy_object_detection_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_object_detection_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized.html b/docs/how_to/deploy_models/deploy_prequantized.html
index 0423a2d10b..88b3301e39 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,8 +480,9 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 43%|####3 | 5.86M/13.6M [00:00<00:00, 61.3MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 71.4MB/s]
+ 26%|##5 | 3.50M/13.6M [00:00<00:00, 36.7MB/s]
+ 52%|#####1 | 7.00M/13.6M [00:00<00:00, 35.6MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 59.5MB/s]
</pre></div>
</div>
</div>
@@ -566,7 +567,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3669 90.3087 92.7059 90.1362 0.2949
+ 90.3164 90.2595 91.5742 90.1201 0.2217
</pre></div>
</div>
<div class="admonition note">
@@ -605,7 +606,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.708 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.305 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/fb8217c13f4351224c6cf3aacf1a87fc/deploy_prequantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized_tflite.html b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
index 2b2a128921..1c1318d6da 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -569,7 +569,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.7184 120.5215 126.8395 119.8450 0.8031
+ 118.9824 118.9099 122.4330 118.1992 0.5684
</pre></div>
</div>
<div class="admonition note">
@@ -597,7 +597,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 51.550 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 52.627 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/56691c7a27d45da61d112276334640d3/deploy_prequantized_tflite.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized_tflite.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_quantized.html b/docs/how_to/deploy_models/deploy_quantized.html
index d8eb91f939..9edcf0f3dc 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -507,7 +507,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 28.689 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 28.331 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7810ecf51bfc05f7d5e8a400ac3e815d/deploy_quantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_quantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
index 1b7da79214..78bcc0314f 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,22 +441,24 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|4 | 6575/132723 [00:00<00:01, 65742.38KB/s]
- 11%|#1 | 14940/132723 [00:00<00:01, 76273.68KB/s]
- 17%|#7 | 22568/132723 [00:00<00:01, 62426.81KB/s]
- 23%|##3 | 31001/132723 [00:00<00:01, 70046.20KB/s]
- 30%|##9 | 39446/132723 [00:00<00:01, 74827.99KB/s]
- 36%|###6 | 47994/132723 [00:00<00:01, 78251.67KB/s]
- 43%|####2 | 56474/132723 [00:00<00:00, 80310.70KB/s]
- 49%|####8 | 64917/132723 [00:00<00:00, 81584.51KB/s]
- 55%|#####5 | 73451/132723 [00:00<00:00, 82735.79KB/s]
- 62%|######1 | 82012/132723 [00:01<00:00, 83610.66KB/s]
- 68%|######8 | 90538/132723 [00:01<00:00, 84109.32KB/s]
- 75%|#######4 | 99085/132723 [00:01<00:00, 84516.41KB/s]
- 81%|########1 | 107557/132723 [00:01<00:00, 84447.82KB/s]
- 87%|########7 | 116016/132723 [00:01<00:00, 81439.18KB/s]
- 94%|#########3| 124581/132723 [00:01<00:00, 82668.72KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 80017.01KB/s]
+ 4%|4 | 5918/132723 [00:00<00:02, 59162.00KB/s]
+ 11%|# | 14177/132723 [00:00<00:01, 72938.53KB/s]
+ 16%|#6 | 21471/132723 [00:00<00:01, 61649.58KB/s]
+ 22%|##2 | 29767/132723 [00:00<00:01, 69220.19KB/s]
+ 28%|##7 | 36880/132723 [00:00<00:01, 67668.24KB/s]
+ 34%|###4 | 45224/132723 [00:00<00:01, 72675.89KB/s]
+ 40%|###9 | 52606/132723 [00:00<00:01, 64401.48KB/s]
+ 46%|####5 | 60925/132723 [00:00<00:01, 69703.92KB/s]
+ 51%|#####1 | 68111/132723 [00:01<00:01, 62558.62KB/s]
+ 56%|#####6 | 74620/132723 [00:01<00:00, 60467.28KB/s]
+ 62%|######2 | 82931/132723 [00:01<00:00, 66523.24KB/s]
+ 69%|######8 | 91302/132723 [00:01<00:00, 71274.97KB/s]
+ 74%|#######4 | 98619/132723 [00:01<00:00, 71027.31KB/s]
+ 81%|######## | 106942/132723 [00:01<00:00, 74513.42KB/s]
+ 86%|########6 | 114680/132723 [00:01<00:00, 68066.71KB/s]
+ 92%|#########2| 122529/132723 [00:01<00:00, 70902.87KB/s]
+ 98%|#########7| 129776/132723 [00:01<00:00, 55166.91KB/s]
+100%|##########| 132723/132723 [00:02<00:00, 64690.75KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -495,7 +497,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 37.498 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 41.829 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/cccb17d28e5e8b2e94ea8cd5ec59f6ed/deploy_ssd_gluoncv.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_ssd_gluoncv.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/sg_execution_times.html b/docs/how_to/deploy_models/sg_execution_times.html
index 41fdd74fb3..f9cbc4e29a 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>11:22.580</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:32.995</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -336,35 +336,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:01.771</p></td>
+<td><p>03:02.909</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:37.498</p></td>
+<td><p>02:41.829</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>01:51.550</p></td>
+<td><p>01:52.627</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></td>
-<td><p>01:28.689</p></td>
+<td><p>01:28.331</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:08.708</p></td>
+<td><p>01:11.305</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:29.972</p></td>
+<td><p>00:30.470</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:22.366</p></td>
+<td><p>00:23.101</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:22.019</p></td>
+<td><p>00:22.416</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 999f8fca67..faefe90c61 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -608,7 +608,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip59233f65-95eb-4c88-bd6d-dfcc99963730 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipadbdcc30-1499-4142-881c-575dcde9156d from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
</pre></div>
</div>
<p>It’s easy to execute MobileNet with native TVM:</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 87f73be456..099ce9af3b 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:41.757</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:42.495</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:38.499</p></td>
+<td><p>00:39.241</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></td>
-<td><p>00:02.306</p></td>
+<td><p>00:02.302</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index b3b8886d14..fd49f2bc02 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -512,10 +512,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6922us [6922us] (46.23%; 46.23%)
-FoldScaleAxis: 8050us [6us] (53.77%; 53.77%)
- FoldConstant: 8044us [1668us] (53.73%; 99.92%)
- InferType: 6376us [6376us] (42.59%; 79.26%)
+InferType: 7816us [7816us] (48.37%; 48.37%)
+FoldScaleAxis: 8343us [9us] (51.63%; 51.63%)
+ FoldConstant: 8334us [1794us] (51.57%; 99.89%)
+ InferType: 6540us [6540us] (40.47%; 78.47%)
</pre></div>
</div>
</div>
@@ -537,10 +537,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6393us [6393us] (44.70%; 44.70%)
-FoldScaleAxis: 7910us [5us] (55.30%; 55.30%)
- FoldConstant: 7905us [1672us] (55.27%; 99.94%)
- InferType: 6233us [6233us] (43.58%; 78.85%)
+InferType: 6499us [6499us] (44.88%; 44.88%)
+FoldScaleAxis: 7983us [6us] (55.12%; 55.12%)
+ FoldConstant: 7977us [1639us] (55.08%; 99.92%)
+ InferType: 6338us [6338us] (43.76%; 79.45%)
</pre></div>
</div>
<p>Register empty list to clear existing instruments.</p>
diff --git a/docs/how_to/optimize_operators/opt_conv_cuda.html b/docs/how_to/optimize_operators/opt_conv_cuda.html
index 0bdb2cceda..a1ae7299a5 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -564,7 +564,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.123455 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 50.563518 ms
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-optimize-operators-opt-conv-cuda-py">
diff --git a/docs/how_to/optimize_operators/opt_conv_tensorcore.html b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
index d6ba74cf53..f577076b7d 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -906,7 +906,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 7.605078 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.696150 ms
</pre></div>
</div>
</div>
diff --git a/docs/how_to/optimize_operators/opt_gemm.html b/docs/how_to/optimize_operators/opt_gemm.html
index 8b4162519c..51dfdc9e47 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -461,8 +461,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019227
-Baseline: 3.254608
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019119
+Baseline: 3.411100
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -522,7 +522,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.296242
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.312324
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -589,7 +589,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.335836
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.348305
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -650,7 +650,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.116821
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.121853
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -733,7 +733,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109916
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -819,7 +819,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111670
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110952
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -909,7 +909,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.148761
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146768
</pre></div>
</div>
<p>Here is the generated IR after parallelization.</p>
diff --git a/docs/how_to/optimize_operators/sg_execution_times.html b/docs/how_to/optimize_operators/sg_execution_times.html
index 55accd9392..1db12b3b60 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.402</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.879</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:31.954</p></td>
+<td><p>00:32.637</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></td>
-<td><p>00:01.320</p></td>
+<td><p>00:01.228</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></td>
-<td><p>00:01.129</p></td>
+<td><p>00:01.014</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
index b53c0e5dc4..7c36cc918a 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:25.646</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:40.525</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -336,27 +336,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>03:25.506</p></td>
+<td><p>03:37.041</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:23.690</p></td>
+<td><p>01:23.537</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>00:56.965</p></td>
+<td><p>00:57.406</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:21.465</p></td>
+<td><p>00:24.013</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:09.116</p></td>
+<td><p>00:09.413</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:08.904</p></td>
+<td><p>00:09.115</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
index fcea9d9b3f..fa47cde5d8 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
@@ -491,187 +491,707 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 128;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [768]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_4: int32 = (rc.outer.outer*1568)
- let cse_var_3: int32 = (ry.outer.outer*7)
- let cse_var_2: int32 = (rc.outer.outer*288)
- let cse_var_1: int32 = (ry.outer.outer*3)
+ for (rc.outer.outer: int32, 0, 8) {
+ for (rx.outer.outer: int32, 0, 3) {
+ let cse_var_1: int32 = (rc.outer.outer*3136)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) - 8)], 0f [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 560), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 672), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 784), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 896), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 776)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1120), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1232), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1344)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1344), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1456)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1456), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1568), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1680)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1680), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1792)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1792), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1904)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1904), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 896), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1008), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1120), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1232), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1456), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1680), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1792), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1904), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[(((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 96768)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2128), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2240), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2464), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2576), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2800), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2912), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_2 < 48), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3024), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 16)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 28)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 20)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 56), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 84)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 84), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 112), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 140)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 140), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 168), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 196), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 224), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 252)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 188)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 280), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 308)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 308), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 336), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 364)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 364), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 392), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 420)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 420), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 448), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 476)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 476), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 384)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 532)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 532), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 560), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 588), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 616), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 644)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 644), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 672), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 700)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 700), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 728)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 728), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 756)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 580)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 784), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 812)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 812), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 840)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 840), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 868)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 868), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 896), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 924)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 924), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 952)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 952), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 980), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 776)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1036)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1036), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1064)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1064), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1092)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1092), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1120), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1148)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1148), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1176), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1204)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1204), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1232), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1260)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 972)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1288)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1288), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1316)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1316), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1344)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1344), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1372), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1400)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1400), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1428)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1428), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1456)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1456), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1484)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1484), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1512)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 1168)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1540)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1540), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1568), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1596)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1596), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1624)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1624), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1652)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1652), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1680)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1680), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1708)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1708), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1736)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1736), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 1364)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1792)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1792), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1820)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1820), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1848)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1848), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1876)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1876), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1904)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1904), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1932)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1932), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1960), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 1988)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1988), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2016)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 1560)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2044)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2044), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2072)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2072), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2100)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2100), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2128)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2128), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2156)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2156), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2184)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2184), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2212)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2212), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2240)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2240), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2268)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 1756)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2296)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2296), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2324)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2324), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2352), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2380)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2380), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2408)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2408), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2436)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2436), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2464)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2464), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2492)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2492), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2520)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 1952)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2548)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2548), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2576)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2576), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2604)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2604), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2632)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2632), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2660)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2660), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2688)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2688), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2716)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2716), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2744)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2744), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2772)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 2148)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2800)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2800), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2828)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2828), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2856)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2856), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2884)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2884), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2912)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2912), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2940)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2940), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2968)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2968), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 2996)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2996), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3024)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 2344)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3052)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3052), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3080)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3080), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3108)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3108), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3136), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3164)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3164), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3192)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3192), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3220)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3220), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3248)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3248), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3276)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 2540)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3304)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3304), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3332)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3332), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3360)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3360), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3388)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3388), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3416)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3416), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3444)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3444), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3472)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3472), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3500)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3500), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3528)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 2736)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3556)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3556), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3584)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3584), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3612)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3612), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3640)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3640), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3668)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3668), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3696)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3696), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3724)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3724), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3752)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3752), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3780)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 2932)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3808)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3808), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3836)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3836), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3864)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3864), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 3)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3892)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3892), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3920), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3948)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3948), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 3976)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3976), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1[(threadIdx.x_1 + 4004)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 4004), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 5)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28 {
+ kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[(threadIdx.x_2*24)] = kernel[(((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer)]
+ kernel.shared_1[((threadIdx.x_2*24) + 1)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 3)]
+ kernel.shared_1[((threadIdx.x_2*24) + 2)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 6)]
+ kernel.shared_1[((threadIdx.x_2*24) + 3)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 9)]
+ kernel.shared_1[((threadIdx.x_2*24) + 4)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 12)]
+ kernel.shared_1[((threadIdx.x_2*24) + 5)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 15)]
+ kernel.shared_1[((threadIdx.x_2*24) + 6)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 18)]
+ kernel.shared_1[((threadIdx.x_2*24) + 7)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 21)]
+ kernel.shared_1[((threadIdx.x_2*24) + 8)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 24)]
+ kernel.shared_1[((threadIdx.x_2*24) + 9)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 27)]
+ kernel.shared_1[((threadIdx.x_2*24) + 10)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 30)]
+ kernel.shared_1[((threadIdx.x_2*24) + 11)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 33)]
+ kernel.shared_1[((threadIdx.x_2*24) + 12)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 36)]
+ kernel.shared_1[((threadIdx.x_2*24) + 13)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 39)]
+ kernel.shared_1[((threadIdx.x_2*24) + 14)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 42)]
+ kernel.shared_1[((threadIdx.x_2*24) + 15)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 45)]
+ kernel.shared_1[((threadIdx.x_2*24) + 16)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 48)]
+ kernel.shared_1[((threadIdx.x_2*24) + 17)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 51)]
+ kernel.shared_1[((threadIdx.x_2*24) + 18)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 54)]
+ kernel.shared_1[((threadIdx.x_2*24) + 19)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 57)]
+ kernel.shared_1[((threadIdx.x_2*24) + 20)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 60)]
+ kernel.shared_1[((threadIdx.x_2*24) + 21)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 63)]
+ kernel.shared_1[((threadIdx.x_2*24) + 22)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 66)]
+ kernel.shared_1[((threadIdx.x_2*24) + 23)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*576)) + (floormod(threadIdx.x_2, 8)*72)) + rx.outer.outer) + 69)]
}
- for (rc.outer.inner: int32, 0, 32) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1536)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1536)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1536)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1536)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1536)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1536)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1536)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1537)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1537)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1537)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1537)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1537)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1537)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1537)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1538)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1538)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1538)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1538)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1538)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1538)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1538)]))
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ if @tir.likely((threadIdx.x_2 < 4), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*24) + 672)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 32)*9)) + rx.outer.outer) + 13824)]
+ kernel.shared_1[((threadIdx.x_2*24) + 673)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 32)*9)) + rx.outer.outer) + 13827)]
+ kernel.shared_1[((threadIdx.x_2*24) + 674)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 32)*9)) + rx.outer.outer) + 13830)]
+ kernel.shared_1[((threadIdx.x_2*24) + 675)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 33)*9)) + rx.outer.outer) + 13824)]
+ kernel.shared_1[((threadIdx.x_2*24) + 676)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 33)*9)) + rx.outer.outer) + 13827)]
+ kernel.shared_1[((threadIdx.x_2*24) + 677)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 33)*9)) + rx.outer.outer) + 13830)]
+ kernel.shared_1[((threadIdx.x_2*24) + 678)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 34)*9)) + rx.outer.outer) + 13824)]
+ kernel.shared_1[((threadIdx.x_2*24) + 679)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 34)*9)) + rx.outer.outer) + 13827)]
+ kernel.shared_1[((threadIdx.x_2*24) + 680)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 34)*9)) + rx.outer.outer) + 13830)]
+ kernel.shared_1[((threadIdx.x_2*24) + 681)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 35)*9)) + rx.outer.outer) + 13824)]
+ kernel.shared_1[((threadIdx.x_2*24) + 682)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 35)*9)) + rx.outer.outer) + 13827)]
+ kernel.shared_1[((threadIdx.x_2*24) + 683)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 35)*9)) + rx.outer.outer) + 13830)]
+ kernel.shared_1[((threadIdx.x_2*24) + 684)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 36)*9)) + rx.outer.outer) + 13824)]
+ kernel.shared_1[((threadIdx.x_2*24) + 685)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 36)*9)) + rx.outer.outer) + 13827)]
+ kernel.shared_1[((threadIdx.x_2*24) + 686)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 36)*9)) + rx.outer.outer) + 13830)]
+ kernel.shared_1[((threadIdx.x_2*24) + 687)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 37)*9)) + rx.outer.outer) + 13824)]
+ kernel.shared_1[((threadIdx.x_2*24) + 688)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 37)*9)) + rx.outer.outer) + 13827)]
+ kernel.shared_1[((threadIdx.x_2*24) + 689)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 37)*9)) + rx.outer.outer) + 13830)]
+ kernel.shared_1[((threadIdx.x_2*24) + 690)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 38)*9)) + rx.outer.outer) + 13824)]
+ kernel.shared_1[((threadIdx.x_2*24) + 691)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 38)*9)) + rx.outer.outer) + 13827)]
+ kernel.shared_1[((threadIdx.x_2*24) + 692)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 38)*9)) + rx.outer.outer) + 13830)]
+ kernel.shared_1[((threadIdx.x_2*24) + 693)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 39)*9)) + rx.outer.outer) + 13824)]
+ kernel.shared_1[((threadIdx.x_2*24) + 694)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 39)*9)) + rx.outer.outer) + 13827)]
+ kernel.shared_1[((threadIdx.x_2*24) + 695)] = kernel[(((((blockIdx.x*18432) + (rc.outer.outer*576)) + (((threadIdx.x_2*8) + 39)*9)) + rx.outer.outer) + 13830)]
+ }
+ for (rc.outer.inner: int32, 0, 4) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*1008) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48))]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48))]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 45)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48))]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 147)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 210)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 273)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 336)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 399)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 462)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 525)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 588)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 651)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 714)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 777)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 36)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 840)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 39)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 903)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 42)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 966)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 532)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 595)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 658)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 721)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 784)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 847)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 910)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48))]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 98)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 161)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 224)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 287)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 350)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 413)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 476)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 539)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 602)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 665)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 728)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 791)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 36)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 854)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 39)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 917)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 980)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48))]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 231)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 294)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 357)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 420)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 483)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 546)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 609)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 672)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 735)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 798)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 861)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 924)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 987)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 46)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 37)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 40)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 43)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 147)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 210)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 273)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 336)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 399)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 462)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 525)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 588)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 651)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 714)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 777)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 840)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 903)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 966)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 46)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 532)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 595)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 658)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 721)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 784)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 37)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 847)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 40)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 910)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 43)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 98)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 161)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 224)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 287)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 350)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 413)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 476)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 539)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 602)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 665)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 728)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 791)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 854)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 40)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 917)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 43)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 980)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 231)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 294)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 357)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 420)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 483)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 546)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 609)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 672)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 735)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 798)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 37)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 861)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 924)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 987)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 46)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 49)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 112)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 238)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 301)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 364)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 427)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 490)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 553)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 616)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 679)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 742)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 805)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 37)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 868)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 40)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 931)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 43)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 994)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 47)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 147)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 210)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 273)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 336)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 399)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 462)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 525)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 588)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 651)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 714)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 777)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 38)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 840)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 41)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 903)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 44)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 966)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 532)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 595)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 658)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 721)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 784)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 847)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 910)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 47)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 98)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 161)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 224)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 287)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 350)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 413)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 476)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 539)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 602)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 665)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 728)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 791)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 38)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 854)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 41)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 917)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 44)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 980)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 231)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 294)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 357)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 420)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 483)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 546)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 609)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 672)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 735)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 798)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 861)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 41)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 924)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 44)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 987)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 49)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 112)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 238)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 301)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 364)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 427)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 490)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 553)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 616)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 679)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 742)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 805)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 38)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 868)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 931)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 994)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 47)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 371)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 434)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 560)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 623)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 686)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 749)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 38)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 875)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 41)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 938)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 44)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + floormod(threadIdx.x, 7)) + 1001)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*48)) + 47)]))
}
}
}
}
- compute[((blockIdx.x*1568) + (threadIdx.x*7))] = max((conv2d_nchw_1[0] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 1)] = max((conv2d_nchw_1[1] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 2)] = max((conv2d_nchw_1[2] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 3)] = max((conv2d_nchw_1[3] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 4)] = max((conv2d_nchw_1[4] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 5)] = max((conv2d_nchw_1[5] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 6)] = max((conv2d_nchw_1[6] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 784)] = max((conv2d_nchw_1[7] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 785)] = max((conv2d_nchw_1[8] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 786)] = max((conv2d_nchw_1[9] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 787)] = max((conv2d_nchw_1[10] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 788)] = max((conv2d_nchw_1[11] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 789)] = max((conv2d_nchw_1[12] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 790)] = max((conv2d_nchw_1[13] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
+ for (i2.inner: int32, 0, 7) {
+ compute[((((blockIdx.x*196) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((blockIdx.x*4) + floordiv(threadIdx.x, 7))]), 0f32)
+ }
}
}
</pre></div>
@@ -707,7 +1227,7 @@ cooperative fetching, unrolling and operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.213 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.306 ms
</pre></div>
</div>
</div>
@@ -738,35 +1258,35 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
-conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=7)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=7)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=32)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
-compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
-compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -783,16 +1303,16 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=24)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=28)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=28)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -810,10 +1330,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[2016];
- __shared__ float kernel_shared[3072];
+extern "C" __global__ void __launch_bounds__(28) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[7];
+ __shared__ float pad_temp_shared[4032];
+ __shared__ float kernel_shared[768];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -821,125 +1341,547 @@ extern "C" __global__ void __launch_bounds__(112) default_function_ker
conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 112) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 336) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 448) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 560) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 672) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 896) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 776)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1120) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1232)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1232) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1344) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1456)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1456) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1680)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1680) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1904)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1904) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1008) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 96768)];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2576) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2800) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 48) {
- kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3024) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 144)];
+ pad_temp_shared[((int)threadIdx.x)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 28)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 56) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 84)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 84) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 112) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 140)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 140) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 168) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 196) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 224) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 252)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 188)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 280) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 308)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 308) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 336) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 364)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 364) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 392) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 420)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 420) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 448) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 476)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 476) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 504)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 384)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 532)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 532) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 560) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 588) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 616) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 644)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 644) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 672) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 700)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 700) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 728)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 728) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 756)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 580)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 812)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 812) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 840)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 840) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 868)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 868) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 896)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 896) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 924)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 924) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 952)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 952) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 980) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1008)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 776)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1036)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1036) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1064)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1064) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1092)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1092) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1120) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1148)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1148) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1176) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1204)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1204) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1232)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1232) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1260)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 972)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1288)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1288) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1316)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1316) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1344) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1372) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1400)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1400) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1428)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1428) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1456)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1456) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1484)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1484) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1512)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1168)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1540)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1540) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1596)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1596) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1624)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1624) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1652)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1652) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1680)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1680) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1708)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1708) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1736)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1736) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1764)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1364)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1792) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1820)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1820) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1848)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1848) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1876)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1876) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1904)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1904) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1932)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1932) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1960) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1988)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1988) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2016)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1560)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2044)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2044) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2072)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2072) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2100)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2100) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2128)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2128) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2156)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2156) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2184)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2184) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2212)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2212) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2240)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2240) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2268)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1756)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2296)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2296) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2324)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2324) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2380)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2380) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2408)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2408) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2436)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2436) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2464)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2464) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2492)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2492) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2520)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1952)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2548)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2548) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2576)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2576) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2604)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2604) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2632)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2632) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2660)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2660) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2688)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2688) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2716)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2716) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2744)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2744) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2772)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2148)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2800)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2800) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2828)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2828) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2856)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2856) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2884)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2884) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2912)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2912) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2940)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2940) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2968)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2968) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2996)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2996) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3024)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2344)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3052)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3052) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3080)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3080) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3108)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3108) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3164)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3164) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3192)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3192) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3220)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3220) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3248)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3248) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3276)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2540)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3304)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3304) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3332)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3332) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3360)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3360) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3388)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3388) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3416)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3416) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3444)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3444) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3472)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3472) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3500)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3500) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3528)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2736)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3556)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3556) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3584)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3584) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3612)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3612) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3640)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3640) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3668)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3668) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3696)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3696) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3724)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3724) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3752)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3752) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3780)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2932)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3808)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3808) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3836)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3836) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3864)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3864) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 13)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3892)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3892) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3920)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3948)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3948) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3976)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3976) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 4004)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 4004) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 27)] : 0.000000e+00f);
+ kernel_shared[(((int)threadIdx.x) * 24)] = kernel[(((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 1)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 3)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 2)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 6)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 3)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 9)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 4)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 12)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 5)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 15)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 6)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 18)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 7)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 21)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 8)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 24)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 9)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 27)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 10)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 30)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 11)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 33)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 12)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 36)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 13)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 39)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 14)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 42)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 15)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 45)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 16)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 48)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 17)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 51)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 18)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 54)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 19)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 57)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 20)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 60)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 21)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 63)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 22)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 66)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 23)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 7) * 72)) + rx_outer_outer) + 69)];
+ if (((int)threadIdx.x) < 4) {
+ kernel_shared[((((int)threadIdx.x) * 24) + 672)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14112)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 673)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14115)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 674)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14118)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 675)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14121)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 676)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14124)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 677)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14127)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 678)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14130)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 679)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14133)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 680)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14136)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 681)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14139)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 682)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14142)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 683)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14145)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 684)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14148)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 685)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14151)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 686)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14154)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 687)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14157)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 688)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14160)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 689)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14163)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 690)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14166)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 691)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14169)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 692)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14172)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 693)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14175)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 694)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14178)];
+ kernel_shared[((((int)threadIdx.x) * 24) + 695)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 72)) + rx_outer_outer) + 14181)];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 32; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1538)]));
+ for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 147)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 210)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 273)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 336)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 399)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 462)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 525)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 588)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 651)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 714)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 777)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 840)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 903)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 966)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 532)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 595)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 658)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 721)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 784)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 847)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 910)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 161)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 224)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 287)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 350)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 413)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 476)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 539)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 602)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 665)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 728)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 791)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 854)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 917)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 980)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 231)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 294)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 357)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 420)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 483)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 546)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 609)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 672)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 735)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 798)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 861)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 924)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 987)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 147)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 210)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 273)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 336)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 399)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 462)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 525)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 588)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 651)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 714)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 777)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 840)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 903)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 966)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 532)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 595)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 658)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 721)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 784)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 847)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 910)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 161)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 224)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 287)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 350)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 413)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 476)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 539)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 602)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 665)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 728)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 791)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 854)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 917)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 980)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 231)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 294)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 357)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 420)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 483)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 546)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 609)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 672)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 735)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 798)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 861)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 924)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 987)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 112)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 238)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 301)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 364)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 427)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 490)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 553)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 616)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 679)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 742)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 805)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 868)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 931)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 994)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 147)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 210)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 273)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 336)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 399)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 462)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 525)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 588)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 651)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 714)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 777)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 840)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 903)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 966)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 532)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 595)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 658)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 721)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 784)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 847)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 910)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 161)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 224)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 287)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 350)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 413)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 476)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 539)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 602)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 665)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 728)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 791)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 854)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 917)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 980)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 231)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 294)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 357)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 420)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 483)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 546)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 609)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 672)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 735)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 798)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 861)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 924)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 987)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 112)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 238)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 301)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 364)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 427)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 490)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 553)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 616)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 679)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 742)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 805)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 868)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 931)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 994)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 560)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 623)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 686)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 749)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 875)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 938)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((int)threadIdx.x) % 7)) + 1001)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
}
}
}
- compute[((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 1)] = max((conv2d_nchw[1] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 2)] = max((conv2d_nchw[2] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 3)] = max((conv2d_nchw[3] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 4)] = max((conv2d_nchw[4] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 5)] = max((conv2d_nchw[5] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 6)] = max((conv2d_nchw[6] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 784)] = max((conv2d_nchw[7] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 785)] = max((conv2d_nchw[8] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 786)] = max((conv2d_nchw[9] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 787)] = max((conv2d_nchw[10] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 788)] = max((conv2d_nchw[11] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 789)] = max((conv2d_nchw[12] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 790)] = max((conv2d_nchw[13] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[((((((int)blockIdx.x) * 196) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 4) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ }
}
</pre></div>
</div>
@@ -975,7 +1917,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 25.506 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 37.041 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e3e540f3b477c0c52d8eb73e674e8ffd/tune_conv2d_layer_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_conv2d_layer_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
index 74e82a69b7..51b78374c8 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -902,7 +902,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.2480 8.2498 8.2512 8.2430 0.0036
+ 8.2647 8.2636 8.2699 8.2605 0.0039
</pre></div>
</div>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index 7a1e4cee2d..27d1fce326 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -921,7 +921,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 755.0323 755.0186 755.1288 754.9493 0.0739
+ 751.9946 752.1492 752.2620 751.5727 0.3019
</pre></div>
</div>
</div>
@@ -943,7 +943,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.690 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.537 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e416b94ca1090b0897c0f6e0df95b911/tune_network_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_x86.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
index 4642d5acac..108c1d378c 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,76 +625,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 16) {
- let cse_var_1: int32 = ((i.inner.init*32) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [512], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
- }
+ for (i.inner.init: int32, 0, 32) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [512], [])[((i.inner.init*16) + j.init)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 16) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((i.inner*32) + (nb_j.inner*16))
- let cse_var_19: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_18: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i.inner*256))
- let cse_var_17: int32 = (cse_var_20 + 9)
- let cse_var_16: int32 = (cse_var_20 + 8)
- let cse_var_15: int32 = (cse_var_20 + 7)
- let cse_var_14: int32 = (cse_var_20 + 6)
- let cse_var_13: int32 = (cse_var_20 + 5)
- let cse_var_12: int32 = (cse_var_20 + 4)
- let cse_var_11: int32 = (cse_var_20 + 3)
- let cse_var_10: int32 = (cse_var_20 + 2)
- let cse_var_9: int32 = (cse_var_20 + 15)
- let cse_var_8: int32 = (cse_var_20 + 14)
- let cse_var_7: int32 = (cse_var_20 + 13)
- let cse_var_6: int32 = (cse_var_20 + 12)
- let cse_var_5: int32 = (cse_var_20 + 11)
- let cse_var_4: int32 = (cse_var_20 + 10)
- let cse_var_3: int32 = (cse_var_20 + 1)
- {
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[((placeholder_3[cse_var_19]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 32) {
+ for (j: int32, 0, 16) {
+ let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_3: int32 = ((i.inner*16) + j)
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 32) {
+ for (i1.inner: int32, 0, 16) {
+ let cse_var_4: int32 = ((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16)) + i1.inner)
+ compute[cse_var_4] = max((compute_5[((i0.inner*16) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
+ }
}
}
}
@@ -732,7 +686,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.675 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.687 ms
</pre></div>
</div>
<div class="admonition note">
diff --git a/docs/how_to/tune_with_autotvm/sg_execution_times.html b/docs/how_to/tune_with_autotvm/sg_execution_times.html
index 3029c1d64f..827250fc5e 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:50.538</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:40.300</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:50.499</p></td>
+<td><p>00:40.264</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.024</p></td>
+<td><p>00:00.020</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
-<td><p>00:00.005</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index febd78734c..ad3ac3206c 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -557,7 +557,8 @@ for this template</p>
waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+No: 1 GFLOPS: 770.17/770.17 result: MeasureResult(costs=(0.0003005842727272727,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.060486316680908, timestamp=1664229055.7021487) [('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8752720
+No: 2 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -679,8 +680,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6796719
-No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7849843
+No: 3 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -802,8 +803,10 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10029485
-No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7548392
+No: 4 GFLOPS: 179.15/770.17 result: MeasureResult(costs=(0.0012922108846153847,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.834754705429077, timestamp=1664229058.745547) [('tile_f', [-1, 1, 16, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9400465
+No: 5 GFLOPS: 63.54/770.17 result: MeasureResult(costs=(0.003643244534883721,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.53425931930542, timestamp=1664229069.9642303) [('tile_f', [-1, 2, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,434580
+No: 6 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -925,9 +928,27 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,804032
-No: 4 GFLOPS: 155.19/155.19 result: MeasureResult(costs=(0.001491721361111111,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7438592910766602, timestamp=1664222304.0532215) [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1554894
-No: 5 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5367848
+No: 7 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 404, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 373, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 297, in recv
+ raise TimeoutError()
+TimeoutError
+
+ [('tile_f', [-1, 8, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1169851
+No: 8 GFLOPS: 2.91/770.17 result: MeasureResult(costs=(0.07967788675,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.544188499450684, timestamp=1664229072.4680457) [('tile_f', [-1, 16, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9943784
+No: 9 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1049,8 +1070,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3604200
-No: 6 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6646888
+No: 10 GFLOPS: 20.32/770.17 result: MeasureResult(costs=(0.011393937777777778,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1761364936828613, timestamp=1664229074.8046503) [('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,88001
+No: 11 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1172,284 +1194,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6080790
-No: 7 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
- blob = feval(*args)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 4: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1009
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:801
- File "../src/runtime/rpc/rpc_endpoint.cc", line 801
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
-During handling of the above exception, another exception occurred:
-
-Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
- costs = time_f(*args).results
- File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
- self.gen.throw(type, value, traceback)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 143, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 71, in get_function
- return self._sess.get_function(name)
- File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCallKeywords
- 18: _PyEval_EvalFrameDefault
- 17: _PyFunction_FastCallKeywords
- 16: _PyEval_EvalCodeWithName
- 15: _PyEval_EvalFrameDefault
- 14: 0x0000000000537c30
- 13: _PyObject_FastCallKeywords
- 12: 0x00007f5fe8c0ffa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:181
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1004
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:211
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/rpc/rpc_endpoint.cc:681
- File "../src/runtime/rpc/rpc_endpoint.cc", line 681
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
-
-Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 16, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5295354
-No: 8 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:379
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:365
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:260
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
-Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:379
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:365
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:260
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9097487
-No: 9 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 128, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7703791
+No: 12 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1571,8 +1317,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5761087
-No: 10 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1290051
+No: 13 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1694,9 +1440,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4791294
-No: 11 GFLOPS: 7.05/155.19 result: MeasureResult(costs=(0.0328588865,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.200226306915283, timestamp=1664222321.1937656) [('tile_f', [-1, 4, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3176250
-No: 12 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8924276
+No: 14 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1818,9 +1563,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2537592
-No: 13 GFLOPS: 1.14/155.19 result: MeasureResult(costs=(0.2039020385,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.5208611488342285, timestamp=1664222328.9082692) [('tile_f', [-1, 2, 2, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7005234
-No: 14 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7519690
+No: 15 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1942,8 +1686,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2872418
-No: 15 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4358846
+No: 16 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2065,9 +1809,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9050097
-No: 16 GFLOPS: 2.14/155.19 result: MeasureResult(costs=(0.10805158225,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.197701692581177, timestamp=1664222330.6675668) [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7939073
-No: 17 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9732405
+No: 17 GFLOPS: 77.72/770.17 result: MeasureResult(costs=(0.002978497742857143,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.431480884552002, timestamp=1664229077.624446) [('tile_f', [-1, 1, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8726470
+No: 18 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2189,9 +1933,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5715521
-No: 18 GFLOPS: 7.05/155.19 result: MeasureResult(costs=(0.0328462485,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.154347896575928, timestamp=1664222335.0020185) [('tile_f', [-1, 2, 8, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8748718
-No: 19 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8073236
+No: 19 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2313,8 +2056,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10435185
-No: 20 GFLOPS: 0.00/155.19 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6224286
+No: 20 GFLOPS: 0.00/770.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2436,7 +2179,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,517853
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7923132
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2475,9 +2218,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1554894
+[('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8752720
Finish loading 20 records
-Time cost of this operator: 0.001856
+Time cost of this operator: 0.000588
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index 4167e8c92d..45948e997e 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -582,10 +582,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.8 98.725 (1, 2, 10, 10, 3) 2 1 [311.8]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.059 0.969 (1, 6, 10, 10) 1 1 [3.059]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.307 (1, 1, 10, 10, 3) 1 1 [0.969]
-Total_time - 315.828 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.5 98.731 (1, 2, 10, 10, 3) 2 1 [311.5]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.043 0.965 (1, 6, 10, 10) 1 1 [3.043]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.961 0.305 (1, 1, 10, 10, 3) 1 1 [0.961]
+Total_time - 315.505 - - - - -
</pre></div>
</div>
</div>
@@ -636,10 +636,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.1 97.217 (1, 6, 10, 10, 1) 2 1 [100.1]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.908 1.853 (1, 6, 10, 10) 1 1 [1.908]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.958 0.93 (1, 1, 10, 10, 3) 1 1 [0.958]
-Total_time - 102.966 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.5 97.306 (1, 6, 10, 10, 1) 2 1 [100.5]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.783 1.727 (1, 6, 10, 10) 1 1 [1.783]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.999 0.968 (1, 1, 10, 10, 3) 1 1 [0.999]
+Total_time - 103.283 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index dc80531d50..ad7e6e1924 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -516,7 +516,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp9bcbxakb/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpjmh5en02/images/random'
</pre></div>
</div>
</div>
@@ -576,8 +576,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp9bcbxakb/images/target contains 8144 images
-/tmp/tmp9bcbxakb/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpjmh5en02/images/target contains 8144 images
+/tmp/tmpjmh5en02/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -689,13 +689,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 47s - loss: 0.2169 - accuracy: 0.9224 - val_loss: 0.1190 - val_accuracy: 0.9615 - 47s/epoch - 144ms/step
+328/328 - 47s - loss: 0.3341 - accuracy: 0.9054 - val_loss: 0.2128 - val_accuracy: 0.9279 - 47s/epoch - 144ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.0982 - accuracy: 0.9638 - val_loss: 0.1383 - val_accuracy: 0.9535 - 43s/epoch - 132ms/step
+328/328 - 44s - loss: 0.1163 - accuracy: 0.9587 - val_loss: 0.1727 - val_accuracy: 0.9483 - 44s/epoch - 133ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0621 - accuracy: 0.9764 - val_loss: 0.1719 - val_accuracy: 0.9479 - 43s/epoch - 131ms/step
+328/328 - 44s - loss: 0.0665 - accuracy: 0.9749 - val_loss: 0.1130 - val_accuracy: 0.9641 - 44s/epoch - 133ms/step
-<keras.callbacks.History object at 0x7f63621e2e10>
+<keras.callbacks.History object at 0x7fa703bfc450>
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 40.144 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 31.974 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-train-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/b52cec46baf4f78d6bcd94cbe269c8a6/micro_train.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_train.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index acb598253c..77c21d0346 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:50.563</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:42.183</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,19 +336,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:40.144</p></td>
+<td><p>04:31.974</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:57.167</p></td>
+<td><p>00:56.913</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:09.090</p></td>
+<td><p>00:09.128</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:04.159</p></td>
+<td><p>00:04.166</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index 1591c4f965..3ec83f27b3 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:44.357</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:44.049</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,19 +336,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:32.006</p></td>
+<td><p>00:32.504</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.720</p></td>
+<td><p>00:10.016</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></td>
-<td><p>00:01.625</p></td>
+<td><p>00:01.523</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 766621f783..f6e3f962d0 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -522,7 +522,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f63405b38c0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fa69d763d40>
</pre></div>
</div>
<p>Register the rule to TVM with override option to override existing rule.
diff --git a/docs/how_to/work_with_schedules/sg_execution_times.html b/docs/how_to/work_with_schedules/sg_execution_times.html
index de26764d39..fa6e5676c9 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:07.981</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:08.568</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,23 +336,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:05.526</p></td>
+<td><p>00:06.286</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:01.180</p></td>
+<td><p>00:00.969</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.557</p></td>
+<td><p>00:00.594</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></td>
-<td><p>00:00.535</p></td>
+<td><p>00:00.534</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.099</p></td>
+<td><p>00:00.101</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
@@ -360,11 +360,11 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.031</p></td>
+<td><p>00:00.028</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.014</p></td>
+<td><p>00:00.015</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 288dc5b520..92884d4351 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -577,7 +577,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp0hrqtxso/input0.cc'\nsource_filename = \"/tmp/tmp0hrqtxso/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp_y938ge8/input0.cc'\nsource_filename = \"/tmp/tmp_y938ge8/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index aa2238b85b..3153785d75 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -224,17 +224,7 @@
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
-<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
-<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
-</ul>
-</li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
-</ul>
-</li>
+<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
<li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 42e94f1faf..4554fc34c3 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1602,7 +1602,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1886,7 +1886,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 2fce303fba..0d3391a63d 100644
--- a/docs/reference/api/typedoc/classes/bytestreamreader.html
+++ b/docs/reference/api/typedoc/classes/bytestreamreader.html
@@ -119,7 +119,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -141,7 +141,7 @@
<div class="tsd-signature tsd-kind-icon">bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Uint8Array</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
</section>
@@ -151,7 +151,7 @@
<div class="tsd-signature tsd-kind-icon">offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
</ul>
</aside>
</section>
@@ -168,7 +168,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">Uint8Array</span></h4>
@@ -185,7 +185,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -202,7 +202,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/cachedcallstack.html b/docs/reference/api/typedoc/classes/cachedcallstack.html
index 4723b29996..7d710e7aed 100644
--- a/docs/reference/api/typedoc/classes/cachedcallstack.html
+++ b/docs/reference/api/typedoc/classes/cachedcallstack.html
@@ -144,7 +144,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L223">memory.ts:223</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -172,7 +172,7 @@
<div class="tsd-signature tsd-kind-icon">temp<wbr>Args<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><a href="../interfaces/disposable.html" class="tsd-signature-type">Disposable</a><span class="tsd-signature-symbol">></span><span class="tsd-signature-symbol"> = []</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L208">memory.ts:208</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -194,7 +194,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L312">memory.ts:312</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L284">memory.ts:284</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -262,7 +262,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L388">memory.ts:388</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -300,7 +300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L376">memory.ts:376</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -340,7 +340,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L267">memory.ts:267</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -373,7 +373,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L243">memory.ts:243</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -390,7 +390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L321">memory.ts:321</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -422,7 +422,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L252">memory.ts:252</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -444,7 +444,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L359">memory.ts:359</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -470,7 +470,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L342">memory.ts:342</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -496,7 +496,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L350">memory.ts:350</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -522,7 +522,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L326">memory.ts:326</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -548,7 +548,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L363">memory.ts:363</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -574,7 +574,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L346">memory.ts:346</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -600,7 +600,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L334">memory.ts:334</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/dldatatype.html b/docs/reference/api/typedoc/classes/dldatatype.html
index 1bd146c7cd..6c875d8b0d 100644
--- a/docs/reference/api/typedoc/classes/dldatatype.html
+++ b/docs/reference/api/typedoc/classes/dldatatype.html
@@ -119,7 +119,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L260">runtime.ts:260</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L258">runtime.ts:258</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L279">runtime.ts:279</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L270">runtime.ts:270</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/dldevice.html b/docs/reference/api/typedoc/classes/dldevice.html
index bcb986b173..3fd67545aa 100644
--- a/docs/reference/api/typedoc/classes/dldevice.html
+++ b/docs/reference/api/typedoc/classes/dldevice.html
@@ -118,7 +118,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L202">runtime.ts:202</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L200">runtime.ts:200</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L223">runtime.ts:223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L230">runtime.ts:230</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/environment.html b/docs/reference/api/typedoc/classes/environment.html
index a378b133d2..35bd931dc9 100644
--- a/docs/reference/api/typedoc/classes/environment.html
+++ b/docs/reference/api/typedoc/classes/environment.html
@@ -125,7 +125,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/environment.ts#L86">environment.ts:86</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -169,7 +169,7 @@
<aside class="tsd-sources">
<p>Implementation of <a href="../interfaces/libraryprovider.html">LibraryProvider</a>.<a href="../interfaces/libraryprovider.html#imports">imports</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/environment.ts#L70">environment.ts:70</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/environment.ts#L69">environment.ts:69</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -210,7 +210,7 @@
<div class="tsd-signature tsd-kind-icon">packedCFunc<wbr>Table<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">ctypes.FTVMWasmPackedCFunc</span><span class="tsd-signature-symbol"> | </span><span class="tsd-signature-type">undefined</span><span class="tsd-signature-symbol">></span><span class="tsd-signature-symbol"> = [undefined,]</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/environment.ts#L78">environment.ts:78</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -228,7 +228,7 @@
<div class="tsd-signature tsd-kind-icon">packedCFunc<wbr>Table<wbr>Free<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span><span class="tsd-signature-symbol"> = []</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/environment.ts#L84">environment.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -250,7 +250,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/environment.ts#L105">environment.ts:105</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ffilibrary.html b/docs/reference/api/typedoc/classes/ffilibrary.html
index f998d4bd4d..dcbebaa28a 100644
--- a/docs/reference/api/typedoc/classes/ffilibrary.html
+++ b/docs/reference/api/typedoc/classes/ffilibrary.html
@@ -131,7 +131,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L49">runtime.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L46">runtime.ts:46</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L45">runtime.ts:45</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L44">runtime.ts:44</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L47">runtime.ts:47</a></li>
</ul>
</aside>
</section>
@@ -203,7 +203,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L76">runtime.ts:76</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L66">runtime.ts:66</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L84">runtime.ts:84</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L95">runtime.ts:95</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L72">runtime.ts:72</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/graphexecutor.html b/docs/reference/api/typedoc/classes/graphexecutor.html
index 5427adb7f9..4dfa9e36b5 100644
--- a/docs/reference/api/typedoc/classes/graphexecutor.html
+++ b/docs/reference/api/typedoc/classes/graphexecutor.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L583">runtime.ts:583</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">module<span class="tsd-signature-symbol">:</span> <a href="module.html" class="tsd-signature-type">Module</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L579">runtime.ts:579</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L654">runtime.ts:654</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L597">runtime.ts:597</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -241,7 +241,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L631">runtime.ts:631</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L644">runtime.ts:644</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -310,7 +310,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L621">runtime.ts:621</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L609">runtime.ts:609</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index e506dc0dd9..3c576faa99 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -139,7 +139,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L692">runtime.ts:692</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L684">runtime.ts:684</a></li>
</ul>
</aside>
</section>
@@ -212,7 +212,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L683">runtime.ts:683</a></li>
</ul>
</aside>
</section>
@@ -229,7 +229,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L994">runtime.ts:994</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -303,7 +303,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L924">runtime.ts:924</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -341,7 +341,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L732">runtime.ts:732</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -358,7 +358,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L952">runtime.ts:952</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -402,7 +402,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L816">runtime.ts:816</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -434,7 +434,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -465,7 +465,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L846">runtime.ts:846</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -497,7 +497,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L750">runtime.ts:750</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -520,7 +520,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -568,7 +568,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L789">runtime.ts:789</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -608,7 +608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L914">runtime.ts:914</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -646,7 +646,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L740">runtime.ts:740</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -722,7 +722,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L868">runtime.ts:868</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -754,7 +754,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L857">runtime.ts:857</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -786,7 +786,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L940">runtime.ts:940</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index e63d376def..597e70e6ef 100644
--- a/docs/reference/api/typedoc/classes/memory.html
+++ b/docs/reference/api/typedoc/classes/memory.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L40">memory.ts:40</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Memory</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L32">memory.ts:32</a></li>
</ul>
</aside>
</section>
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span><span class="tsd-signature-symbol"> = true</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L33">memory.ts:33</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L154">memory.ts:154</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -210,7 +210,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L90">memory.ts:90</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -233,7 +233,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L97">memory.ts:97</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -256,7 +256,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L74">memory.ts:74</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L81">memory.ts:81</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -302,7 +302,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L104">memory.ts:104</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -325,7 +325,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L132">memory.ts:132</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -362,7 +362,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L145">memory.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -393,7 +393,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L60">memory.ts:60</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -416,7 +416,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L67">memory.ts:67</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -439,7 +439,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L53">memory.ts:53</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -462,7 +462,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L114">memory.ts:114</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -485,7 +485,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L124">memory.ts:124</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -502,7 +502,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/memory.ts#L175">memory.ts:175</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/module.html b/docs/reference/api/typedoc/classes/module.html
index 0897799c3f..b7e641191f 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -124,7 +124,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L504">runtime.ts:504</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L502">runtime.ts:502</a></li>
</ul>
</aside>
</section>
@@ -187,7 +187,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L516">runtime.ts:516</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -204,7 +204,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L530">runtime.ts:530</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -236,7 +236,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L561">runtime.ts:561</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index a647213edd..4dce32e72d 100644
--- a/docs/reference/api/typedoc/classes/ndarray.html
+++ b/docs/reference/api/typedoc/classes/ndarray.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L304">runtime.ts:304</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L293">runtime.ts:293</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L289">runtime.ts:289</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L291">runtime.ts:291</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -240,7 +240,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L370">runtime.ts:370</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -273,7 +273,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L414">runtime.ts:414</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -305,7 +305,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -322,7 +322,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L474">runtime.ts:474</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -346,7 +346,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L443">runtime.ts:443</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index df6a77e3b2..9d09ce990e 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -122,7 +122,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L158">runtime.ts:158</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
</section>
@@ -164,7 +164,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L165">runtime.ts:165</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index a033bd3e8a..2a126ec3f4 100644
--- a/docs/reference/api/typedoc/classes/rpcserver.html
+++ b/docs/reference/api/typedoc/classes/rpcserver.html
@@ -115,7 +115,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index 22dbc38fe2..aadb9d623a 100644
--- a/docs/reference/api/typedoc/classes/scalar.html
+++ b/docs/reference/api/typedoc/classes/scalar.html
@@ -112,7 +112,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index 0923168cd1..29a487966c 100644
--- a/docs/reference/api/typedoc/classes/webgpucontext.html
+++ b/docs/reference/api/typedoc/classes/webgpucontext.html
@@ -120,7 +120,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -145,7 +145,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">GPUDevice</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
</ul>
</aside>
</section>
@@ -155,7 +155,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
</ul>
</aside>
</section>
@@ -172,7 +172,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -209,7 +209,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/enums/argtypecode.html b/docs/reference/api/typedoc/enums/argtypecode.html
index f66df237e1..0c1cf9c0bd 100644
--- a/docs/reference/api/typedoc/enums/argtypecode.html
+++ b/docs/reference/api/typedoc/enums/argtypecode.html
@@ -106,7 +106,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 6</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index f8c66e5f9d..0cecc912ee 100644
--- a/docs/reference/api/typedoc/enums/aynccallbackcode.html
+++ b/docs/reference/api/typedoc/enums/aynccallbackcode.html
@@ -93,7 +93,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Exception<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L676">runtime.ts:676</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L675">runtime.ts:675</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 1eed112f65..5e8af176af 100644
--- a/docs/reference/api/typedoc/enums/dldatatypecode.html
+++ b/docs/reference/api/typedoc/enums/dldatatypecode.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L240">runtime.ts:240</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L243">runtime.ts:243</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L241">runtime.ts:241</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index cf1b4baed7..d68e8b105b 100644
--- a/docs/reference/api/typedoc/enums/rpcserverstate.html
+++ b/docs/reference/api/typedoc/enums/rpcserverstate.html
@@ -90,7 +90,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index a797f550df..12f15380a3 100644
--- a/docs/reference/api/typedoc/enums/sizeof.html
+++ b/docs/reference/api/typedoc/enums/sizeof.html
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index 86676309a1..a594c398de 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L36">runtime.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L246">runtime.ts:246</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L247">runtime.ts:247</a></li>
</ul>
</aside>
</section>
@@ -1549,7 +1549,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
</section>
@@ -1559,7 +1559,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L249">runtime.ts:249</a></li>
</ul>
</aside>
</section>
@@ -1569,7 +1569,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L250">runtime.ts:250</a></li>
</ul>
</aside>
</section>
@@ -1580,7 +1580,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L175">runtime.ts:175</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1589,7 +1589,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L176">runtime.ts:176</a></li>
</ul>
</aside>
</section>
@@ -1599,7 +1599,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L180">runtime.ts:180</a></li>
</ul>
</aside>
</section>
@@ -1609,7 +1609,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L177">runtime.ts:177</a></li>
</ul>
</aside>
</section>
@@ -1619,7 +1619,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L178">runtime.ts:178</a></li>
</ul>
</aside>
</section>
@@ -1629,7 +1629,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L179">runtime.ts:179</a></li>
</ul>
</aside>
</section>
@@ -1640,7 +1640,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L183">runtime.ts:183</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1649,7 +1649,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L186">runtime.ts:186</a></li>
</ul>
</aside>
</section>
@@ -1659,7 +1659,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L184">runtime.ts:184</a></li>
</ul>
</aside>
</section>
@@ -1669,7 +1669,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L185">runtime.ts:185</a></li>
</ul>
</aside>
</section>
@@ -1679,7 +1679,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
</section>
@@ -1689,7 +1689,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L187">runtime.ts:187</a></li>
</ul>
</aside>
</section>
@@ -1699,7 +1699,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L188">runtime.ts:188</a></li>
</ul>
</aside>
</section>
@@ -1709,7 +1709,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/runtime.ts#L190">runtime.ts:190</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index 7fcf7ac305..af4099336a 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -113,7 +113,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/types.ts#L52">types.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/interfaces/functioninfo.html b/docs/reference/api/typedoc/interfaces/functioninfo.html
index 1557b381ca..a336fa42f3 100644
--- a/docs/reference/api/typedoc/interfaces/functioninfo.html
+++ b/docs/reference/api/typedoc/interfaces/functioninfo.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">arg_<wbr>types<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">launch_<wbr>param_<wbr>tags<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">name<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/libraryprovider.html b/docs/reference/api/typedoc/interfaces/libraryprovider.html
index c5c096df72..08a7c02734 100644
--- a/docs/reference/api/typedoc/interfaces/libraryprovider.html
+++ b/docs/reference/api/typedoc/interfaces/libraryprovider.html
@@ -112,7 +112,7 @@
<div class="tsd-signature tsd-kind-icon">imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/types.ts#L34">types.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -127,7 +127,7 @@
<div class="tsd-signature tsd-kind-icon">start<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>inst<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">Instance</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fd2681372/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e1f3f9058/web/src/types.ts#L39">types.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/searchindex.js b/docs/searchindex.js
index c2ea887b24..d35f58a0fd 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
+Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
diff --git a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
index 1e23d54986..4d1bc1662b 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:21.987</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:22.672</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:21.980</p></td>
+<td><p>00:22.665</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 0c9ad3f57d..2de9d75345 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -569,7 +569,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 23.60s!
+resnet18_v1 inference graph built in 24.27s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_detection.html b/docs/topic/vta/tutorials/frontend/deploy_detection.html
index 9ae406f005..672730fa84 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -587,7 +587,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 16.53s!
+yolov3-tiny inference graph built in 16.75s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index 1f258d51ce..b111264067 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:34.438</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:33.907</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:49.802</p></td>
+<td><p>00:49.362</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:44.636</p></td>
+<td><p>00:44.544</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index 90ecb1e177..eff71cf186 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.048</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.072</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.633</p></td>
+<td><p>00:02.662</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></td>
-<td><p>00:00.416</p></td>
+<td><p>00:00.410</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index fea05d6fbf..c2c0f037b1 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.743</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.745</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.391</p></td>
+<td><p>00:00.397</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></td>
-<td><p>00:00.352</p></td>
+<td><p>00:00.349</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index 3884004043..496bb926c0 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -478,6 +478,9 @@ trials, we can load the best schedule from the log file and apply it.</p>
<a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sch</span></a><span class="p">,</span> <a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
</pre></div>
</div>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>*E
+</pre></div>
+</div>
</div>
<div class="section" id="inspecting-the-optimized-schedule">
<h2>Inspecting the Optimized Schedule<a class="headerlink" href="#inspecting-the-optimized-schedule" title="Permalink to this headline">¶</a></h2>
@@ -565,7 +568,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 96.325 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.814 ms
</pre></div>
</div>
</div>
@@ -629,7 +632,6 @@ resume the status and do more 5 trials.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Resume search:
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
-*E
</pre></div>
</div>
</div>
@@ -640,7 +642,7 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.597 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 14.488 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index 9b1bd5ece7..5f6eced678 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -669,16 +669,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 12.58/12.58 result: MeasureResult(costs=(0.021346469200000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5053350925445557, timestamp=1664221080.281347) [('tile_y', [-1, 32]), ('tile_x', [-1, 128])],None,75
-No: 2 GFLOPS: 10.10/12.58 result: MeasureResult(costs=(0.0265824112,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5982592105865479, timestamp=1664221080.9241135) [('tile_y', [-1, 512]), ('tile_x', [-1, 512])],None,99
-No: 3 GFLOPS: 1.97/12.58 result: MeasureResult(costs=(0.136568222,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3049232959747314, timestamp=1664221084.218269) [('tile_y', [-1, 512]), ('tile_x', [-1, 8])],None,39
-No: 4 GFLOPS: 3.09/12.58 result: MeasureResult(costs=(0.0868321444,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5004169940948486, timestamp=1664221085.7739544) [('tile_y', [-1, 128]), ('tile_x', [-1, 8])],None,37
-No: 5 GFLOPS: 1.53/12.58 result: MeasureResult(costs=(0.175027406,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.939075231552124, timestamp=1664221088.9318147) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
-No: 6 GFLOPS: 13.81/13.81 result: MeasureResult(costs=(0.0194402746,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.48528003692626953, timestamp=1664221090.3495922) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
-No: 7 GFLOPS: 4.58/13.81 result: MeasureResult(costs=(0.0585868598,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.0872364044189453, timestamp=1664221092.376788) [('tile_y', [-1, 16]), ('tile_x', [-1, 16])],None,44
-No: 8 GFLOPS: 12.44/13.81 result: MeasureResult(costs=(0.021586282199999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6239986419677734, timestamp=1664221092.9347243) [('tile_y', [-1, 256]), ('tile_x', [-1, 128])],None,78
-No: 9 GFLOPS: 4.52/13.81 result: MeasureResult(costs=(0.059432939,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1062226295471191, timestamp=1664221094.294028) [('tile_y', [-1, 8]), ('tile_x', [-1, 16])],None,43
-No: 10 GFLOPS: 8.41/13.81 result: MeasureResult(costs=(0.0319145958,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8026306629180908, timestamp=1664221094.9684076) [('tile_y', [-1, 16]), ('tile_x', [-1, 64])],None,64
+No: 1 GFLOPS: 10.08/10.08 result: MeasureResult(costs=(0.0266191396,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.663262128829956, timestamp=1664227814.8990576) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
+No: 2 GFLOPS: 10.37/10.37 result: MeasureResult(costs=(0.0258787292,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7077369689941406, timestamp=1664227815.5305746) [('tile_y', [-1, 1]), ('tile_x', [-1, 128])],None,70
+No: 3 GFLOPS: 3.93/10.37 result: MeasureResult(costs=(0.068234874,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2401442527770996, timestamp=1664227817.7171843) [('tile_y', [-1, 16]), ('tile_x', [-1, 8])],None,34
+No: 4 GFLOPS: 12.68/12.68 result: MeasureResult(costs=(0.021162052,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6068720817565918, timestamp=1664227819.1688583) [('tile_y', [-1, 64]), ('tile_x', [-1, 128])],None,76
+No: 5 GFLOPS: 1.69/12.68 result: MeasureResult(costs=(0.15863106580000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6720221042633057, timestamp=1664227821.9962373) [('tile_y', [-1, 1]), ('tile_x', [-1, 8])],None,30
+No: 6 GFLOPS: 11.61/12.68 result: MeasureResult(costs=(0.0231142084,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5251588821411133, timestamp=1664227822.5337727) [('tile_y', [-1, 32]), ('tile_x', [-1, 32])],None,55
+No: 7 GFLOPS: 10.52/12.68 result: MeasureResult(costs=(0.0255183186,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5874519348144531, timestamp=1664227824.0467129) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
+No: 8 GFLOPS: 11.40/12.68 result: MeasureResult(costs=(0.0235384858,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5579280853271484, timestamp=1664227824.6405678) [('tile_y', [-1, 4]), ('tile_x', [-1, 512])],None,92
+No: 9 GFLOPS: 9.86/12.68 result: MeasureResult(costs=(0.027221641799999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.543665885925293, timestamp=1664227825.3016732) [('tile_y', [-1, 1]), ('tile_x', [-1, 512])],None,90
+No: 10 GFLOPS: 10.94/12.68 result: MeasureResult(costs=(0.024541742,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.500617504119873, timestamp=1664227825.866088) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
</pre></div>
</div>
<p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index d5def609b5..9ab8fc26b2 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -547,7 +547,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 518.8625257100057, 'median': 519.0639800500094, 'std': 1.3911651244158252}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 521.1109951399976, 'median': 520.7685348999973, 'std': 0.9562144510221742}
</pre></div>
</div>
</div>
@@ -699,178 +699,179 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 9.61/ 22.80 GFLOPS | Progress: (4/20) | 8.60 s
-[Task 1/25] Current/Best: 11.06/ 22.80 GFLOPS | Progress: (8/20) | 16.22 s
-[Task 1/25] Current/Best: 19.12/ 22.80 GFLOPS | Progress: (12/20) | 19.73 s
-[Task 1/25] Current/Best: 5.60/ 22.80 GFLOPS | Progress: (16/20) | 24.88 s
-[Task 1/25] Current/Best: 22.67/ 22.80 GFLOPS | Progress: (20/20) | 26.78 s Done.
+[Task 1/25] Current/Best: 8.36/ 14.79 GFLOPS | Progress: (4/20) | 7.32 s
+[Task 1/25] Current/Best: 21.99/ 21.99 GFLOPS | Progress: (8/20) | 11.49 s
+[Task 1/25] Current/Best: 11.66/ 21.99 GFLOPS | Progress: (12/20) | 13.73 s
+[Task 1/25] Current/Best: 17.19/ 21.99 GFLOPS | Progress: (16/20) | 15.63 s
+[Task 1/25] Current/Best: 10.62/ 21.99 GFLOPS | Progress: (20/20) | 17.68 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 11.72/ 15.73 GFLOPS | Progress: (4/20) | 3.53 s
-[Task 2/25] Current/Best: 6.38/ 15.73 GFLOPS | Progress: (8/20) | 4.90 s
-[Task 2/25] Current/Best: 9.80/ 18.27 GFLOPS | Progress: (12/20) | 6.66 s
-[Task 2/25] Current/Best: 6.87/ 18.27 GFLOPS | Progress: (16/20) | 7.71 s
-[Task 2/25] Current/Best: 12.78/ 18.27 GFLOPS | Progress: (20/20) | 9.34 s Done.
+[Task 2/25] Current/Best: 21.52/ 21.52 GFLOPS | Progress: (4/20) | 3.55 s
+[Task 2/25] Current/Best: 21.37/ 21.52 GFLOPS | Progress: (8/20) | 4.49 s
+[Task 2/25] Current/Best: 16.26/ 21.52 GFLOPS | Progress: (12/20) | 5.61 s
+[Task 2/25] Current/Best: 12.36/ 21.52 GFLOPS | Progress: (16/20) | 6.71 s
+[Task 2/25] Current/Best: 14.67/ 21.52 GFLOPS | Progress: (20/20) | 8.91 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 20.01/ 20.01 GFLOPS | Progress: (4/20) | 3.77 s
-[Task 3/25] Current/Best: 12.24/ 20.01 GFLOPS | Progress: (8/20) | 5.72 s
-[Task 3/25] Current/Best: 14.94/ 20.01 GFLOPS | Progress: (12/20) | 7.94 s
-[Task 3/25] Current/Best: 7.02/ 20.04 GFLOPS | Progress: (16/20) | 10.37 s
-[Task 3/25] Current/Best: 11.26/ 22.05 GFLOPS | Progress: (20/20) | 12.50 s Done.
+[Task 3/25] Current/Best: 8.01/ 18.03 GFLOPS | Progress: (4/20) | 4.51 s
+[Task 3/25] Current/Best: 15.69/ 18.03 GFLOPS | Progress: (8/20) | 6.93 s
+[Task 3/25] Current/Best: 12.38/ 18.03 GFLOPS | Progress: (12/20) | 8.97 s
+[Task 3/25] Current/Best: 16.75/ 18.52 GFLOPS | Progress: (16/20) | 11.18 s
+[Task 3/25] Current/Best: 6.60/ 23.79 GFLOPS | Progress: (20/20) | 13.06 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 19.64/ 19.64 GFLOPS | Progress: (4/20) | 4.24 s
-[Task 4/25] Current/Best: 15.30/ 19.64 GFLOPS | Progress: (8/20) | 5.90 s
-[Task 4/25] Current/Best: 11.00/ 21.91 GFLOPS | Progress: (12/20) | 9.74 s
-[Task 4/25] Current/Best: 13.56/ 21.91 GFLOPS | Progress: (16/20) | 12.41 s
-[Task 4/25] Current/Best: 9.61/ 21.91 GFLOPS | Progress: (20/20) | 14.17 s Done.
+[Task 4/25] Current/Best: 19.70/ 19.70 GFLOPS | Progress: (4/20) | 5.50 s
+[Task 4/25] Current/Best: 16.79/ 19.70 GFLOPS | Progress: (8/20) | 11.95 s
+[Task 4/25] Current/Best: 9.19/ 19.70 GFLOPS | Progress: (12/20) | 13.89 s
+[Task 4/25] Current/Best: 16.01/ 19.70 GFLOPS | Progress: (16/20) | 18.31 s
+[Task 4/25] Current/Best: 13.92/ 19.70 GFLOPS | Progress: (20/20) | 20.91 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 17.29/ 17.98 GFLOPS | Progress: (4/20) | 3.68 s
-[Task 5/25] Current/Best: 13.07/ 18.60 GFLOPS | Progress: (8/20) | 5.19 s
-[Task 5/25] Current/Best: 11.44/ 18.60 GFLOPS | Progress: (12/20) | 7.04 s
-[Task 5/25] Current/Best: 14.91/ 21.52 GFLOPS | Progress: (16/20) | 8.51 s
-[Task 5/25] Current/Best: 4.88/ 21.52 GFLOPS | Progress: (20/20) | 10.63 s Done.
+[Task 5/25] Current/Best: 18.60/ 18.60 GFLOPS | Progress: (4/20) | 3.53 s
+[Task 5/25] Current/Best: 20.15/ 20.15 GFLOPS | Progress: (8/20) | 5.08 s
+[Task 5/25] Current/Best: 10.77/ 21.43 GFLOPS | Progress: (12/20) | 6.82 s
+[Task 5/25] Current/Best: 14.48/ 21.43 GFLOPS | Progress: (16/20) | 9.16 s
+[Task 5/25] Current/Best: 14.56/ 21.43 GFLOPS | Progress: (20/20) | 10.91 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 9.49/ 12.36 GFLOPS | Progress: (4/20) | 4.14 s
-[Task 6/25] Current/Best: 12.50/ 13.66 GFLOPS | Progress: (8/20) | 6.42 s
-[Task 6/25] Current/Best: 11.40/ 17.97 GFLOPS | Progress: (12/20) | 10.20 s
-[Task 6/25] Current/Best: 11.66/ 17.97 GFLOPS | Progress: (16/20) | 12.44 s
-[Task 6/25] Current/Best: 8.52/ 17.97 GFLOPS | Progress: (20/20) | 15.61 s Done.
+[Task 6/25] Current/Best: 3.84/ 14.94 GFLOPS | Progress: (4/20) | 4.79 s
+[Task 6/25] Current/Best: 7.87/ 16.02 GFLOPS | Progress: (8/20) | 6.91 s
+[Task 6/25] Current/Best: 4.17/ 16.02 GFLOPS | Progress: (12/20) | 9.36 s
+[Task 6/25] Current/Best: 9.72/ 18.03 GFLOPS | Progress: (16/20) | 12.42 s
+[Task 6/25] Current/Best: 16.51/ 18.03 GFLOPS | Progress: (20/20) | 14.36 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 6.38/ 15.10 GFLOPS | Progress: (4/20) | 4.01 s
-[Task 7/25] Current/Best: 17.83/ 18.27 GFLOPS | Progress: (8/20) | 5.64 s
-[Task 7/25] Current/Best: 8.43/ 19.21 GFLOPS | Progress: (12/20) | 7.80 s
-[Task 7/25] Current/Best: 20.30/ 20.30 GFLOPS | Progress: (16/20) | 10.29 s
-[Task 7/25] Current/Best: 14.98/ 20.30 GFLOPS | Progress: (20/20) | 12.34 s Done.
+[Task 7/25] Current/Best: 11.30/ 18.45 GFLOPS | Progress: (4/20) | 4.02 s
+[Task 7/25] Current/Best: 15.27/ 18.45 GFLOPS | Progress: (8/20) | 5.94 s
+[Task 7/25] Current/Best: 11.86/ 18.45 GFLOPS | Progress: (12/20) | 8.19 s
+[Task 7/25] Current/Best: 5.87/ 18.45 GFLOPS | Progress: (16/20) | 11.31 s
+[Task 7/25] Current/Best: 16.22/ 21.88 GFLOPS | Progress: (20/20) | 13.55 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 9.80/ 11.79 GFLOPS | Progress: (4/20) | 8.23 s
-[Task 8/25] Current/Best: 8.24/ 21.11 GFLOPS | Progress: (8/20) | 19.14 s
-[Task 8/25] Current/Best: 13.74/ 21.11 GFLOPS | Progress: (12/20) | 22.94 s
-[Task 8/25] Current/Best: 8.38/ 21.11 GFLOPS | Progress: (16/20) | 26.73 s
-[Task 8/25] Current/Best: 11.33/ 21.11 GFLOPS | Progress: (20/20) | 28.90 s Done.
+[Task 8/25] Current/Best: 12.82/ 12.82 GFLOPS | Progress: (4/20) | 7.36 s
+[Task 8/25] Current/Best: 14.20/ 14.62 GFLOPS | Progress: (8/20) | 10.07 s
+[Task 8/25] Current/Best: 4.61/ 14.62 GFLOPS | Progress: (12/20) | 15.55 s
+[Task 8/25] Current/Best: 10.83/ 18.82 GFLOPS | Progress: (16/20) | 17.52 s
+[Task 8/25] Current/Best: 2.49/ 18.82 GFLOPS | Progress: (20/20) | 20.17 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 8.84/ 18.55 GFLOPS | Progress: (4/20) | 3.54 s
-[Task 9/25] Current/Best: 19.09/ 21.00 GFLOPS | Progress: (8/20) | 4.92 s
-[Task 9/25] Current/Best: 17.64/ 21.00 GFLOPS | Progress: (12/20) | 11.75 s
-[Task 9/25] Current/Best: 6.57/ 21.00 GFLOPS | Progress: (16/20) | 13.10 s
-[Task 9/25] Current/Best: 10.80/ 21.00 GFLOPS | Progress: (20/20) | 19.64 s Done.
+[Task 9/25] Current/Best: 13.51/ 20.53 GFLOPS | Progress: (4/20) | 3.62 s
+[Task 9/25] Current/Best: 14.62/ 20.53 GFLOPS | Progress: (8/20) | 8.91 s
+[Task 9/25] Current/Best: 9.50/ 20.53 GFLOPS | Progress: (12/20) | 11.02 s
+[Task 9/25] Current/Best: 12.73/ 20.53 GFLOPS | Progress: (16/20) | 13.41 s
+[Task 9/25] Current/Best: 8.16/ 20.53 GFLOPS | Progress: (20/20) | 15.33 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 3.82/ 13.77 GFLOPS | Progress: (4/20) | 4.02 s
-[Task 10/25] Current/Best: 3.33/ 13.77 GFLOPS | Progress: (8/20) | 7.44 s
-[Task 10/25] Current/Best: 12.21/ 15.67 GFLOPS | Progress: (12/20) | 8.77 s
-[Task 10/25] Current/Best: 12.38/ 15.67 GFLOPS | Progress: (16/20) | 10.83 s
-[Task 10/25] Current/Best: 10.59/ 22.20 GFLOPS | Progress: (20/20) | 14.39 s Done.
+[Task 10/25] Current/Best: 20.49/ 20.49 GFLOPS | Progress: (4/20) | 3.16 s
+[Task 10/25] Current/Best: 14.28/ 20.49 GFLOPS | Progress: (8/20) | 4.47 s
+[Task 10/25] Current/Best: 17.97/ 20.49 GFLOPS | Progress: (12/20) | 5.95 s
+[Task 10/25] Current/Best: 12.29/ 20.49 GFLOPS | Progress: (16/20) | 8.33 s
+[Task 10/25] Current/Best: 16.32/ 20.49 GFLOPS | Progress: (20/20) | 10.01 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 16.92/ 21.35 GFLOPS | Progress: (4/20) | 3.83 s
-[Task 11/25] Current/Best: 6.71/ 23.65 GFLOPS | Progress: (8/20) | 5.79 s
-[Task 11/25] Current/Best: 18.87/ 23.65 GFLOPS | Progress: (12/20) | 8.42 s
-[Task 11/25] Current/Best: 7.25/ 23.65 GFLOPS | Progress: (16/20) | 10.75 s
-[Task 11/25] Current/Best: 10.98/ 23.65 GFLOPS | Progress: (20/20) | 13.10 s Done.
+[Task 11/25] Current/Best: 6.24/ 17.16 GFLOPS | Progress: (4/20) | 3.83 s
+[Task 11/25] Current/Best: 11.39/ 20.80 GFLOPS | Progress: (8/20) | 7.53 s
+[Task 11/25] Current/Best: 17.78/ 23.37 GFLOPS | Progress: (12/20) | 9.41 s
+[Task 11/25] Current/Best: 22.03/ 23.37 GFLOPS | Progress: (16/20) | 11.22 s
+[Task 11/25] Current/Best: 9.93/ 23.37 GFLOPS | Progress: (20/20) | 13.35 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 15.88/ 20.51 GFLOPS | Progress: (4/20) | 4.37 s
-[Task 12/25] Current/Best: 12.54/ 20.51 GFLOPS | Progress: (8/20) | 6.68 s
-[Task 12/25] Current/Best: 21.77/ 21.77 GFLOPS | Progress: (12/20) | 8.35 s
-[Task 12/25] Current/Best: 19.95/ 21.77 GFLOPS | Progress: (16/20) | 11.06 s
-[Task 12/25] Current/Best: 10.01/ 21.77 GFLOPS | Progress: (20/20) | 14.00 s Done.
+[Task 12/25] Current/Best: 10.30/ 13.95 GFLOPS | Progress: (4/20) | 10.44 s
+[Task 12/25] Current/Best: 8.53/ 14.08 GFLOPS | Progress: (8/20) | 14.80 s
+[Task 12/25] Current/Best: 18.13/ 18.13 GFLOPS | Progress: (12/20) | 18.03 s
+[Task 12/25] Current/Best: 5.66/ 19.02 GFLOPS | Progress: (16/20) | 20.53 s
+[Task 12/25] Current/Best: 21.23/ 21.23 GFLOPS | Progress: (20/20) | 22.64 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 17.17/ 17.17 GFLOPS | Progress: (4/20) | 5.47 s
-[Task 13/25] Current/Best: 15.63/ 17.17 GFLOPS | Progress: (8/20) | 8.27 s
-[Task 13/25] Current/Best: 9.95/ 17.17 GFLOPS | Progress: (12/20) | 10.34 s
-[Task 13/25] Current/Best: 6.88/ 19.28 GFLOPS | Progress: (16/20) | 13.90 s
-[Task 13/25] Current/Best: 3.09/ 19.28 GFLOPS | Progress: (20/20) | 18.41 s Done.
+[Task 13/25] Current/Best: 12.50/ 12.50 GFLOPS | Progress: (4/20) | 4.65 s
+[Task 13/25] Current/Best: 8.43/ 15.81 GFLOPS | Progress: (8/20) | 8.11 s
+[Task 13/25] Current/Best: 9.26/ 17.80 GFLOPS | Progress: (12/20) | 10.86 s
+[Task 13/25] Current/Best: 16.79/ 17.80 GFLOPS | Progress: (16/20) | 13.25 s
+[Task 13/25] Current/Best: 16.69/ 21.28 GFLOPS | Progress: (20/20) | 16.17 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 12.27/ 16.05 GFLOPS | Progress: (4/20) | 4.16 s
-[Task 14/25] Current/Best: 14.59/ 16.05 GFLOPS | Progress: (8/20) | 6.89 s
-[Task 14/25] Current/Best: 12.74/ 16.05 GFLOPS | Progress: (12/20) | 10.00 s
-[Task 14/25] Current/Best: 10.47/ 16.05 GFLOPS | Progress: (16/20) | 14.25 s
-[Task 14/25] Current/Best: 7.49/ 16.05 GFLOPS | Progress: (20/20) | 17.56 s Done.
-
+[Task 14/25] Current/Best: 14.08/ 15.92 GFLOPS | Progress: (4/20) | 3.61 s
+[Task 14/25] Current/Best: 19.14/ 21.44 GFLOPS | Progress: (8/20) | 5.95 s
+[Task 14/25] Current/Best: 11.44/ 21.44 GFLOPS | Progress: (12/20) | 8.42 s
+[Task 14/25] Current/Best: 9.53/ 21.55 GFLOPS | Progress: (16/20) | 11.21 s
+[Task 14/25] Current/Best: 2.68/ 21.55 GFLOPS | Progress: (20/20) | 14.10 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 3.19/ 21.12 GFLOPS | Progress: (4/20) | 3.36 s
-[Task 15/25] Current/Best: 17.92/ 21.12 GFLOPS | Progress: (8/20) | 5.24 s
-[Task 15/25] Current/Best: 6.19/ 21.12 GFLOPS | Progress: (12/20) | 6.60 s
-[Task 15/25] Current/Best: 15.21/ 21.12 GFLOPS | Progress: (16/20) | 8.00 s
-[Task 15/25] Current/Best: 21.08/ 21.12 GFLOPS | Progress: (20/20) | 10.24 s Done.
-
-[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 9.46/ 17.85 GFLOPS | Progress: (4/20) | 3.81 s
-[Task 16/25] Current/Best: 16.08/ 17.85 GFLOPS | Progress: (8/20) | 5.71 s
-[Task 16/25] Current/Best: 14.28/ 17.85 GFLOPS | Progress: (12/20) | 6.99 s
-[Task 16/25] Current/Best: 18.67/ 21.93 GFLOPS | Progress: (16/20) | 8.16 s
-[Task 16/25] Current/Best: 12.60/ 21.93 GFLOPS | Progress: (20/20) | 11.13 s Done.
+[Task 15/25] Current/Best: 9.08/ 16.25 GFLOPS | Progress: (4/20) | 4.42 s
+[Task 15/25] Current/Best: 5.13/ 16.25 GFLOPS | Progress: (8/20) | 9.66 s
+[Task 15/25] Current/Best: 12.28/ 16.25 GFLOPS | Progress: (12/20) | 12.75 s
+[Task 15/25] Current/Best: 12.99/ 18.42 GFLOPS | Progress: (16/20) | 14.40 s
+[Task 15/25] Current/Best: 9.11/ 18.42 GFLOPS | Progress: (20/20) | 17.77 s
+[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+ Done.
+
+[Task 16/25] Current/Best: 9.06/ 14.01 GFLOPS | Progress: (4/20) | 5.79 s
+[Task 16/25] Current/Best: 14.64/ 14.64 GFLOPS | Progress: (8/20) | 7.21 s
+[Task 16/25] Current/Best: 5.78/ 18.34 GFLOPS | Progress: (12/20) | 8.79 s
+[Task 16/25] Current/Best: 10.24/ 18.34 GFLOPS | Progress: (16/20) | 10.04 s
+[Task 16/25] Current/Best: 14.35/ 20.50 GFLOPS | Progress: (20/20) | 11.37 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 17.01/ 17.01 GFLOPS | Progress: (4/20) | 4.26 s
-[Task 17/25] Current/Best: 17.31/ 22.72 GFLOPS | Progress: (8/20) | 6.01 s
-[Task 17/25] Current/Best: 15.27/ 22.72 GFLOPS | Progress: (12/20) | 8.10 s
-[Task 17/25] Current/Best: 6.61/ 22.72 GFLOPS | Progress: (16/20) | 10.66 s
-[Task 17/25] Current/Best: 10.50/ 22.72 GFLOPS | Progress: (20/20) | 13.13 s Done.
+[Task 17/25] Current/Best: 22.56/ 22.56 GFLOPS | Progress: (4/20) | 3.81 s
+[Task 17/25] Current/Best: 19.77/ 22.56 GFLOPS | Progress: (8/20) | 6.09 s
+[Task 17/25] Current/Best: 9.74/ 22.56 GFLOPS | Progress: (12/20) | 8.22 s
+[Task 17/25] Current/Best: 18.63/ 22.56 GFLOPS | Progress: (16/20) | 11.90 s
+[Task 17/25] Current/Best: 20.31/ 22.56 GFLOPS | Progress: (20/20) | 13.53 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 19.54/ 19.54 GFLOPS | Progress: (4/20) | 3.92 s
-[Task 18/25] Current/Best: 9.00/ 19.56 GFLOPS | Progress: (8/20) | 7.15 s
-[Task 18/25] Current/Best: 5.81/ 19.85 GFLOPS | Progress: (12/20) | 9.21 s
-[Task 18/25] Current/Best: 17.39/ 19.85 GFLOPS | Progress: (16/20) | 11.29 s
-[Task 18/25] Current/Best: 9.64/ 19.85 GFLOPS | Progress: (20/20) | 15.92 s Done.
+[Task 18/25] Current/Best: 13.64/ 16.16 GFLOPS | Progress: (4/20) | 3.70 s
+[Task 18/25] Current/Best: 19.82/ 19.82 GFLOPS | Progress: (8/20) | 7.21 s
+[Task 18/25] Current/Best: 13.94/ 19.82 GFLOPS | Progress: (12/20) | 12.63 s
+[Task 18/25] Current/Best: 10.57/ 19.82 GFLOPS | Progress: (16/20) | 14.41 s
+[Task 18/25] Current/Best: 17.01/ 19.82 GFLOPS | Progress: (20/20) | 19.56 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 18.99/ 18.99 GFLOPS | Progress: (4/20) | 4.50 s
-[Task 19/25] Current/Best: 17.90/ 18.99 GFLOPS | Progress: (8/20) | 7.66 s
-[Task 19/25] Current/Best: 10.15/ 18.99 GFLOPS | Progress: (12/20) | 11.53 s
-[Task 19/25] Current/Best: 16.93/ 19.88 GFLOPS | Progress: (16/20) | 14.50 s
-[Task 19/25] Current/Best: 9.44/ 23.30 GFLOPS | Progress: (20/20) | 17.86 s Done.
+[Task 19/25] Current/Best: 3.08/ 12.30 GFLOPS | Progress: (4/20) | 5.67 s
+[Task 19/25] Current/Best: 4.04/ 19.44 GFLOPS | Progress: (8/20) | 9.09 s
+[Task 19/25] Current/Best: 14.04/ 19.44 GFLOPS | Progress: (12/20) | 12.81 s
+[Task 19/25] Current/Best: 15.85/ 19.44 GFLOPS | Progress: (16/20) | 15.85 s
+[Task 19/25] Current/Best: 11.54/ 20.92 GFLOPS | Progress: (20/20) | 18.17 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 14.01/ 18.33 GFLOPS | Progress: (4/20) | 4.81 s
-[Task 20/25] Current/Best: 8.08/ 18.33 GFLOPS | Progress: (8/20) | 7.91 s
-[Task 20/25] Current/Best: 17.40/ 18.33 GFLOPS | Progress: (12/20) | 10.51 s
-[Task 20/25] Current/Best: 7.91/ 18.90 GFLOPS | Progress: (16/20) | 13.34 s
-[Task 20/25] Current/Best: 13.28/ 18.90 GFLOPS | Progress: (20/20) | 14.98 s
+[Task 20/25] Current/Best: 13.64/ 16.80 GFLOPS | Progress: (4/20) | 5.01 s
+[Task 20/25] Current/Best: 13.25/ 16.80 GFLOPS | Progress: (8/20) | 6.81 s
+[Task 20/25] Current/Best: 19.61/ 19.94 GFLOPS | Progress: (12/20) | 8.68 s
+[Task 20/25] Current/Best: 19.99/ 19.99 GFLOPS | Progress: (16/20) | 12.64 s
+[Task 20/25] Current/Best: 6.20/ 19.99 GFLOPS | Progress: (20/20) | 16.48 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 16.49/ 16.87 GFLOPS | Progress: (4/20) | 4.10 s Done.
+[Task 21/25] Current/Best: 21.85/ 21.85 GFLOPS | Progress: (4/20) | 4.12 s
+[Task 21/25] Current/Best: 13.20/ 21.85 GFLOPS | Progress: (8/20) | 5.59 s
+[Task 21/25] Current/Best: 4.71/ 21.85 GFLOPS | Progress: (12/20) | 7.51 s
+[Task 21/25] Current/Best: 5.33/ 21.85 GFLOPS | Progress: (16/20) | 11.48 s Done.
+
+[Task 21/25] Current/Best: 15.40/ 21.85 GFLOPS | Progress: (20/20) | 13.65 s Done.
-[Task 21/25] Current/Best: 10.64/ 19.52 GFLOPS | Progress: (8/20) | 5.72 s
-[Task 21/25] Current/Best: 2.29/ 19.52 GFLOPS | Progress: (12/20) | 7.80 s
-[Task 21/25] Current/Best: 8.61/ 21.28 GFLOPS | Progress: (16/20) | 11.10 s
-[Task 21/25] Current/Best: 18.57/ 21.28 GFLOPS | Progress: (20/20) | 12.10 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 14.18/ 14.57 GFLOPS | Progress: (4/20) | 4.51 s
-[Task 22/25] Current/Best: 9.51/ 16.04 GFLOPS | Progress: (8/20) | 7.08 s
-[Task 22/25] Current/Best: 8.58/ 21.48 GFLOPS | Progress: (12/20) | 9.68 s
-[Task 22/25] Current/Best: 16.72/ 21.48 GFLOPS | Progress: (16/20) | 11.98 s
-[Task 22/25] Current/Best: 5.33/ 21.48 GFLOPS | Progress: (20/20) | 13.55 s Done.
+[Task 22/25] Current/Best: 20.80/ 21.02 GFLOPS | Progress: (4/20) | 4.47 s
+[Task 22/25] Current/Best: 16.86/ 21.02 GFLOPS | Progress: (8/20) | 5.89 s
+[Task 22/25] Current/Best: 16.29/ 21.02 GFLOPS | Progress: (12/20) | 7.47 s
+[Task 22/25] Current/Best: 20.64/ 21.02 GFLOPS | Progress: (16/20) | 9.12 s
+[Task 22/25] Current/Best: 9.55/ 21.02 GFLOPS | Progress: (20/20) | 11.18 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 6.31/ 19.95 GFLOPS | Progress: (4/20) | 5.31 s
-[Task 23/25] Current/Best: 11.13/ 19.95 GFLOPS | Progress: (8/20) | 7.62 s
-[Task 23/25] Current/Best: 23.60/ 23.60 GFLOPS | Progress: (12/20) | 10.28 s
-[Task 23/25] Current/Best: 12.15/ 23.60 GFLOPS | Progress: (16/20) | 13.42 s
-[Task 23/25] Current/Best: 6.49/ 23.60 GFLOPS | Progress: (20/20) | 15.55 s Done.
+[Task 23/25] Current/Best: 14.66/ 17.83 GFLOPS | Progress: (4/20) | 4.23 s
+[Task 23/25] Current/Best: 19.11/ 20.46 GFLOPS | Progress: (8/20) | 6.36 s
+[Task 23/25] Current/Best: 15.40/ 20.90 GFLOPS | Progress: (12/20) | 8.99 s
+[Task 23/25] Current/Best: 10.15/ 20.90 GFLOPS | Progress: (16/20) | 11.44 s
+[Task 23/25] Current/Best: 18.33/ 20.90 GFLOPS | Progress: (20/20) | 13.84 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 6.46/ 6.46 GFLOPS | Progress: (4/20) | 7.36 s
-[Task 24/25] Current/Best: 1.88/ 7.79 GFLOPS | Progress: (8/20) | 18.09 s
-[Task 24/25] Current/Best: 3.01/ 8.99 GFLOPS | Progress: (12/20) | 28.77 s
-[Task 24/25] Current/Best: 9.96/ 9.96 GFLOPS | Progress: (16/20) | 30.69 s
-[Task 24/25] Current/Best: 2.09/ 9.96 GFLOPS | Progress: (20/20) | 40.97 s
+[Task 24/25] Current/Best: 9.87/ 9.87 GFLOPS | Progress: (4/20) | 12.63 s
+[Task 24/25] Current/Best: 3.01/ 9.87 GFLOPS | Progress: (8/20) | 24.38 s
+[Task 24/25] Current/Best: 6.84/ 9.87 GFLOPS | Progress: (12/20) | 34.91 s
+[Task 24/25] Current/Best: 1.61/ 9.87 GFLOPS | Progress: (16/20) | 39.55 s
+[Task 24/25] Current/Best: 6.30/ 9.87 GFLOPS | Progress: (20/20) | 50.29 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-[Task 25/25] Current/Best: 8.73/ 8.73 GFLOPS | Progress: (4/20) | 13.96 s
-[Task 25/25] Current/Best: 3.43/ 8.73 GFLOPS | Progress: (8/20) | 25.67 s
-[Task 25/25] Current/Best: 5.09/ 8.73 GFLOPS | Progress: (12/20) | 30.31 s
-[Task 25/25] Current/Best: 7.15/ 8.73 GFLOPS | Progress: (16/20) | 40.83 s
-[Task 25/25] Current/Best: 1.56/ 8.73 GFLOPS | Progress: (20/20) | 51.52 s
+[Task 25/25] Current/Best: 8.95/ 9.19 GFLOPS | Progress: (4/20) | 3.94 s
+[Task 25/25] Current/Best: 1.54/ 9.19 GFLOPS | Progress: (8/20) | 5.09 s
+[Task 25/25] Current/Best: 3.51/ 9.19 GFLOPS | Progress: (12/20) | 15.84 s
+[Task 25/25] Current/Best: 5.43/ 9.19 GFLOPS | Progress: (16/20) | 20.67 s
+[Task 25/25] Current/Best: 5.81/ 9.34 GFLOPS | Progress: (20/20) | 31.39 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -969,8 +970,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 404.8580872799903, 'median': 404.96806209998795, 'std': 0.46157520536385244}
-unoptimized: {'mean': 518.8625257100057, 'median': 519.0639800500094, 'std': 1.3911651244158252}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 418.28373845000215, 'median': 418.4676126499994, 'std': 1.1869006065156673}
+unoptimized: {'mean': 521.1109951399976, 'median': 520.7685348999973, 'std': 0.9562144510221742}
</pre></div>
</div>
</div>
@@ -984,7 +985,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 33.706 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 22.455 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/57a45d9bef1af358191e7d50043e652c/autotvm_relay_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">autotvm_relay_x86.py</span></code></a></p>
diff --git a/docs/tutorial/cross_compilation_and_rpc.html b/docs/tutorial/cross_compilation_and_rpc.html
index 2017cf1ef0..d892c72574 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -527,7 +527,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.25e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.246e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index d7281fd576..0e9bb90100 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -484,7 +484,7 @@ we can schedule the following series of operations ending with <code class="code
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
... 217 lines suppressed ...