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 2023/01/09 05:26:40 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@a435cbb3b1484e6f347421444168ccc312ef41d3)
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 ff681fcd14 deploying docs (apache/tvm@a435cbb3b1484e6f347421444168ccc312ef41d3)
ff681fcd14 is described below
commit ff681fcd14256946dff623fa4106dbf66b98e01a
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Mon Jan 9 05:26:33 2023 +0000
deploying docs (apache/tvm@a435cbb3b1484e6f347421444168ccc312ef41d3)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 324216 -> 298784 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 23634 -> 22856 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_adreno.rst.txt | 2 +-
.../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 | 22 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../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 | 1408 +++++++++++++++-----
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 22 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 8 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 337 +++--
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../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 | 4 +-
.../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 | 4 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 4 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 62 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 20 +-
.../tutorial/tensor_expr_get_started.rst.txt | 49 +-
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 | 11 +-
docs/how_to/compile_models/from_pytorch.html | 9 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_adreno.html | 2 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 41 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../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 | 38 +-
docs/how_to/deploy_models/sg_execution_times.html | 22 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
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 | 1408 +++++++++++++++-----
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 22 +-
.../tune_with_autotvm/sg_execution_times.html | 8 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 337 +++--
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 4 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
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 | 4 +-
.../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 | 4 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 4 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 274 ++--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 20 +-
docs/tutorial/tensor_expr_get_started.html | 45 +-
130 files changed, 3374 insertions(+), 1781 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 58230570fb..fb3c2850a3 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 c7f45c5bc4..86defffe09 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 85b3c0b75f..3e65c133e2 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -319,7 +319,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 9.125 seconds)
+ **Total running time of the script:** ( 1 minutes 8.729 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 4984c4f526..6ef54fb3ea 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -232,7 +232,7 @@ 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 952ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 954ms/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 7b564a2e36..5afa5c9981 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -116,7 +116,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip7f435239-a9d5-4a5c-bb6f-e647f08a3a07 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip01e257ee-77be-44a5-a5d2-8714a6c23836 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 7e52993cd0..094792b52c 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -121,7 +121,7 @@ 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]
19%|#9 | 7.99M/41.5M [00:00<00:00, 52.1MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 57.8MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 65.0MB/s]
87%|########6 | 36.0M/41.5M [00:00<00:00, 85.6MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 71.4MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 43.8MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 50.3MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 56.1MB/s]
78%|#######8 | 32.4M/41.5M [00:00<00:00, 66.0MB/s]
96%|#########6| 39.9M/41.5M [00:00<00:00, 69.6MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 60.0MB/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 b28ef6f82c..29ccf103e5 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -102,7 +102,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
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]
33%|###3 | 14.9M/44.7M [00:00<00:00, 156MB/s]
67%|######6 | 29.8M/44.7M [00:00<00:00, 122MB/s]
94%|#########3| 41.9M/44.7M [00:00<00:00, 109MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 97.2MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#8 | 8.12M/44.7M [00:00<00:00, 41.8MB/s]
54%|#####3 | 24.0M/44.7M [00:00<00:00, 83.7MB/s]
74%|#######3 | 33.0M/44.7M [00:00<00:00, 64.6MB/s]
99%|#########8| 44.2M/44.7M [00:00<00:00, 73.6MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 70.8MB/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 cb2654a96f..7ffd88f9d4 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -425,7 +425,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 11.934 seconds)
+ **Total running time of the script:** ( 1 minutes 11.554 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 e687bf59a6..aa71362553 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
=================
-**05:41.893** total execution time for **how_to_compile_models** files:
+**05:41.492** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.934 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.554 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:09.125 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:08.729 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.808 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.406 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.173 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:31.998 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:28.871 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.300 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.456 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.234 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.967 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.958 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.392 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.796 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.753 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.131 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.413 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.385 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
index a83a5060ac..9aad85e8fa 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -728,7 +728,7 @@ well as provides information about the model's performance
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2691.7470 2691.0709 2695.0863 2689.2381 1.8076
+ 2548.3779 2545.6305 2569.5322 2544.2804 7.1825
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 dddecf7f16..95dbea95b1 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
@@ -437,7 +437,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.2766 16.1532 16.9554 15.9501 0.3318
+ 15.5592 15.5490 15.6707 15.5240 0.0407
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 fd41481ec8..90d2c82587 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
@@ -131,7 +131,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
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]
5%|4 | 7.99M/170M [00:00<00:02, 70.7MB/s]
11%|# | 18.1M/170M [00:00<00:01, 81.9MB/s]
16%|#5 | 26.5M/170M [00:00<00:01, 84.6MB/s]
20%|## | 34.6M/170M [00:00<00:01, 81.2MB/s]
25%|##4 | 42.4M/170M [00:00<00:02, 62.8MB/s]
31%|### | 52.1M/170M [00:00<00:01, 73.4MB/s]
38%|###7 | 64.0M/170M [00:00<00:01, 74.0MB/s]
43%|####3 | 73.4M/170M [00:01<00:01, 80.2MB/s]
48%|####7 | 81.5M/170M [00:01<00:01, 79.8MB/s]
53%|#####2 | 89.7M/170M [00:01<00:01, 81.5MB/s]
58%|#####7 | 98.4M/170M [00:01<00:00, 84.4MB/s]
64%|######3 | 108M/170M [00:01<00:00, 89.5MB/s]
71%|####### | 120M/170M [00:01<00:00, 82.9MB/s]
78%|#######7 | 132M/170M [00:01<00:00, 93.3MB/s]
83%|########3 | 141M/170M [00:01<00:00, 83.3MB/s]
89%|########9 | 152M/170M [00:01<00:00, 79.3MB/s]
94%|#########4| 160M/170M [00:02<00:00, 80.0MB/s]
99%|#########8| 168M/170M [00:02<00:00, 72.9MB/s]
100%|##########| 170M/170M [00:02<00:00, 78.5MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.99M/170M [00:00<00:02, 78.0MB/s]
9%|9 | 16.0M/170M [00:00<00:02, 71.1MB/s]
16%|#5 | 27.0M/170M [00:00<00:01, 89.3MB/s]
21%|##1 | 35.7M/170M [00:00<00:01, 84.1MB/s]
28%|##8 | 48.0M/170M [00:00<00:01, 81.9MB/s]
34%|###3 | 57.4M/170M [00:00<00:01, 86.7MB/s]
39%|###8 | 65.9M/170M [00:00<00:01, 80.2MB/s]
43%|####3 | 73.7M/170M [00:00<00:01, 80.1MB/s]
48%|####7 | 81.4M/170M [00:01<00:01, 76.2MB/s]
53%|#####3 | 90.6M/170M [00:01<00:01, 80.5MB/s]
58%|#####7 | 98.4M/170M [00:01<00:01, 71.7MB/s]
62%|######2 | 106M/170M [00:01<00:00, 73.0MB/s]
66%|######6 | 113M/170M [00:01<00:00, 70.2MB/s]
71%|####### | 120M/170M [00:01<00:00, 68.6MB/s]
77%|#######6 | 130M/170M [00:01<00:00, 77.5MB/s]
81%|########1 | 138M/170M [00:01<00:00, 75.5MB/s]
86%|########6 | 147M/170M [00:01<00:00, 81.3MB/s]
93%|#########2| 157M/170M [00:02<00:00, 87.2MB/s]
97%|#########7| 166M/170M [00:02<00:00, 84.4MB/s]
100%|##########| 170M/170M [00:02<00:00, 79.0MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: 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)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: 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').
@@ -300,7 +300,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 17.253 seconds)
+ **Total running time of the script:** ( 3 minutes 11.875 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 27e37abed1..56bf1e4181 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -240,7 +240,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
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]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 68.6MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 95.9MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 70.7MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 88.1MB/s]
@@ -422,7 +422,7 @@ 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)
- 90.5975 90.4758 94.0629 90.1740 0.5058
+ 90.2023 90.1006 94.1301 89.9469 0.4430
@@ -471,7 +471,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.859 seconds)
+ **Total running time of the script:** ( 1 minutes 5.747 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 01b786b58c..86775c9b22 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
@@ -436,7 +436,7 @@ 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)
- 120.1702 120.1580 121.6625 119.2851 0.4108
+ 120.0912 120.0693 122.7677 118.7279 0.6104
@@ -473,7 +473,7 @@ 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:** ( 2 minutes 28.878 seconds)
+ **Total running time of the script:** ( 2 minutes 23.152 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 3af8f5ed63..4a6773b747 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -257,7 +257,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 22.062 seconds)
+ **Total running time of the script:** ( 1 minutes 24.812 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 ee5e416b1a..06511ea857 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
@@ -170,7 +170,7 @@ 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]
4%|4 | 5744/132723 [00:00<00:02, 57434.17KB/s]
10%|# | 13360/132723 [00:00<00:01, 68447.02KB/s]
16%|#5 | 21050/132723 [00:00<00:01, 72302.70KB/s]
22%|##1 | 28715/132723 [00:00<00:01, 74001.48KB/s]
27%|##7 | 36427/132723 [00:00<00:01, 75124.31KB/s]
33%|###3 | 44027/132723 [00:00<00:01, 75415.86KB/s]
39%|###9 | 51810/132723 [00:00<00:01, 76203.04KB/s]
45%|####4 | 59498/132723 [00:00<00:00, 76407.88KB/s]
51%|##### | 67235/132723 [00:00<00:00, 76706.62KB/s]
56%|#####6 | 74906/132723 [00:01<00:00, 76451.74KB/s]
62%|######2 | 82595/132723 [00:01<00:00, 76582.84KB/s]
68%|######8 | 90293/132723 [00:01<00:00, 76701.75KB/s]
74%|#######3 | 97997/132723 [00:01<00:00, 76800.41KB/s]
80%|#######9 | 105731/132723 [00:01<00:00, 76960.83KB/s]
85%|########5 | 113431/132723 [00:01<00:00, 76971.44KB/s]
91%|#########
1| 121129/132723 [00:01<00:00, 76872.58KB/s]
97%|#########7| 128974/132723 [00:01<00:00, 77345.07KB/s]
100%|##########| 132723/132723 [00:01<00:00, 75944.35KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|3 | 5039/132723 [00:00<00:02, 50386.32KB/s]
10%|9 | 12768/132723 [00:00<00:01, 66207.40KB/s]
15%|#5 | 20538/132723 [00:00<00:01, 71452.05KB/s]
21%|##1 | 28460/132723 [00:00<00:01, 74517.28KB/s]
27%|##7 | 36183/132723 [00:00<00:01, 75492.31KB/s]
33%|###3 | 44018/132723 [00:00<00:01, 76461.85KB/s]
39%|###9 | 52254/132723 [00:00<00:01, 78386.89KB/s]
45%|####5 | 60309/132723 [00:00<00:00, 79072.98KB/s]
51%|#####1 | 68304/132723 [00:00<00:00, 79345.03KB/s]
58%|#####7 | 76320/132723 [00:01<00:00, 79593.70KB/s]
64%|######3 | 84298/132723 [00:01<00:00, 79649.58KB/s]
70%|######9 | 92338/132723 [00:01<00:00, 79875.03KB/s]
76%|#######5 | 100338/132723 [00:01<00:00, 79907.20KB/s]
82%|########1 | 108393/132723 [00:01<00:00, 80100.38KB/s]
88%|########7 | 116431/132723 [00:01<00:00, 80177.88KB/s]
94%|########
#3| 124449/132723 [00:01<00:00, 80038.06KB/s]
100%|#########9| 132701/132723 [00:01<00:00, 80782.10KB/s]
100%|##########| 132723/132723 [00:01<00:00, 77912.76KB/s]
@@ -246,7 +246,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 7.395 seconds)
+ **Total running time of the script:** ( 3 minutes 5.177 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 9287c6e2f2..60f431ffee 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
@@ -5,26 +5,26 @@
Computation times
=================
-**13:42.282** total execution time for **how_to_deploy_models** files:
+**13:26.413** 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``) | 03:17.253 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:11.875 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:07.395 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:05.177 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:28.878 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:23.152 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:22.062 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:24.812 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:06.859 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:05.747 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:53.523 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:51.339 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.880 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.164 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.446 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:24.682 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.979 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.459 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 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 43e48bb118..f6871798f8 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
@@ -476,7 +476,7 @@ 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.zip0df57d2a-3121-4336-98e0-d7239a445491 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip6a6453e4-4e26-4bcd-8b47-bde16ddd6e0e 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 1683d0d3c8..7613fada87 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
@@ -5,14 +5,14 @@
Computation times
=================
-**00:47.946** total execution time for **how_to_extend_tvm** files:
+**00:46.851** 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``) | 00:44.458 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:43.425 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.443 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.402 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.038 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.017 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 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 7ef8c2c525..af9fea7f3f 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
@@ -220,10 +220,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 7289us [7289us] (46.47%; 46.47%)
- FoldScaleAxis: 8397us [7us] (53.53%; 53.53%)
- FoldConstant: 8389us [1725us] (53.49%; 99.91%)
- InferType: 6664us [6664us] (42.49%; 79.44%)
+ InferType: 7110us [7110us] (46.21%; 46.21%)
+ FoldScaleAxis: 8277us [6us] (53.79%; 53.79%)
+ FoldConstant: 8271us [1680us] (53.75%; 99.93%)
+ InferType: 6591us [6591us] (42.83%; 79.69%)
@@ -262,10 +262,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6687us [6687us] (44.81%; 44.81%)
- FoldScaleAxis: 8235us [5us] (55.19%; 55.19%)
- FoldConstant: 8230us [1705us] (55.15%; 99.94%)
- InferType: 6525us [6525us] (43.73%; 79.29%)
+ InferType: 6652us [6652us] (45.20%; 45.20%)
+ FoldScaleAxis: 8065us [5us] (54.80%; 54.80%)
+ FoldConstant: 8060us [1656us] (54.77%; 99.94%)
+ InferType: 6404us [6404us] (43.52%; 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 8a24b12fd5..1312c2050c 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
@@ -344,7 +344,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.204128 ms
+ Convolution: 40.375934 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 1534167fac..62ffa0e400 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
@@ -661,7 +661,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 13.386995 ms
+ conv2d with tensor core: 13.351292 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 d6c5059d18..ef073d04cf 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -147,8 +147,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.019434
- Baseline: 3.455880
+ Numpy running time: 0.018283
+ Baseline: 3.461599
@@ -242,7 +242,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.300253
+ Opt1: 0.301409
@@ -344,7 +344,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.335396
+ Opt2: 0.329831
@@ -439,7 +439,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.117203
+ Opt3: 0.115119
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109657
+ Opt4: 0.109342
@@ -684,7 +684,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111716
+ Opt5: 0.112251
@@ -808,7 +808,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147122
+ Opt6: 0.147203
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 e4ee4a3ec2..5fa388c0f2 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
=================
-**00:35.181** total execution time for **how_to_optimize_operators** files:
+**00:35.003** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.562 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.361 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.521 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.536 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.098 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.106 | 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 fd8c5edab8..335bcb10cf 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
=================
-**09:28.786** total execution time for **how_to_tune_with_autoscheduler** files:
+**08:55.689** 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``) | 05:42.208 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:32.273 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:32.179 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:31.115 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:01.921 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:01.790 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:49.065 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:27.382 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.089 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.079 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.324 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.050 | 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 27675042a6..f3efee7bd3 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
@@ -243,183 +243,580 @@ cooperative fetching, unrolling and operator fusion.
bias: Buffer(bias_2: Pointer(float32), float32, [1, 512, 1, 1], []),
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 128;
- allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [384]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
- conv2d_nchw_1[2] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 8;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [28]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [1008]), 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, [49], [], scope="local", align=16)[0] = 0f32
+ conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[14] = 0f32
+ conv2d_nchw_1[21] = 0f32
conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[15] = 0f32
+ conv2d_nchw_1[22] = 0f32
+ conv2d_nchw_1[2] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[16] = 0f32
+ conv2d_nchw_1[23] = 0f32
conv2d_nchw_1[3] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
- for (rx.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*1568)
- let cse_var_1: int32 = (rc.outer.outer*288)
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[17] = 0f32
+ conv2d_nchw_1[24] = 0f32
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[18] = 0f32
+ conv2d_nchw_1[25] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[19] = 0f32
+ conv2d_nchw_1[26] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ conv2d_nchw_1[20] = 0f32
+ conv2d_nchw_1[27] = 0f32
+ for (rc.outer.outer: int32, 0, 32) {
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_4: int32 = (rc.outer.outer*784)
+ let cse_var_3: int32 = (ry.outer.outer*7)
+ let cse_var_2: int32 = (rc.outer.outer*144)
+ let cse_var_1: int32 = (ry.outer.outer*3)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], 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_3: Buffer(data_2, float32, [25088], [])[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 49)] = @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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 49), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 98), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 147)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 147), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 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" = 49;
- 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_3[(((((cse_var_2 + (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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 245)] = @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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 245), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 294)] = @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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 294), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 343)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 343), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 441)] = @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_3[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 335)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 490)] = @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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 490), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 539)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 539), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 588), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 637)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 637), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 686)] = @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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 686), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 735)] = @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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 735), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 833)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 833), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 882)] = @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_3[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 678)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 931)] = @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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 931), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 980), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1029)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1029), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1078)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1078), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1127)] = @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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1127), 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" = 49;
- 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_3[(((((cse_var_2 + (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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1225)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1225), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1274)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1274), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1323)] = @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_3[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 1021)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- 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_3[(((((cse_var_2 + (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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1421)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1421), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1470)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1470), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1519)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1519), 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" = 49;
- 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_3[(((((cse_var_2 + (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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1617)] = @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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1617), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1666)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1666), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1715)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1715), 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" = 49;
- 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_3[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 1364)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1813)] = @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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1813), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1862)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1862), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1911)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1911), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 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" = 49;
- 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_3[(((((cse_var_2 + (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" = 49;
- if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 2009)] = 0f32
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1: Buffer(kernel.shared, float32, [384], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((blockIdx.x*18432) + cse_var_1) + (threadIdx.x_2*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 49)] = kernel_3[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 49), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 49), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 98), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 2), 96)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 147)] = kernel_3[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 147), 96)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 17), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel_3[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 196), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 245)] = kernel_3[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 245), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 53), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 294)] = kernel_3[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 294), 96)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 2)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_2 < 41), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 343)] = kernel_3[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 343), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 55), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1008], [], 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_3: Buffer(data_2, float32, [25088], [])[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) - 8)], 0f32 [...]
+ 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_3[((((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_3[((((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_3[((((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_3[((((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_3[((((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_3[((((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_3[((((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_3[((((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_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 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_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 112), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 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_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 224), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 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_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 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 + 448)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 448), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 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_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 560), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 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_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 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 + 784)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 784), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 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_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 896), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 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_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 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 + 1120)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1120), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 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_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1232), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 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_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 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 + 1456)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1456), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 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_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1568), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 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_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 161280)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1792), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 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_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1904), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 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_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 193536)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2128), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 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_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2240), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 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_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 225792)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2464), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 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_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2576), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 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_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2800), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 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_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2912), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 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_3[((((((blockIdx.x*294912) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 290304)]
}
- for (rc.outer.inner: int32, 0, 8) {
- let cse_var_3: int32 = (rc.outer.inner*12)
- {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*252) + threadIdx.x)]*kernel.shared_1[cse_var_3]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rc.outer.inner*252) + threadIdx.x)]*kernel.shared_1[(cse_var_3 + 192)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rc.outer.inner*252) + threadIdx.x)]*kernel.shared_1[(cse_var_3 + 96)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rc.outer.inner*252) + threadIdx.x)]*kernel.shared_1[(cse_var_3 + 288)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_3 + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_3 + 195)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_3 + 99)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_3 + 291)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_3 + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_3 + 198)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_3 + 102)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_3 + 294)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_3 + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_3 + 201)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_3 + 105)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_3 + 297)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_3 + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_3 + 193)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_3 + 97)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_3 + 289)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_3 + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_3 + 196)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_3 + 100)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_3 + 292)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_3 + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_3 + 199)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_3 + 103)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_3 + 295)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_3 + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_3 + 202)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_3 + 106)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_3 + 298)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_3 + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_3 + 194)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_3 + 98)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_3 + 290)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_3 + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_3 + 197)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_3 + 101)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_3 + 293)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_3 + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_3 + 200)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_3 + 104)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_3 + 296)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_3 + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_3 + 203)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_3 + 107)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_3 + 299)]))
- }
+ for (rx.outer.inner: int32, 0, 3) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(rx.outer.inner + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + rx.outer.inner)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(rx.outer.inner + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 768)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(rx.outer.inner + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1536)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(rx.outer.inner + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2304)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 771)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1539)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2307)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 6)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 774)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1542)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2310)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 777)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1545)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2313)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 12)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 780)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1548)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2316)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 783)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1551)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2319)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 786)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1554)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2322)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 789)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1557)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2325)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 792)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1560)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2328)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 795)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1563)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2331)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 798)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1566)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2334)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 33)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 801)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1569)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2337)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 804)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1572)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2340)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 39)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 807)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1575)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2343)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 810)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1578)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2346)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 813)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1581)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2349)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + rx.outer.inner)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 768)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1536)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2304)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 3)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 771)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1539)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2307)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 6)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 774)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1542)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2310)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 777)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1545)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2313)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 12)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 780)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1548)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2316)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 15)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 783)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1551)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2319)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 387)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 387)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 786)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 387)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1554)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 387)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2322)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 21)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 789)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1557)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2325)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 513)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 513)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 792)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 513)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1560)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 513)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2328)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 795)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1563)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2331)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 639)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 639)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 798)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 639)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1566)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 639)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2334)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 702)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 702)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 801)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 702)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1569)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 702)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2337)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 765)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 765)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 804)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 765)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1572)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 765)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2340)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 807)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1575)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2343)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 810)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1578)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2346)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 954)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 954)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 813)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 954)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1581)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 954)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2349)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + rx.outer.inner)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 768)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1536)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2304)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 3)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 771)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1539)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2307)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 6)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 774)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1542)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2310)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 777)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1545)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2313)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 12)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 780)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1548)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2316)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 15)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 783)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1551)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2319)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 396)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 396)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 786)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 396)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1554)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 396)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2322)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 21)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 789)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1557)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2325)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 522)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 522)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 792)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 522)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1560)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 522)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2328)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 795)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1563)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2331)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 798)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1566)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2334)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 711)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 711)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 801)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 711)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1569)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 711)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2337)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 774)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 774)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 804)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 774)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1572)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 774)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2340)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 837)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 837)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 807)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 837)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1575)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 837)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2343)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 810)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1578)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2346)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 963)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 963)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 813)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 963)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1581)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 963)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2349)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + rx.outer.inner)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 768)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1536)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2304)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 3)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 771)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1539)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2307)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 6)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 774)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1542)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2310)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 777)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1545)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2313)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 12)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 780)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1548)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2316)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 15)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 783)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1551)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2319)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 786)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1554)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2322)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 468)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 21)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 468)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 789)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 468)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1557)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 468)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2325)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 531)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 531)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 792)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 531)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1560)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 531)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2328)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 594)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 594)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 795)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 594)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1563)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 594)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2331)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 798)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1566)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2334)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 720)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 720)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 801)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 720)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1569)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 720)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2337)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 783)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 783)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 804)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 783)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1572)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 783)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2340)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 846)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 846)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 807)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 846)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1575)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 846)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2343)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 810)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1578)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2346)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 813)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1581)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2349)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + rx.outer.inner)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 768)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1536)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2304)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 3)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 771)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1539)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2307)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 6)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 774)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1542)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2310)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 777)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1545)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2313)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 12)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 780)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1548)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2316)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 15)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 783)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1551)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2319)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 786)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1554)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2322)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 477)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 21)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 477)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 789)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 477)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1557)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 477)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2325)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 540)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 540)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 792)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 540)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1560)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 540)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2328)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 603)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 603)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 795)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 603)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1563)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 603)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2331)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 798)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1566)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2334)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 801)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1569)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2337)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 792)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 792)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 804)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 792)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1572)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 792)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2340)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 855)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 855)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 807)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 855)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1575)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 855)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2343)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 918)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 918)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 810)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 918)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1578)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 918)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2346)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 813)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1581)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2349)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + rx.outer.inner)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 768)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1536)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2304)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 3)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 771)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1539)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2307)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 6)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 774)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1542)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2310)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 777)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1545)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2313)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 12)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 780)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1548)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2316)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 15)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 783)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1551)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2319)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 786)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1554)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2322)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 21)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 789)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1557)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2325)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 549)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 549)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 792)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 549)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1560)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 549)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2328)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 612)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 612)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 795)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 612)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1563)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 612)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2331)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 675)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 675)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 798)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 675)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1566)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 675)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2334)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 801)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1569)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2337)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 801)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 801)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 804)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 801)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1572)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 801)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2340)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 864)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 864)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 807)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 864)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1575)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 864)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2343)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 927)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 927)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 810)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 927)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1578)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 927)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2346)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 813)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1581)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2349)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + rx.outer.inner)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 768)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1536)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2304)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 3)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 771)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1539)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2307)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 6)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 774)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1542)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2310)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 777)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1545)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2313)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 12)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 780)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1548)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2316)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 15)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 783)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1551)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2319)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 786)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1554)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2322)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 21)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 789)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1557)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2325)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 558)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 558)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 792)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 558)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1560)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 558)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2328)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 621)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 621)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 795)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 621)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1563)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 621)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2331)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 684)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 684)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 798)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 684)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1566)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 684)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2334)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 801)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1569)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2337)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 804)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1572)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2340)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 873)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 873)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 807)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 873)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1575)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 873)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2343)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 936)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 936)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 810)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 936)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1578)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 936)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2346)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 999)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 999)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 813)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 999)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1581)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 999)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2349)]))
}
}
}
}
- for (i1.inner: int32, 0, 2) {
- compute_3: Buffer(compute_2, float32, [25088], [])[(((blockIdx.x*196) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*4) + i1.inner)]), 0f32)
- compute_3[((((blockIdx.x*196) + (i1.inner*49)) + threadIdx.x) + 98)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias_3[(((blockIdx.x*4) + i1.inner) + 2)]), 0f32)
+ for (i2.inner: int32, 0, 7) {
+ compute_3: Buffer(compute_2, float32, [25088], [])[((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*64) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute_3[(((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7)) + 784)] = max((conv2d_nchw_1[(i2.inner + 7)] + bias_3[(((blockIdx.x*64) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
+ compute_3[(((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7)) + 1568)] = max((conv2d_nchw_1[(i2.inner + 14)] + bias_3[(((blockIdx.x*64) + floordiv(threadIdx.x, 7)) + 32)]), 0f32)
+ compute_3[(((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7)) + 2352)] = max((conv2d_nchw_1[(i2.inner + 21)] + bias_3[(((blockIdx.x*64) + floordiv(threadIdx.x, 7)) + 48)]), 0f32)
}
}
}
@@ -474,7 +871,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.244 ms
+ Execution time of this operator: 0.415 ms
@@ -522,33 +919,33 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
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=2)
+ 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=1)
- 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=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=4)
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=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=4)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
+ 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=1)
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=3)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
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=1)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
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=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
- 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_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=4)
+ 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=7)
@@ -571,14 +968,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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)
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=49)
+ 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)
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=49)
+ 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)
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:
@@ -596,127 +993,538 @@ 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__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[4];
- __shared__ float pad_temp_shared[2016];
- __shared__ float kernel_shared[384];
+ 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[28];
+ __shared__ float pad_temp_shared[1008];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[14] = 0.000000e+00f;
+ conv2d_nchw[21] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[15] = 0.000000e+00f;
+ conv2d_nchw[22] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[16] = 0.000000e+00f;
+ conv2d_nchw[23] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
- for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[17] = 0.000000e+00f;
+ conv2d_nchw[24] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[18] = 0.000000e+00f;
+ conv2d_nchw[25] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[19] = 0.000000e+00f;
+ conv2d_nchw[26] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ conv2d_nchw[20] = 0.000000e+00f;
+ conv2d_nchw[27] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
__syncthreads();
- 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 * 1568) + ((int)threadIdx.x)) + rx_outer_outer) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((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 * 1568) + (((((int)threadIdx.x) + 49) / 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) + 98)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 98) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 147) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 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 * 1568) + (((((int)threadIdx.x) + 196) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 245)] = (((((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 * 1568) + (((((int)threadIdx.x) + 245) / 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) + 294)] = (((((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 * 1568) + (((((int)threadIdx.x) + 294) / 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) + 343)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 343) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 441)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 1568) + ((int)threadIdx.x)) + rx_outer_outer) + 335)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 490)] = (((((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 * 1568) + (((((int)threadIdx.x) + 490) / 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) + 539)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 539) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 588) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 637)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 637) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((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 * 1568) + (((((int)threadIdx.x) + 686) / 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) + 735)] = (((((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 * 1568) + (((((int)threadIdx.x) + 735) / 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) + 784)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 833)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 833) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 882)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 1568) + ((int)threadIdx.x)) + rx_outer_outer) + 678)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 931)] = (((((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 * 1568) + (((((int)threadIdx.x) + 931) / 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) + 980)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 980) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1029)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1029) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1078)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1078) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1127)] = (((((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 * 1568) + (((((int)threadIdx.x) + 1127) / 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) + 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 * 1568) + (((((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) + 1225)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1225) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1274)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1274) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1323)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 1568) + ((int)threadIdx.x)) + rx_outer_outer) + 1021)] : 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 * 1568) + (((((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) + 1421)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1421) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1470)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1470) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1519)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1519) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 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 * 1568) + (((((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) + 1617)] = (((((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 * 1568) + (((((int)threadIdx.x) + 1617) / 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) + 1666)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1666) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1715)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1715) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 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 * 1568) + ((int)threadIdx.x)) + rx_outer_outer) + 1364)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1813)] = (((((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 * 1568) + (((((int)threadIdx.x) + 1813) / 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) + 1862)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1862) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1911)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1911) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 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 * 1568) + (((((int)threadIdx.x) + 1960) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 7) {
- pad_temp_shared[(((int)threadIdx.x) + 2009)] = 0.000000e+00f;
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 49) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 49) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 98) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) + 2) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 147)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 147) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 17) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 196) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 4) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 245)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 245) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 53) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 294) / 96) * 4608)) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 18)];
- if (((int)threadIdx.x) < 41) {
- kernel_shared[(((int)threadIdx.x) + 343)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 343) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 55) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ 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 * 784) + ((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((int)threadIdx.x) + 896) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 448) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 560) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 784) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 896) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1120) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1232) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1456) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1568) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 161280)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1792) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1904) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 193536)];
+ kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2128) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2240) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 225792)];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2464) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2576) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2800) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2912) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 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) * 294912) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 290304)];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[(rc_outer_inner * 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 192)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 96)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 288)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 195)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 99)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 291)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 198)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 102)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 294)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 201)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 105)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 297)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 193)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 97)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 289)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 196)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 100)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 292)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 199)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 103)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 295)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 202)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 106)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 298)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 194)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 98)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 290)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 197)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 101)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 293)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 200)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 104)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 296)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 203)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 107)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 299)]));
+ for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + rx_outer_inner)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 768)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1536)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2304)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 771)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1539)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2307)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 6)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 774)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1542)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2310)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 777)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1545)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2313)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 12)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 780)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1548)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2316)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 783)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1551)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2319)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 18)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 786)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1554)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2322)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 789)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1557)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2325)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 792)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1560)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2328)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 27)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 795)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1563)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2331)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 798)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1566)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2334)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 33)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 801)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1569)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2337)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 804)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1572)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2340)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 39)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 807)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1575)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2343)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 810)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1578)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2346)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 45)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 813)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1581)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2349)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + rx_outer_inner)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 768)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1536)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2304)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 3)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 771)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1539)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2307)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 6)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 774)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1542)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2310)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 777)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1545)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2313)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 12)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 780)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1548)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2316)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 15)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 783)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1551)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2319)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 18)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 786)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1554)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2322)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 21)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 789)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1557)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2325)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 792)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1560)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2328)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 795)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1563)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2331)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 639)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 639)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 798)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 639)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1566)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 639)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2334)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 702)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 702)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 801)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 702)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1569)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 702)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2337)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 765)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 765)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 804)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 765)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1572)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 765)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2340)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 807)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1575)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2343)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 810)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1578)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2346)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 954)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 954)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 813)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 954)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1581)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 954)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2349)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + rx_outer_inner)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 768)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1536)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2304)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 3)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 771)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1539)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2307)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 6)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 774)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1542)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2310)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 9)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 777)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1545)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2313)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 12)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 780)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1548)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2316)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 15)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 783)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1551)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2319)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 18)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 786)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1554)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2322)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 21)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 789)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1557)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2325)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 792)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1560)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2328)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 795)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1563)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2331)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 798)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1566)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2334)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 711)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 711)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 801)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 711)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1569)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 711)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2337)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 774)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 774)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 804)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 774)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1572)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 774)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2340)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 837)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 837)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 807)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 837)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1575)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 837)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2343)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 810)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1578)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2346)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 963)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 963)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 813)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 963)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1581)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 963)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2349)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + rx_outer_inner)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 768)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1536)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2304)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 3)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 771)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1539)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2307)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 6)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 774)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1542)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2310)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 9)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 777)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1545)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2313)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 12)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 780)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1548)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2316)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 15)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 783)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1551)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2319)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 18)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 786)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1554)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2322)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 21)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 789)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1557)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2325)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 792)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1560)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2328)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 795)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1563)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2331)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 798)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1566)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2334)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 720)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 720)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 801)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 720)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1569)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 720)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2337)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 783)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 783)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 804)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 783)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1572)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 783)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2340)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 846)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 846)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 807)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 846)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1575)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 846)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2343)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 810)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1578)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2346)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 813)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1581)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2349)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + rx_outer_inner)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 768)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1536)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2304)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 3)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 771)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1539)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2307)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 6)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 774)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1542)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2310)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 9)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 777)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1545)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2313)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 12)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 780)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1548)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2316)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 15)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 783)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1551)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2319)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 18)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 786)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1554)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2322)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 21)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 789)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1557)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2325)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 792)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1560)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2328)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 795)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1563)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2331)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 798)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1566)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2334)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 801)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1569)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2337)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 792)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 792)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 804)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 792)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1572)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 792)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2340)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 855)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 855)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 807)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 855)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1575)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 855)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2343)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 918)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 918)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 810)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 918)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1578)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 918)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2346)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 813)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1581)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2349)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + rx_outer_inner)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 768)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1536)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2304)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 3)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 771)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1539)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2307)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 6)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 774)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1542)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2310)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 777)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1545)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2313)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 12)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 780)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1548)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2316)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 15)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 783)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1551)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2319)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 18)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 786)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1554)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2322)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 21)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 789)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1557)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2325)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 549)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 549)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 792)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 549)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1560)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 549)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2328)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 795)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1563)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2331)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 675)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 675)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 798)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 675)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1566)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 675)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2334)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 801)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1569)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2337)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 801)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 801)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 804)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 801)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1572)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 801)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2340)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 864)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 864)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 807)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 864)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1575)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 864)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2343)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 927)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 927)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 810)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 927)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1578)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 927)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2346)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 813)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1581)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2349)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + rx_outer_inner)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 768)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1536)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2304)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 3)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 771)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1539)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2307)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 6)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 774)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1542)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2310)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 9)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 777)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1545)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2313)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 12)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 780)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1548)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2316)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 15)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 783)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1551)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2319)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 18)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 786)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1554)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2322)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 21)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 789)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1557)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2325)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 558)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 558)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 792)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 558)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1560)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 558)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2328)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 795)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1563)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2331)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 684)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 684)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 798)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 684)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1566)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 684)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2334)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 801)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1569)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2337)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 804)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1572)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2340)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 873)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 873)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 807)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 873)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1575)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 873)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2343)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 936)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 936)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 810)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 936)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1578)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 936)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2346)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 999)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 999)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 813)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 999)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1581)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 999)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2349)]));
}
}
}
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[(((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 4) + i1_inner)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x)) + 98)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 4) + i1_inner) + 2)]), 0.000000e+00f);
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 64) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 784)] = max((conv2d_nchw[(i2_inner + 7)] + bias[(((((int)blockIdx.x) * 64) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 1568)] = max((conv2d_nchw[(i2_inner + 14)] + bias[(((((int)blockIdx.x) * 64) + (((int)threadIdx.x) / 7)) + 32)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 2352)] = max((conv2d_nchw[(i2_inner + 21)] + bias[(((((int)blockIdx.x) * 64) + (((int)threadIdx.x) / 7)) + 48)]), 0.000000e+00f);
}
}
@@ -778,7 +1586,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 42.208 seconds)
+ **Total running time of the script:** ( 5 minutes 32.273 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 c99229c605..7ff555ab18 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
@@ -647,7 +647,7 @@ 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)
- 7.8874 7.8938 7.8943 7.8741 0.0094
+ 7.8737 7.8755 7.8770 7.8685 0.0037
@@ -675,7 +675,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.921 seconds)
+ **Total running time of the script:** ( 1 minutes 1.790 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
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 e96ac64cff..ed4a5391c5 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
@@ -666,7 +666,7 @@ 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)
- 749.6636 749.6433 749.9993 749.3483 0.2661
+ 753.1270 753.0658 753.7329 752.5821 0.4718
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 32.179 seconds)
+ **Total running time of the script:** ( 1 minutes 31.115 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 8585841a08..542bc8b6da 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
@@ -390,28 +390,28 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [1024]), storage_scope = global {
- for (i.outer.inner: int32, 0, 16) {
+ for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 4) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 16) {
for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [1024], [])[((((i.outer.inner*64) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
+ compute_4: Buffer(compute_3, float32, [2048], [])[((((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
}
}
for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
- for (i.inner: int32, 0, 2) {
+ for (i.inner: int32, 0, 16) {
for (j: int32, 0, 16) {
let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_2: int32 = ((((i.outer.inner*64) + (i.inner*32)) + (nb_j.inner*16)) + j)
- compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.outer.inner*512)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ let cse_var_2: int32 = ((((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16)) + j)
+ compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ for (i0.inner: int32, 0, 64) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_4, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
}
}
@@ -468,7 +468,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 2.130 ms
+ Execution time of this operator: 1.504 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 1f402e7066..5f8c00bc05 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
@@ -5,16 +5,16 @@
Computation times
=================
-**00:33.178** total execution time for **how_to_tune_with_autotvm** files:
+**00:40.880** 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``) | 00:33.143 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:40.845 | 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_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
-+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 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 |
++--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.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 7564983168..bad8f17546 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
@@ -269,7 +269,8 @@ 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: 115.61/115.61 result: MeasureResult(costs=(0.0020025195660377357,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.174020767211914, timestamp=1673240573.1018007) [('tile_f', [-1, 8, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7651630
+ No: 2 GFLOPS: 0.00/115.61 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -391,8 +392,8 @@ 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 875, 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, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2218954
- 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, 32, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1275857
+ No: 3 GFLOPS: 0.00/115.61 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -514,8 +515,8 @@ 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 875, 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, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4094784
- 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, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2768102
+ No: 4 GFLOPS: 0.00/115.61 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -637,8 +638,8 @@ 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 875, 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, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2373231
- No: 4 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, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9359252
+ No: 5 GFLOPS: 0.00/115.61 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -760,8 +761,8 @@ 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 875, 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, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6703601
- No: 5 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, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2021690
+ No: 6 GFLOPS: 0.00/115.61 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -883,8 +884,8 @@ 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 875, 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, 128, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754811
- No: 6 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, 2, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6672351
+ No: 7 GFLOPS: 0.00/115.61 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1006,10 +1007,8 @@ 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 875, 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, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2688852
- No: 7 GFLOPS: 81.13/81.13 result: MeasureResult(costs=(0.002853425575,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.593247652053833, timestamp=1673207944.3081067) [('tile_f', [-1, 1, 64, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3494833
- No: 8 GFLOPS: 565.24/565.24 result: MeasureResult(costs=(0.00040955998465473144,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5637280941009521, timestamp=1673207945.3138244) [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5081626
- No: 9 GFLOPS: 0.00/565.24 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8191521
+ No: 8 GFLOPS: 0.00/115.61 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1131,8 +1130,9 @@ 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 875, 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, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8284183
- No: 10 GFLOPS: 0.00/565.24 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2544456
+ No: 9 GFLOPS: 1.67/115.61 result: MeasureResult(costs=(0.13828141775,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8109846115112305, timestamp=1673240579.1649926) [('tile_f', [-1, 1, 2, 128]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6455893
+ No: 10 GFLOPS: 0.00/115.61 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1254,10 +1254,8 @@ 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 875, 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, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2580423
- No: 11 GFLOPS: 6.14/565.24 result: MeasureResult(costs=(0.03770536025,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2243459224700928, timestamp=1673207948.3442025) [('tile_f', [-1, 64, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2331153
- No: 12 GFLOPS: 212.14/565.24 result: MeasureResult(costs=(0.0010912774489795919,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7804789543151855, timestamp=1673207949.3513148) [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7053461
- No: 13 GFLOPS: 0.00/565.24 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7923929
+ No: 11 GFLOPS: 0.00/115.61 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1379,8 +1377,8 @@ 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 875, 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, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3857813
- No: 14 GFLOPS: 0.00/565.24 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 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,519531
+ No: 12 GFLOPS: 0.00/115.61 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1502,161 +1500,133 @@ 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 875, 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, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7109464
- No: 15 GFLOPS: 0.00/565.24 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
- blob = feval(*args)
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9868970
+ No: 13 GFLOPS: 124.87/124.87 result: MeasureResult(costs=(0.0018539882985074627,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2893645763397217, timestamp=1673240581.8125648) [('tile_f', [-1, 4, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,38322
+ No: 14 GFLOPS: 0.00/124.87 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, 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 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/./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):
- 4: TVMFuncCall
+ 24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ 23: 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:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
- 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 706, 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 746, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 144, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 72, 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: 0x00007f9e4d319fa2
- 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:185
- 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:1007
- 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:223
- 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
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 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:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:395
+ 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:381
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:276
+ 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:454
+ 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:1749
+ 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:1693
+ 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:1617
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:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
- 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
+ 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 875, 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):
- 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, 32, 1, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5456389
- No: 16 GFLOPS: 0.00/565.24 result: 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:1730
+ 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:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:395
+ 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:381
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:276
+ 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:454
+ 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:1749
+ 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:1693
+ 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:1617
+ 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 875, 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, 32, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1607482
+ No: 15 GFLOPS: 0.95/124.87 result: MeasureResult(costs=(0.24270285025000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.071226596832275, timestamp=1673240585.3610103) [('tile_f', [-1, 1, 1, 32]), ('tile_y', [-1, 7, 1, 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,9732325
+ No: 16 GFLOPS: 0.00/124.87 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1778,8 +1748,8 @@ 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 875, 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, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6723322
- No: 17 GFLOPS: 0.00/565.24 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7162256
+ No: 17 GFLOPS: 0.00/124.87 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1901,8 +1871,26 @@ 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 875, 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, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3441340
- No: 18 GFLOPS: 0.00/565.24 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1721740
+ No: 18 GFLOPS: 0.00/124.87 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 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+ TimeoutError
+
+ [('tile_f', [-1, 8, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('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', 512), ('unroll_explicit', 1)],None,7403718
+ No: 19 GFLOPS: 0.00/124.87 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2024,8 +2012,8 @@ 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 875, 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, 64, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,982788
- No: 19 GFLOPS: 0.00/565.24 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10192803
+ No: 20 GFLOPS: 0.00/124.87 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2147,8 +2135,7 @@ 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 875, 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, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2930145
- No: 20 GFLOPS: 5.25/565.24 result: MeasureResult(costs=(0.044077056749999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.035950183868408, timestamp=1673207957.5529802) [('tile_f', [-1, 1, 2, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5326610
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8559880
@@ -2203,9 +2190,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5081626
+ [('tile_f', [-1, 4, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,38322
Finish loading 20 records
- Time cost of this operator: 0.000721
+ Time cost of this operator: 0.001924
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 b8432065f6..d475226dbf 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
@@ -368,10 +368,10 @@ 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 310.6 98.715 (1, 2, 10, 10, 3) 2 1 [310.6]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.076 0.978 (1, 6, 10, 10) 1 1 [3.076]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.308 (1, 1, 10, 10, 3) 1 1 [0.969]
- Total_time - 314.644 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.3 98.702 (1, 2, 10, 10, 3) 2 1 [311.3]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.134 0.994 (1, 6, 10, 10) 1 1 [3.134]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.96 0.305 (1, 1, 10, 10, 3) 1 1 [0.96]
+ Total_time - 315.395 - - - - -
@@ -436,10 +436,10 @@ 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 105.1 97.451 (1, 6, 10, 10, 1) 2 1 [105.1]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.787 1.657 (1, 6, 10, 10) 1 1 [1.787]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.963 0.893 (1, 1, 10, 10, 3) 1 1 [0.963]
- Total_time - 107.849 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 134.1 97.943 (1, 6, 10, 10, 1) 2 1 [134.1]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.856 1.356 (1, 6, 10, 10) 1 1 [1.856]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.96 0.701 (1, 1, 10, 10, 3) 1 1 [0.96]
+ Total_time - 136.916 - - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index 3ee1ff8d88..6bb08ce83e 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -117,7 +117,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 114MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 36.3MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -322,7 +322,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.488 seconds)
+ **Total running time of the script:** ( 1 minutes 2.762 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
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 c2c07a86dc..2e60fcf5a5 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
@@ -218,7 +218,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmpd4y05yt_/images/random'
+ '/tmp/tmp350nmquk/images/random'
@@ -309,7 +309,7 @@ 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: [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
+ :alt: [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -318,8 +318,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpd4y05yt_/images/target contains 8144 images
- /tmp/tmpd4y05yt_/images/random contains 5000 images
+ /tmp/tmp350nmquk/images/target contains 8144 images
+ /tmp/tmp350nmquk/images/random contains 5000 images
@@ -494,13 +494,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.1971 - accuracy: 0.9311 - val_loss: 0.2416 - val_accuracy: 0.9139 - 47s/epoch - 143ms/step
+ 328/328 - 47s - loss: 0.2178 - accuracy: 0.9226 - val_loss: 0.2906 - val_accuracy: 0.9048 - 47s/epoch - 143ms/step
Epoch 2/3
- 328/328 - 44s - loss: 0.0919 - accuracy: 0.9670 - val_loss: 0.1066 - val_accuracy: 0.9698 - 44s/epoch - 133ms/step
+ 328/328 - 43s - loss: 0.0973 - accuracy: 0.9636 - val_loss: 0.1064 - val_accuracy: 0.9634 - 43s/epoch - 132ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0586 - accuracy: 0.9781 - val_loss: 0.1025 - val_accuracy: 0.9690 - 43s/epoch - 133ms/step
+ 328/328 - 43s - loss: 0.0753 - accuracy: 0.9725 - val_loss: 0.0871 - val_accuracy: 0.9687 - 43s/epoch - 131ms/step
- <keras.callbacks.History object at 0x7f2f09e55910>
+ <keras.callbacks.History object at 0x7f5cfce22e10>
@@ -857,7 +857,7 @@ 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 17.521 seconds)
+ **Total running time of the script:** ( 4 minutes 24.563 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 30258fd961..ffa780e492 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
@@ -5,18 +5,18 @@
Computation times
=================
-**06:25.983** total execution time for **how_to_work_with_microtvm** files:
+**06:29.692** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:17.521 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:24.563 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:04.488 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:02.762 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:52.163 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:50.810 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.974 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.775 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.834 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.780 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.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 cf645a9a15..99d3ceb279 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
=================
-**00:44.747** total execution time for **how_to_work_with_relay** files:
+**00:44.343** 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``) | 00:32.865 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.213 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.206 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.526 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.669 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.597 | 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 ca7e35f5ca..53798ad222 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
@@ -265,7 +265,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f2f0a77d8c0>
+ <function my_cuda_math_rule at 0x7f5d861fbdd0>
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 c2f19dbbc4..a7a43fecae 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
=================
-**00:07.699** total execution time for **how_to_work_with_schedules** files:
+**00:07.257** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.211 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.749 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.120 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.154 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.581 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.577 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.569 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.561 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.116 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.114 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.050 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.049 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.029 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.024 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.023 | 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 bcc8c2ee8c..d56024583c 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.
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp1re09rxh/input0.cc'\nsource_filename = \"/tmp/tmp1re09rxh/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/tmpfe44yf11/input0.cc'\nsource_filename = \"/tmp/tmpfe44yf11/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 566908b267..845482fc04 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
=================
-**00:26.490** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:25.973** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.484 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:25.966 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 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 bbe53ce80a..fd1603b818 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -293,7 +293,7 @@ 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 29.20s!
+ resnet18_v1 inference graph built in 28.36s!
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 6099be0853..1fc762d394 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -337,7 +337,7 @@ 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 19.78s!
+ yolov3-tiny inference graph built in 19.34s!
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 0e0ffd59f8..c1edc4997d 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
=================
-**01:32.432** total execution time for **topic_vta_tutorials_frontend** files:
+**01:31.283** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:46.372 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:46.068 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:46.060 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:45.214 | 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 08e3e43e61..d0718e6176 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
=================
-**00:03.193** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.129** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.729 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.673 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.464 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.456 | 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 379cc980a6..69f47d8f2b 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -8,7 +8,7 @@ Computation times
**00:00.824** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.442 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.448 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.382 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.376 | 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 29cc07c9aa..c11487d216 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -329,7 +329,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.969 ms
+ Execution time of this operator: 97.153 ms
@@ -447,7 +447,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.591 seconds)
+ **Total running time of the script:** ( 1 minutes 23.747 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 bc2c291ba9..b2511ff729 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -454,16 +454,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 9.62/9.62 result: MeasureResult(costs=(0.027898718,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6814179420471191, timestamp=1673206541.7217193) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 3.31/9.62 result: MeasureResult(costs=(0.081053556,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5457041263580322, timestamp=1673206543.2708719) [('tile_y', [-1, 64]), ('tile_x', [-1, 8])],None,36
- No: 3 GFLOPS: 1.81/9.62 result: MeasureResult(costs=(0.1486419228,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6199307441711426, timestamp=1673206546.717056) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 4 GFLOPS: 11.74/11.74 result: MeasureResult(costs=(0.0228617026,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5938427448272705, timestamp=1673206547.3465004) [('tile_y', [-1, 256]), ('tile_x', [-1, 512])],None,98
- No: 5 GFLOPS: 1.86/11.74 result: MeasureResult(costs=(0.144347768,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5399982929229736, timestamp=1673206550.092905) [('tile_y', [-1, 512]), ('tile_x', [-1, 8])],None,39
- No: 6 GFLOPS: 2.71/11.74 result: MeasureResult(costs=(0.0989268586,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8124949932098389, timestamp=1673206552.6885347) [('tile_y', [-1, 2]), ('tile_x', [-1, 8])],None,31
- No: 7 GFLOPS: 12.73/12.73 result: MeasureResult(costs=(0.021078582399999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5693621635437012, timestamp=1673206554.0728147) [('tile_y', [-1, 32]), ('tile_x', [-1, 512])],None,95
- No: 8 GFLOPS: 12.68/12.73 result: MeasureResult(costs=(0.021176568200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.652878999710083, timestamp=1673206554.6630762) [('tile_y', [-1, 1]), ('tile_x', [-1, 64])],None,60
- No: 9 GFLOPS: 12.24/12.73 result: MeasureResult(costs=(0.0219353664,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5713191032409668, timestamp=1673206555.346897) [('tile_y', [-1, 8]), ('tile_x', [-1, 256])],None,83
- No: 10 GFLOPS: 1.75/12.73 result: MeasureResult(costs=(0.15359519800000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6658265590667725, timestamp=1673206558.0598083) [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
+ No: 1 GFLOPS: 0.50/0.50 result: MeasureResult(costs=(0.5390616124000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.850629091262817, timestamp=1673239170.5277846) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
+ No: 2 GFLOPS: 9.12/9.12 result: MeasureResult(costs=(0.029428969399999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7751691341400146, timestamp=1673239172.0044737) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
+ No: 3 GFLOPS: 11.41/11.41 result: MeasureResult(costs=(0.023520208,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6208279132843018, timestamp=1673239172.6393936) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
+ No: 4 GFLOPS: 1.72/11.41 result: MeasureResult(costs=(0.1564901232,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.722008466720581, timestamp=1673239176.1454906) [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
+ No: 5 GFLOPS: 2.06/11.41 result: MeasureResult(costs=(0.1301242782,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3213050365448, timestamp=1673239178.6602304) [('tile_y', [-1, 256]), ('tile_x', [-1, 4])],None,28
+ No: 6 GFLOPS: 3.95/11.41 result: MeasureResult(costs=(0.0679048804,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3706169128417969, timestamp=1673239179.9976563) [('tile_y', [-1, 64]), ('tile_x', [-1, 16])],None,46
+ No: 7 GFLOPS: 13.14/13.14 result: MeasureResult(costs=(0.020434777199999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6490328311920166, timestamp=1673239181.3323748) [('tile_y', [-1, 128]), ('tile_x', [-1, 128])],None,77
+ No: 8 GFLOPS: 10.44/13.14 result: MeasureResult(costs=(0.025721925200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6830213069915771, timestamp=1673239182.00092) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
+ No: 9 GFLOPS: 1.47/13.14 result: MeasureResult(costs=(0.1827412212,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.1473960876464844, timestamp=1673239185.2715592) [('tile_y', [-1, 4]), ('tile_x', [-1, 1])],None,2
+ No: 10 GFLOPS: 0.89/13.14 result: MeasureResult(costs=(0.3000508844,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.023648738861084, timestamp=1673239190.318813) [('tile_y', [-1, 64]), ('tile_x', [-1, 2])],None,16
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index d6d9b3700b..a759fe2064 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -324,7 +324,7 @@ standard deviation.
.. code-block:: none
- {'mean': 512.9814760500005, 'median': 513.116963899995, 'std': 2.1695880671952343}
+ {'mean': 511.56517501999707, 'median': 511.7573987999947, 'std': 2.2377189524267567}
@@ -558,31 +558,29 @@ 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: 9.44/ 16.64 GFLOPS | Progress: (4/20) | 7.85 s
[Task 1/25] Current/Best: 11.19/ 16.64 GFLOPS | Progress: (8/20) | 11.81 s
[Task 1/25] Current/Best: 14.30/ 22.29 GFLOPS | Progress: (12/20) | 14.30 s
[Task 1/25] Current/Best: 11.04/ 22.29 GFLOPS | Progress: (16/20) | 17.25 s
[Task 1/25] Current/Best: 23.94/ 23.94 GFLOPS | Progress: (20/20) | 19.21 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.87/ 12.92 GFLOPS | Progress: (4/20) | 4.11 s
[Task 2/25] Current/Best: 11.01/ 18.58 GFLOPS | Progress: (8/20) | 5.81 s
[Task 2/25] Current/Best: 15.19/ 23.00 GFLOPS | Progress: (12/20) | 7.51 s
[Task 2/25] Current/Best: 19.23/ 23.00 GFLOPS | Progress: (16/20) | 9.20 s
[Task 2/25] Current/Best: 12.68/ 23.00 GFLOPS | Progress: (20/20) | 10.61 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 15.86/ 22.40 GFLOPS | Progress: (4/20) | 3.88 s
[Task 3/25] Current/Best: 23.37/ 23.37 GFLOPS | Progress: (8/20) | 6.04 s
[Task 3/25] Current/Best: 3.17/ 23.37 GFLOPS | Progress: (12/20) | 10.15 s
[Task 3/25] Current/Best: 3.14/ 23.37 GFLOPS | Progress: (16/20) | 13.40 s
[Task 3/25] Current/Best: 19.33/ 23.37 GFLOPS | Progress: (20/20) | 15.40 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 13.25/ 16.98 GFLOPS | Progress: (4/20) | 4.00 s
[Task 4/25] Current/Best: 8.45/ 20.64 GFLOPS | Progress: (8/20) | 6.02 s
[Task 4/25] Current/Best: 16.85/ 20.64 GFLOPS | Progress: (12/20) | 8.04 s
[Task 4/25] Current/Best: 13.77/ 20.64 GFLOPS | Progress: (16/20) | 11.11 s
[Task 4/25] Current/Best: 11.21/ 20.64 GFLOPS | Progress: (20/20) | 14.23 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 10.67/ 11.44 GFLOPS | Progress: (4/20) | 4.20 s
[Task 5/25] Current/Best: 13.26/ 13.26 GFLOPS | Progress: (8/20) | 6.94 s
[Task 5/25] Current/Best: 6.01/ 13.26 GFLOPS | Progress: (12/20) | 9.21 s
[Task 5/25] Current/Best: 9.55/ 13.49 GFLOPS | Progress: (16/20) | 11.37 s
[Task 5/25] Current/Best: 3.62/ 18.22 GFLOPS | Progress: (20/20) | 13.84 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 13.17/ 14.65 GFLOPS | Progress: (4/20) | 4.35 s
[Task 6/25] Current/Best: 9.66/ 19.63 GFLOPS | Progress: (8/20) | 6.63 s
[Task 6/25] Current/Best: 8.86/ 19.63 GFLOPS | Progress: (12/20) | 8.97 s
[Task 6/25] Current/Best: 11.10/ 19.63 GFLOPS | Progress: (16/20) | 12.36 s
[Task 6/25] Current/Best: 6.08/ 19.63 GFLOPS | Progress: (20/20) | 15.42 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.75/ 20.02 GFLOPS | Progress: (4/20) | 4.79 s
[Task 7/25] Current/Best: 13.52/ 20.02 GFLOPS | Progress: (8/20) | 7.79 s
[Task 7/25] Current/Best: 8.81/ 20.02 GFLOPS | Progress: (12/20) | 10.28 s
[Task 7/25] Current/Best: 6.11/ 20.02 GFLOPS | Progress: (16/20) | 12.86 s
[Task 7/25] Current/Best: 18.44/ 20.02 GFLOPS | Progress: (20/20) | 15.39 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 8.86/ 13.74 GFLOPS | Progress: (4/20) | 4.86 s
[Task 8/25] Current/Best: 2.10/ 18.54 GFLOPS | Progress: (8/20) | 8.07 s
[Task 8/25] Current/Best: 10.50/ 18.54 GFLOPS | Progress: (12/20) | 20.06 s
[Task 8/25] Current/Best: 2.77/ 18.54 GFLOPS | Progress: (16/20) | 23.05 s
[Task 8/25] Current/Best: 12.51/ 18.54 GFLOPS | Progress: (20/20) | 34.43 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 11.53/ 21.54 GFLOPS | Progress: (4/20) | 8.03 s
[Task 9/25] Current/Best: 6.49/ 21.54 GFLOPS | Progress: (8/20) | 9.82 s
[Task 9/25] Current/Best: 14.49/ 21.54 GFLOPS | Progress: (12/20) | 14.09 s
[Task 9/25] Current/Best: 11.36/ 21.54 GFLOPS | Progress: (16/20) | 16.31 s
[Task 9/25] Current/Best: 16.49/ 21.54 GFLOPS | Progress: (20/20
) | 18.17 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 4.27/ 12.90 GFLOPS | Progress: (4/20) | 3.84 s
[Task 10/25] Current/Best: 11.56/ 16.10 GFLOPS | Progress: (8/20) | 6.40 s
[Task 10/25] Current/Best: 15.00/ 16.10 GFLOPS | Progress: (12/20) | 9.89 s
[Task 10/25] Current/Best: 14.47/ 16.10 GFLOPS | Progress: (16/20) | 12.17 s
[Task 10/25] Current/Best: 10.07/ 17.27 GFLOPS | Progress: (20/20) | 14.95 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 7.05/ 23.97 GFLOPS | Progress: (4/20) | 4.22 s
[Task 11/25] Current/Best: 11.56/ 23.97 GFLOPS | Progress: (8/20) | 8.07 s
[Task 11/25] Current/Best: 3.13/ 23.97 GFLOPS | Progress: (12/20) | 10.93 s
[Task 11/25] Current/Best: 15.95/ 23.97 GFLOPS | Progress: (16/20) | 13.79 s
[Task 11/25] Current/Best: 17.29/ 23.97 GFLOPS | Progress: (20/20) | 16.05 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 4.46/ 15.48 GFLOPS | Progress: (4/20) | 8.06 s
[Task 12/25] Current/Best: 13.49/ 15.48 GFLOPS | Progress: (8/20) | 11.96 s
[Task 12/25] Current/Best: 13.07/ 17.99 GFLOPS | Progress: (12/20) | 15.00 s
[Task 12/25] Current/Best: 17.50/ 18.36 GFLOPS | Progress: (16/20) | 17.30 s
[Task 12/25] Current/Best: 2.94/ 18.36 GFLOPS | Progress: (20/20) | 22.28 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 13.96/ 19.63 GFLOPS | Progress: (4/20) | 4.50 s
[Task 13/25] Current/Best: 6.38/ 19.63 GFLOPS | Progress: (8/20) | 7.19 s
[Task 13/25] Current/Best: 15.51/ 21.63 GFLOPS | Progress: (12/20) | 9.52 s
[Task 13/25] Current/Best: 19.83/ 21.63 GFLOPS | Progress: (16/20) | 12.86 s
[Task 13/25] Current/Best: 6.21/ 21.63 GFLOPS | Progress: (20/20) | 16.54 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 9.86/ 13.25 GFLOPS | Progress: (4/20) | 5.13 s
[Task 14/25] Current/Best: 12.93/ 16.26 GFLOPS | Progress: (8/20) | 8.76 s
[Task 14/25] Current/Best: 17.65/ 17.65 GFLOPS | Progress: (12/20) | 10.55 s
[Task 14/25] Current/Best: 6.16/ 17.65 GFLOPS | Progress: (16/20) | 14.31 s
[Task 14/25] Current/Best: 19.69/ 19.69 GFLOPS | Progress: (20/20) | 17.56 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 6.63/ 15.46 GFLOPS | Progress: (4/20) | 7.98 s Done.
- Done.
-
[Task 15/25] Current/Best: 6.41/ 15.46 GFLOPS | Progress: (8/20) | 13.32 s
[Task 15/25] Current/Best: 9.40/ 20.68 GFLOPS | Progress: (12/20) | 15.64 s
[Task 15/25] Current/Best: 13.80/ 20.68 GFLOPS | Progress: (16/20) | 17.21 s
[Task 15/25] Current/Best: 22.44/ 22.44 GFLOPS | Progress: (20/20) | 19.06 s Done.
-
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 8.90/ 19.15 GFLOPS | Progress: (4/20) | 3.36 s
[Task 16/25] Current/Best: 18.50/ 19.15 GFLOPS | Progress: (8/20) | 5.81 s
[Task 16/25] Current/Best: 18.30/ 19.15 GFLOPS | Progress: (12/20) | 7.43 s
[Task 16/25] Current/Best: 14.68/ 19.15 GFLOPS | Progress: (16/20) | 9.77 s
[Task 16/25] Current/Best: 11.12/ 19.15 GFLOPS | Progress: (20/20) | 11.43 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 17.11/ 17.94 GFLOPS | Progress: (4/20) | 4.51 s
[Task 17/25] Current/Best: 17.67/ 23.04 GFLOPS | Progress: (8/20) | 6.45 s
[Task 17/25] Current/Best: 13.11/ 23.04 GFLOPS | Progress: (12/20) | 8.33 s
[Task 17/25] Current/Best: 11.98/ 23.04 GFLOPS | Progress: (16/20) | 10.87 s
[Task 17/25] Current/Best: 14.08/ 23.04 GFLOPS | Progress: (20/20) | 13.63 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 4.34/ 17.17 GFLOPS | Progress: (4/20) | 4.25 s
[Task 18/25] Current/Best: 19.33/ 19.86 GFLOPS | Progress: (8/20) | 7.18 s
[Task 18/25] Current/Best: 8.96/ 19.86 GFLOPS | Progress: (12/20) | 9.95 s
[Task 18/25] Current/Best: 5.61/ 19.86 GFLOPS | Progress: (16/20) | 16.09 s
[Task 18/25] Current/Best: 15.71/ 19.86 GFLOPS | Progress: (20/20) | 18.67 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 11.34/ 11.34 GFLOPS | Progress: (4/20) | 5.79 s
[Task 19/25] Current/Best: 17.77/ 17.77 GFLOPS | Progress: (8/20) | 10.95 s
[Task 19/25] Current/Best: 5.28/ 19.19 GFLOPS | Progress: (12/20) | 14.44 s
[Task 19/25] Current/Best: 8.94/ 23.19 GFLOPS | Progress: (16/20) | 17.37 s
[Task 19/25] Current/Best: 5.33/ 23.19 GFLOPS | Progress: (20/20) | 20.07 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.85/ 12.88 GFLOPS | Progress: (4/20) | 5.36 s
[Task 20/25] Current/Best: 4.78/ 15.08 GFLOPS | Progress: (8/20) | 9.11 s
[Task 20/25] Current/Best: 1.58/ 16.87 GFLOPS | Progress: (12/20) | 12.50 s
[Task 20/25] Current/Best: 15.85/ 16.87 GFLOPS | Progress: (16/20) | 16.26 s
[Task 20/25] Current/Best: 7.34/ 19.61 GFLOPS | Progress: (20/20) | 19.08 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 7.99/ 16.32 GFLOPS | Progress: (4/20) | 3.87 s
[Task 21/25] Current/Best: 13.72/ 21.63 GFLOPS | Progress: (8/20) | 6.35 s
[Task 21/25] Current/Best: 5.31/ 21.63 GFLOPS | Progress: (12/20) | 8.59 s
[Task 21/25] Current/Best: 15.03/ 21.63 GFLOPS | Progress: (16/20) | 11.85 s
[Task 21/25] Current/Best: 8.25/ 21.63 GFLOPS | Progress: (20/20)
| 14.34 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 12.82/ 12.82 GFLOPS | Progress: (4/20) | 4.36 s Done.
- Done.
-
[Task 22/25] Current/Best: 5.30/ 15.88 GFLOPS | Progress: (8/20) | 9.28 s
[Task 22/25] Current/Best: 11.36/ 18.43 GFLOPS | Progress: (12/20) | 11.41 s
[Task 22/25] Current/Best: 14.04/ 22.02 GFLOPS | Progress: (16/20) | 13.52 s
[Task 22/25] Current/Best: 15.99/ 22.02 GFLOPS | Progress: (20/20) | 15.22 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 14.25/ 14.25 GFLOPS | Progress: (4/20) | 5.16 s
[Task 23/25] Current/Best: 10.59/ 22.87 GFLOPS | Progress: (8/20) | 7.67 s
[Task 23/25] Current/Best: 18.50/ 22.87 GFLOPS | Progress: (12/20) | 9.81 s
[Task 23/25] Current/Best: 6.13/ 22.87 GFLOPS | Progress: (16/20) | 13.76 s
[Task 23/25] Current/Best: 10.69/ 22.87 GFLOPS | Progress: (20/20) | 17.43 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 3.50/ 3.50 GFLOPS | Progress: (4/20) | 10.28 s
[Task 24/25] Current/Best: 7.50/ 7.50 GFLOPS | Progress: (8/20) | 17.66 s
[Task 24/25] Current/Best: 6.85/ 7.50 GFLOPS | Progress: (12/20) | 28.59 s
[Task 24/25] Current/Best: 0.68/ 7.50 GFLOPS | Progress: (16/20) | 39.58 s
[Task 24/25] Current/Best: 9.07/ 9.07 GFLOPS | Progress: (20/20) | 47.55 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 3.49/ 8.60 GFLOPS | Progress: (4/20) | 7.30 s
[Task 25/25] Current/Best: 2.86/ 8.60 GFLOPS | Progress: (8/20) | 9.06 s
[Task 25/25] Current/Best: 0.00/ 8.60 GFLOPS | Progress: (12/20) | 19.15 s Done.
-
[Task 25/25] Current/Best: 2.87/ 8.60 GFLOPS | Progress: (16/20) | 22.03 s
[Task 25/25] Current/Best: 1.55/ 8.60 GFLOPS | Progress: (20/20) | 23.42 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 9.52/ 22.23 GFLOPS | Progress: (4/20) | 7.22 s
[Task 1/25] Current/Best: 12.91/ 22.23 GFLOPS | Progress: (8/20) | 10.84 s
[Task 1/25] Current/Best: 10.18/ 22.23 GFLOPS | Progress: (12/20) | 14.69 s
[Task 1/25] Current/Best: 16.62/ 22.23 GFLOPS | Progress: (16/20) | 17.48 s
[Task 1/25] Current/Best: 14.32/ 22.23 GFLOPS | Progress: (20/20) | 19.42 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 9.62/ 21.06 GFLOPS | Progress: (4/20) | 3.37 s
[Task 2/25] Current/Best: 16.78/ 21.06 GFLOPS | Progress: (8/20) | 4.95 s
[Task 2/25] Current/Best: 14.95/ 21.06 GFLOPS | Progress: (12/20) | 6.86 s
[Task 2/25] Current/Best: 19.56/ 21.06 GFLOPS | Progress: (16/20) | 8.67 s
[Task 2/25] Current/Best: 9.79/ 21.06 GFLOPS | Progress: (20/20) | 10.29 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 11.18/ 13.23 GFLOPS | Progress: (4/20) | 4.49 s
[Task 3/25] Current/Best: 14.60/ 14.84 GFLOPS | Progress: (8/20) | 7.31 s
[Task 3/25] Current/Best: 17.77/ 17.77 GFLOPS | Progress: (12/20) | 9.90 s
[Task 3/25] Current/Best: 14.56/ 23.83 GFLOPS | Progress: (16/20) | 12.26 s
[Task 3/25] Current/Best: 9.16/ 23.83 GFLOPS | Progress: (20/20) | 15.47 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 13.48/ 13.48 GFLOPS | Progress: (4/20) | 4.26 s
[Task 4/25] Current/Best: 10.62/ 13.48 GFLOPS | Progress: (8/20) | 9.18 s
[Task 4/25] Current/Best: 12.80/ 18.61 GFLOPS | Progress: (12/20) | 11.94 s
[Task 4/25] Current/Best: 11.02/ 18.61 GFLOPS | Progress: (16/20) | 14.36 s
[Task 4/25] Current/Best: 14.36/ 21.45 GFLOPS | Progress: (20/20) | 16.68 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 13.04/ 13.53 GFLOPS | Progress: (4/20) | 3.89 s
[Task 5/25] Current/Best: 5.79/ 20.35 GFLOPS | Progress: (8/20) | 6.64 s
[Task 5/25] Current/Best: 11.87/ 20.35 GFLOPS | Progress: (12/20) | 8.89 s
[Task 5/25] Current/Best: 5.07/ 20.35 GFLOPS | Progress: (16/20) | 10.94 s
[Task 5/25] Current/Best: 11.76/ 20.35 GFLOPS | Progress: (20/20) | 14.19 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 2.62/ 16.97 GFLOPS | Progress: (4/20) | 5.29 s
[Task 6/25] Current/Best: 2.94/ 20.35 GFLOPS | Progress: (8/20) | 8.73 s
[Task 6/25] Current/Best: 13.17/ 20.35 GFLOPS | Progress: (12/20) | 11.57 s
[Task 6/25] Current/Best: 9.02/ 20.36 GFLOPS | Progress: (16/20) | 14.04 s
[Task 6/25] Current/Best: 3.19/ 20.36 GFLOPS | Progress: (20/20) | 17.98 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 16.08/ 16.08 GFLOPS | Progress: (4/20) | 4.11 s
[Task 7/25] Current/Best: 8.74/ 16.08 GFLOPS | Progress: (8/20) | 7.85 s
[Task 7/25] Current/Best: 9.18/ 19.39 GFLOPS | Progress: (12/20) | 10.88 s
[Task 7/25] Current/Best: 11.23/ 19.39 GFLOPS | Progress: (16/20) | 13.87 s
[Task 7/25] Current/Best: 15.32/ 19.39 GFLOPS | Progress: (20/20) | 16.13 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 2.55/ 12.26 GFLOPS | Progress: (4/20) | 10.89 s
[Task 8/25] Current/Best: 8.08/ 12.26 GFLOPS | Progress: (8/20) | 19.18 s
[Task 8/25] Current/Best: 5.97/ 12.26 GFLOPS | Progress: (12/20) | 25.91 s
[Task 8/25] Current/Best: 13.11/ 13.11 GFLOPS | Progress: (16/20) | 29.88 s
[Task 8/25] Current/Best: 13.86/ 13.86 GFLOPS | Progress: (20/20) | 32.50 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 11.73/ 18.62 GFLOPS | Progress: (4/20) | 4.56 s
[Task 9/25] Current/Best: 11.20/ 18.62 GFLOPS | Progress: (8/20) | 11.70 s
[Task 9/25] Current/Best: 9.68/ 19.95 GFLOPS | Progress: (12/20) | 15.22 s
[Task 9/25] Current/Best: 5.21/ 19.95 GFLOPS | Progress: (16/20) | 20.65 s
[Task 9/25] Current/Best: 16.01/ 19.95 GFLOPS | Progress: (20/20) | 22.31 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 4.31/ 18.63 GFLOPS | Progress: (4/20) | 4.72 s
[Task 10/25] Current/Best: 15.53/ 18.63 GFLOPS | Progress: (8/20) | 6.71 s
[Task 10/25] Current/Best: 3.14/ 18.63 GFLOPS | Progress: (12/20) | 9.53 s
[Task 10/25] Current/Best: 14.31/ 18.63 GFLOPS | Progress: (16/20) | 11.34 s
[Task 10/25] Current/Best: 10.33/ 18.63 GFLOPS | Progress: (20/20) | 13.16 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 8.43/ 23.15 GFLOPS | Progress: (4/20) | 4.32 s
[Task 11/25] Current/Best: 16.38/ 23.15 GFLOPS | Progress: (8/20) | 7.45 s
[Task 11/25] Current/Best: 16.44/ 23.15 GFLOPS | Progress: (12/20) | 9.85 s
[Task 11/25] Current/Best: 6.84/ 23.15 GFLOPS | Progress: (16/20) | 13.09 s
[Task 11/25] Current/Best: 19.14/ 23.15 GFLOPS | Progress: (20/20) | 15.71 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 3.10/ 14.10 GFLOPS | Progress: (4/20) | 5.56 s
[Task 12/25] Current/Best: 5.85/ 18.71 GFLOPS | Progress: (8/20) | 7.65 s
[Task 12/25] Current/Best: 15.05/ 18.71 GFLOPS | Progress: (12/20) | 10.82 s
[Task 12/25] Current/Best: 5.18/ 20.96 GFLOPS | Progress: (16/20) | 14.50 s
[Task 12/25] Current/Best: 11.00/ 20.96 GFLOPS | Progress: (20/20) | 17.59 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 9.48/ 21.39 GFLOPS | Progress: (4/20) | 4.14 s
[Task 13/25] Current/Best: 15.63/ 21.39 GFLOPS | Progress: (8/20) | 6.07 s
[Task 13/25] Current/Best: 16.12/ 21.39 GFLOPS | Progress: (12/20) | 9.01 s
[Task 13/25] Current/Best: 18.64/ 21.39 GFLOPS | Progress: (16/20) | 13.34 s
[Task 13/25] Current/Best: 8.76/ 21.39 GFLOPS | Progress: (20/20) | 16.08 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 15.25/ 22.25 GFLOPS | Progress: (4/20) | 4.24 s
[Task 14/25] Current/Best: 13.88/ 22.25 GFLOPS | Progress: (8/20) | 8.57 s
[Task 14/25] Current/Best: 9.17/ 22.25 GFLOPS | Progress: (12/20) | 14.89 s
[Task 14/25] Current/Best: 10.72/ 22.25 GFLOPS | Progress: (16/20) | 21.00 s
[Task 14/25] Current/Best: 17.61/ 22.25 GFLOPS | Progress: (20/20) | 23.63 s Done.
+
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 12.36/ 19.35 GFLOPS | Progress: (4/20) | 3.77 s
[Task 15/25] Current/Best: 13.98/ 19.35 GFLOPS | Progress: (8/20) | 5.79 s
[Task 15/25] Current/Best: 17.28/ 21.09 GFLOPS | Progress: (12/20) | 7.27 s
[Task 15/25] Current/Best: 21.02/ 21.09 GFLOPS | Progress: (16/20) | 8.98 s
[Task 15/25] Current/Best: 11.23/ 21.09 GFLOPS | Progress: (20/20) | 11.22 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 17.99/ 17.99 GFLOPS | Progress: (4/20) | 3.62 s
[Task 16/25] Current/Best: 13.51/ 17.99 GFLOPS | Progress: (8/20) | 5.47 s
[Task 16/25] Current/Best: 14.24/ 17.99 GFLOPS | Progress: (12/20) | 7.64 s
[Task 16/25] Current/Best: 11.34/ 17.99 GFLOPS | Progress: (16/20) | 11.57 s
[Task 16/25] Current/Best: 10.00/ 18.50 GFLOPS | Progress: (20/20) |
15.21 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 22.31/ 22.31 GFLOPS | Progress: (4/20) | 4.11 s
[Task 17/25] Current/Best: 6.14/ 22.31 GFLOPS | Progress: (8/20) | 6.41 s
[Task 17/25] Current/Best: 12.87/ 22.31 GFLOPS | Progress: (12/20) | 9.03 s
[Task 17/25] Current/Best: 12.20/ 22.31 GFLOPS | Progress: (16/20) | 11.68 s
[Task 17/25] Current/Best: 10.32/ 22.31 GFLOPS | Progress: (20/20) | 16.83 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 2.86/ 19.07 GFLOPS | Progress: (4/20) | 5.24 s
[Task 18/25] Current/Best: 16.98/ 19.07 GFLOPS | Progress: (8/20) | 7.31 s
[Task 18/25] Current/Best: 18.68/ 19.07 GFLOPS | Progress: (12/20) | 10.69 s
[Task 18/25] Current/Best: 4.98/ 19.07 GFLOPS | Progress: (16/20) | 13.00 s
[Task 18/25] Current/Best: 1.57/ 19.07 GFLOPS | Progress: (20/20) | 16.32 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 8.93/ 20.13 GFLOPS | Progress: (4/20) | 4.60 s
[Task 19/25] Current/Best: 9.55/ 20.13 GFLOPS | Progress: (8/20) | 7.38 s
[Task 19/25] Current/Best: 17.10/ 20.13 GFLOPS | Progress: (12/20) | 10.48 s
[Task 19/25] Current/Best: 9.27/ 20.13 GFLOPS | Progress: (16/20) | 13.74 s
[Task 19/25] Current/Best: 17.51/ 20.13 GFLOPS | Progress: (20/20) | 17.80 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 18.15/ 18.15 GFLOPS | Progress: (4/20) | 4.23 s
[Task 20/25] Current/Best: 7.43/ 18.15 GFLOPS | Progress: (8/20) | 7.45 s
[Task 20/25] Current/Best: 10.97/ 18.15 GFLOPS | Progress: (12/20) | 11.54 s Done.
+
[Task 20/25] Current/Best: 8.87/ 18.15 GFLOPS | Progress: (16/20) | 13.54 s
[Task 20/25] Current/Best: 16.43/ 18.15 GFLOPS | Progress: (20/20) | 16.75 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 8.39/ 12.96 GFLOPS | Progress: (4/20) | 4.96 s
[Task 21/25] Current/Best: 4.49/ 16.93 GFLOPS | Progress: (8/20) | 7.37 s
[Task 21/25] Current/Best: 5.43/ 16.93 GFLOPS | Progress: (12/20) | 10.03 s
[Task 21/25] Current/Best: 17.45/ 22.50 GFLOPS | Progress: (16/20) | 11.96 s
[Task 21/25] Current/Best: 16.63/ 22.50 GFLOPS | Progress: (20/20) | 14.85 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 10.59/ 19.78 GFLOPS | Progress: (4/20) | 3.95 s
[Task 22/25] Current/Best: 10.91/ 21.11 GFLOPS | Progress: (8/20) | 5.99 s
[Task 22/25] Current/Best: 10.14/ 21.11 GFLOPS | Progress: (12/20
) | 8.53 s
[Task 22/25] Current/Best: 18.11/ 21.11 GFLOPS | Progress: (16/20) | 10.71 s
[Task 22/25] Current/Best: 15.90/ 21.11 GFLOPS | Progress: (20/20) | 12.32 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 11.50/ 20.74 GFLOPS | Progress: (4/20) | 5.36 s
[Task 23/25] Current/Best: 12.13/ 20.74 GFLOPS | Progress: (8/20) | 8.37 s
[Task 23/25] Current/Best: 2.63/ 20.74 GFLOPS | Progress: (12/20) | 12.25 s
[Task 23/25] Current/Best: 9.58/ 20.74 GFLOPS | Progress: (16/20) | 15.80 s
[Task 23/25] Current/Best: 16.92/ 20.74 GFLOPS | Progress: (20/20) | 18.39 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 0.74/ 8.01 GFLOPS | Progress: (4/20) | 12.78 s
[Task 24/25] Current/Best: 3.61/ 9.24 GFLOPS | Progress: (8/20) | 23.71 s Done.
+
[Task 24/25] Current/Best: 3.71/ 10.24 GFLOPS | Progress: (12/20) | 34.64 s
[Task 24/25] Current/Best: 1.69/ 10.24 GFLOPS | Progress: (16/20) | 45.69 s
[Task 24/25] Current/Best: 3.92/ 10.24 GFLOPS | Progress: (20/20) | 48.19 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 3.01/ 8.38 GFLOPS | Progress: (4/20) | 5.16 s
[Task 25/25] Current/Best: 5.02/ 8.49 GFLOPS | Progress: (8/20) | 6.69 s
[Task 25/25] Current/Best: 1.55/ 9.25 GFLOPS | Progress: (12/20) | 8.27 s
[Task 25/25] Current/Best: 8.48/ 9.25 GFLOPS | Progress: (16/20) | 9.63 s
[Task 25/25] Current/Best: 7.21/ 9.25 GFLOPS | Progress: (20/20) | 18.54 s Done.
@@ -679,9 +677,9 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621104
- class='n02123159 tiger cat' with probability=0.356377
- class='n02124075 Egyptian cat' with probability=0.019713
+ class='n02123045 tabby, tabby cat' with probability=0.621103
+ class='n02123159 tiger cat' with probability=0.356379
+ class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -737,8 +735,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 408.15722969999797, 'median': 408.19497814999295, 'std': 2.4655740798439547}
- unoptimized: {'mean': 512.9814760500005, 'median': 513.116963899995, 'std': 2.1695880671952343}
+ optimized: {'mean': 418.37471445000347, 'median': 418.23366605000274, 'std': 0.4591835005156814}
+ unoptimized: {'mean': 511.56517501999707, 'median': 511.7573987999947, 'std': 2.2377189524267567}
@@ -761,7 +759,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 11 minutes 11.378 seconds)
+ **Total running time of the script:** ( 11 minutes 4.451 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 003bc4c93c..429ee45a48 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -274,7 +274,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.245e-07 secs/op
+ 1.203e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 75040d1713..d0e5471c47 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -264,7 +264,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x17e034a0)), stage(b, placeholder(b, 0x5306300)), 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, 0x23312e10)), stage(b, placeholder(b, 0x6ab6f10)), 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 78d901d8da..80a0c20d25 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**14:19.345** total execution time for **tutorial** files:
+**14:37.512** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:11.378 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:04.451 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:07.591 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:23.747 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:02.668 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.991 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:34.021 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.693 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:21.240 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:32.911 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.439 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.711 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.818 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.822 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.179 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.172 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.009 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.002 | 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 c1938a5acf..363bffc558 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -298,7 +298,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
+ Numpy running time: 0.000007
naive: 0.000007
@@ -397,7 +397,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000006
+ parallel: 0.000007
@@ -452,7 +452,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000025
+ vector: 0.000042
@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, [n: int32], [stride: int32], type="auto"),
@@ -503,10 +503,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.756029999654856e-06 1.0
- naive 6.6697e-06 0.8599373649014769
- parallel 6.0653999999999996e-06 0.7820237931351361
- vector 2.4616699999999998e-05 3.1738789046838964
+ numpy 7.306019999759883e-06 1.0
+ naive 7.489e-06 1.0250450998281049
+ parallel 6.970399999999999e-06 0.9540625402379251
+ vector 4.18898e-05 5.733600510452577
@@ -927,7 +927,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018343
+ Numpy running time: 0.018771
@@ -985,7 +985,7 @@ optimizations.
.. code-block:: none
- none: 3.535982
+ none: 3.339059
@@ -1087,7 +1087,7 @@ schedule.
.. code-block:: none
- blocking: 0.299280
+ blocking: 0.292577
@@ -1182,7 +1182,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.335652
+ vectorization: 0.333358
@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, [1024, 1024], []),
@@ -1255,7 +1255,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.119530
+ loop permutation: 0.116399
@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, [1024, 1024], []),
@@ -1353,7 +1353,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.109487
+ array packing: 0.109907
@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, [1024, 1024], []),
@@ -1445,7 +1445,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110940
+ block caching: 0.111226
@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, [1024, 1024], []),
@@ -1530,7 +1530,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.146024
+ parallelization: 0.146855
@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, [1024, 1024], []),
@@ -1610,13 +1610,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.535982266 1.0
- blocking 0.2992804805 0.08463856942318726
- vectorization 0.3356515825 0.094924566146
- loop permutation 0.11952960940000001 0.033803792103068206
- array packing 0.1094872316 0.03096373888884204
- block caching 0.11093986420000002 0.03137455333606586
- parallelization 0.1460238378 0.04129654133282353
+ none 3.3390590394 1.0
+ blocking 0.2925770818 0.08762261413999245
+ vectorization 0.3333578841 0.0998358759657935
+ loop permutation 0.1163994854 0.03485996624393799
+ array packing 0.1099073437 0.032915663485767355
+ block caching 0.11122612800000001 0.03331062035368694
+ parallelization 0.1468552615 0.043981031711972554
@@ -1656,11 +1656,6 @@ 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 2.668 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 8dbd312f1e..09f3490f23 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-a99f0c15458653896c0bbe00ebf91d144c37aff2
+a435cbb3b1484e6f347421444168ccc312ef41d3
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 845eaa3660..73c1bd9a6f 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -585,7 +585,7 @@ 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 9.125 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.729 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 835b1db04f..a4dd750674 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ Tensorflow is also required since it’s used as the default backend of keras.</
<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 952ms/step
+1/1 [==============================] - 1s 954ms/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 8386b6be2a..205f6deb9e 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -439,7 +439,7 @@
<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.zip7f435239-a9d5-4a5c-bb6f-e647f08a3a07 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.zip01e257ee-77be-44a5-a5d2-8714a6c23836 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 76679c11c1..9752d552a1 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -449,11 +449,12 @@ 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]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 52.1MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 57.8MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 65.0MB/s]
- 87%|########6 | 36.0M/41.5M [00:00<00:00, 85.6MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 71.4MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 43.8MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 50.3MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 56.1MB/s]
+ 78%|#######8 | 32.4M/41.5M [00:00<00:00, 66.0MB/s]
+ 96%|#########6| 39.9M/41.5M [00:00<00:00, 69.6MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 60.0MB/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 a4bc9afb6d..395ccebedd 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -432,10 +432,11 @@ be unstable.</p>
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]
- 33%|###3 | 14.9M/44.7M [00:00<00:00, 156MB/s]
- 67%|######6 | 29.8M/44.7M [00:00<00:00, 122MB/s]
- 94%|#########3| 41.9M/44.7M [00:00<00:00, 109MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 97.2MB/s]
+ 18%|#8 | 8.12M/44.7M [00:00<00:00, 41.8MB/s]
+ 54%|#####3 | 24.0M/44.7M [00:00<00:00, 83.7MB/s]
+ 74%|#######3 | 33.0M/44.7M [00:00<00:00, 64.6MB/s]
+ 99%|#########8| 44.2M/44.7M [00:00<00:00, 73.6MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 70.8MB/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 eca91944a9..cfbab4e4c9 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -649,7 +649,7 @@ 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 11.934 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.554 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 bbcc72ce74..ceca9e8dea 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>05:41.893</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:41.492</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,43 +349,43 @@
</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>01:11.934</p></td>
+<td><p>01:11.554</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>01:09.125</p></td>
+<td><p>01:08.729</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>00:46.808</p></td>
+<td><p>00:46.406</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>00:32.173</p></td>
+<td><p>00:31.998</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>00:28.871</p></td>
+<td><p>00:29.300</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:26.456</p></td>
+<td><p>00:26.234</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:24.967</p></td>
+<td><p>00:24.958</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>00:22.392</p></td>
+<td><p>00:22.796</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>00:16.753</p></td>
+<td><p>00:17.131</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>00:02.413</p></td>
+<td><p>00:02.385</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno.html b/docs/how_to/deploy_models/deploy_model_on_adreno.html
index 8a39df1689..34b97ce6f2 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -920,7 +920,7 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2691.7470 2691.0709 2695.0863 2689.2381 1.8076
+ 2548.3779 2545.6305 2569.5322 2544.2804 7.1825
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
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 9fe428e5d2..dc9f77854b 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -662,7 +662,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.2766 16.1532 16.9554 15.9501 0.3318
+ 15.5592 15.5490 15.6707 15.5240 0.0407
</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 3cf684dbdd..3e27307460 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -454,25 +454,26 @@ be unstable.</p>
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]
- 5%|4 | 7.99M/170M [00:00<00:02, 70.7MB/s]
- 11%|# | 18.1M/170M [00:00<00:01, 81.9MB/s]
- 16%|#5 | 26.5M/170M [00:00<00:01, 84.6MB/s]
- 20%|## | 34.6M/170M [00:00<00:01, 81.2MB/s]
- 25%|##4 | 42.4M/170M [00:00<00:02, 62.8MB/s]
- 31%|### | 52.1M/170M [00:00<00:01, 73.4MB/s]
- 38%|###7 | 64.0M/170M [00:00<00:01, 74.0MB/s]
- 43%|####3 | 73.4M/170M [00:01<00:01, 80.2MB/s]
- 48%|####7 | 81.5M/170M [00:01<00:01, 79.8MB/s]
- 53%|#####2 | 89.7M/170M [00:01<00:01, 81.5MB/s]
- 58%|#####7 | 98.4M/170M [00:01<00:00, 84.4MB/s]
- 64%|######3 | 108M/170M [00:01<00:00, 89.5MB/s]
- 71%|####### | 120M/170M [00:01<00:00, 82.9MB/s]
- 78%|#######7 | 132M/170M [00:01<00:00, 93.3MB/s]
- 83%|########3 | 141M/170M [00:01<00:00, 83.3MB/s]
- 89%|########9 | 152M/170M [00:01<00:00, 79.3MB/s]
- 94%|#########4| 160M/170M [00:02<00:00, 80.0MB/s]
- 99%|#########8| 168M/170M [00:02<00:00, 72.9MB/s]
-100%|##########| 170M/170M [00:02<00:00, 78.5MB/s]
+ 5%|4 | 7.99M/170M [00:00<00:02, 78.0MB/s]
+ 9%|9 | 16.0M/170M [00:00<00:02, 71.1MB/s]
+ 16%|#5 | 27.0M/170M [00:00<00:01, 89.3MB/s]
+ 21%|##1 | 35.7M/170M [00:00<00:01, 84.1MB/s]
+ 28%|##8 | 48.0M/170M [00:00<00:01, 81.9MB/s]
+ 34%|###3 | 57.4M/170M [00:00<00:01, 86.7MB/s]
+ 39%|###8 | 65.9M/170M [00:00<00:01, 80.2MB/s]
+ 43%|####3 | 73.7M/170M [00:00<00:01, 80.1MB/s]
+ 48%|####7 | 81.4M/170M [00:01<00:01, 76.2MB/s]
+ 53%|#####3 | 90.6M/170M [00:01<00:01, 80.5MB/s]
+ 58%|#####7 | 98.4M/170M [00:01<00:01, 71.7MB/s]
+ 62%|######2 | 106M/170M [00:01<00:00, 73.0MB/s]
+ 66%|######6 | 113M/170M [00:01<00:00, 70.2MB/s]
+ 71%|####### | 120M/170M [00:01<00:00, 68.6MB/s]
+ 77%|#######6 | 130M/170M [00:01<00:00, 77.5MB/s]
+ 81%|########1 | 138M/170M [00:01<00:00, 75.5MB/s]
+ 86%|########6 | 147M/170M [00:01<00:00, 81.3MB/s]
+ 93%|#########2| 157M/170M [00:02<00:00, 87.2MB/s]
+ 97%|#########7| 166M/170M [00:02<00:00, 84.4MB/s]
+100%|##########| 170M/170M [00:02<00:00, 79.0MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: 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)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: 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=& [...]
@@ -570,7 +571,7 @@ 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 17.253 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 11.875 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 d15ccb8011..567d5d6ed1 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -498,8 +498,8 @@ training. Other models require a full post training calibration.</p>
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]
- 59%|#####8 | 7.99M/13.6M [00:00<00:00, 68.6MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 95.9MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 70.7MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 88.1MB/s]
</pre></div>
</div>
</div>
@@ -590,7 +590,7 @@ 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)
- 90.5975 90.4758 94.0629 90.1740 0.5058
+ 90.2023 90.1006 94.1301 89.9469 0.4430
</pre></div>
</div>
<div class="admonition note">
@@ -629,7 +629,7 @@ 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 6.859 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.747 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 fa4cdd1f13..cc8f63a7be 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -583,7 +583,7 @@ 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)
- 120.1702 120.1580 121.6625 119.2851 0.4108
+ 120.0912 120.0693 122.7677 118.7279 0.6104
</pre></div>
</div>
<div class="admonition note">
@@ -611,7 +611,7 @@ 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> ( 2 minutes 28.878 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 23.152 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 c2d6457360..4b42ee3e23 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -521,7 +521,7 @@ 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 22.062 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 24.812 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 4bb6e8237e..119b32a70b 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -463,24 +463,24 @@ 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]
- 4%|4 | 5744/132723 [00:00<00:02, 57434.17KB/s]
- 10%|# | 13360/132723 [00:00<00:01, 68447.02KB/s]
- 16%|#5 | 21050/132723 [00:00<00:01, 72302.70KB/s]
- 22%|##1 | 28715/132723 [00:00<00:01, 74001.48KB/s]
- 27%|##7 | 36427/132723 [00:00<00:01, 75124.31KB/s]
- 33%|###3 | 44027/132723 [00:00<00:01, 75415.86KB/s]
- 39%|###9 | 51810/132723 [00:00<00:01, 76203.04KB/s]
- 45%|####4 | 59498/132723 [00:00<00:00, 76407.88KB/s]
- 51%|##### | 67235/132723 [00:00<00:00, 76706.62KB/s]
- 56%|#####6 | 74906/132723 [00:01<00:00, 76451.74KB/s]
- 62%|######2 | 82595/132723 [00:01<00:00, 76582.84KB/s]
- 68%|######8 | 90293/132723 [00:01<00:00, 76701.75KB/s]
- 74%|#######3 | 97997/132723 [00:01<00:00, 76800.41KB/s]
- 80%|#######9 | 105731/132723 [00:01<00:00, 76960.83KB/s]
- 85%|########5 | 113431/132723 [00:01<00:00, 76971.44KB/s]
- 91%|#########1| 121129/132723 [00:01<00:00, 76872.58KB/s]
- 97%|#########7| 128974/132723 [00:01<00:00, 77345.07KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 75944.35KB/s]
+ 4%|3 | 5039/132723 [00:00<00:02, 50386.32KB/s]
+ 10%|9 | 12768/132723 [00:00<00:01, 66207.40KB/s]
+ 15%|#5 | 20538/132723 [00:00<00:01, 71452.05KB/s]
+ 21%|##1 | 28460/132723 [00:00<00:01, 74517.28KB/s]
+ 27%|##7 | 36183/132723 [00:00<00:01, 75492.31KB/s]
+ 33%|###3 | 44018/132723 [00:00<00:01, 76461.85KB/s]
+ 39%|###9 | 52254/132723 [00:00<00:01, 78386.89KB/s]
+ 45%|####5 | 60309/132723 [00:00<00:00, 79072.98KB/s]
+ 51%|#####1 | 68304/132723 [00:00<00:00, 79345.03KB/s]
+ 58%|#####7 | 76320/132723 [00:01<00:00, 79593.70KB/s]
+ 64%|######3 | 84298/132723 [00:01<00:00, 79649.58KB/s]
+ 70%|######9 | 92338/132723 [00:01<00:00, 79875.03KB/s]
+ 76%|#######5 | 100338/132723 [00:01<00:00, 79907.20KB/s]
+ 82%|########1 | 108393/132723 [00:01<00:00, 80100.38KB/s]
+ 88%|########7 | 116431/132723 [00:01<00:00, 80177.88KB/s]
+ 94%|#########3| 124449/132723 [00:01<00:00, 80038.06KB/s]
+100%|#########9| 132701/132723 [00:01<00:00, 80782.10KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 77912.76KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -519,7 +519,7 @@ 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> ( 3 minutes 7.395 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> ( 3 minutes 5.177 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 f098497271..f6325d167d 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>13:42.282</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>13:26.413</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,43 +349,43 @@
</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>03:17.253</p></td>
+<td><p>03:11.875</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>03:07.395</p></td>
+<td><p>03:05.177</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>02:28.878</p></td>
+<td><p>02:23.152</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>01:22.062</p></td>
+<td><p>01:24.812</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>01:06.859</p></td>
+<td><p>01:05.747</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_adreno.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno.py</span></code>)</p></td>
-<td><p>00:53.523</p></td>
+<td><p>00:51.339</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:35.880</p></td>
+<td><p>00:35.164</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:25.446</p></td>
+<td><p>00:24.682</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:24.979</p></td>
+<td><p>00:24.459</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>
-<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/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 907cd2a754..b9bd399eb3 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -622,7 +622,7 @@ 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.zip0df57d2a-3121-4336-98e0-d7239a445491 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.zip6a6453e4-4e26-4bcd-8b47-bde16ddd6e0e 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 25fdefc4d3..030fab9b26 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:47.946</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:46.851</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</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>00:44.458</p></td>
+<td><p>00:43.425</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>00:02.443</p></td>
+<td><p>00:02.402</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>
-<td><p>00:01.038</p></td>
+<td><p>00:01.017</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.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 df3d7844b6..14751cceef 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -526,10 +526,10 @@ 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: 7289us [7289us] (46.47%; 46.47%)
-FoldScaleAxis: 8397us [7us] (53.53%; 53.53%)
- FoldConstant: 8389us [1725us] (53.49%; 99.91%)
- InferType: 6664us [6664us] (42.49%; 79.44%)
+InferType: 7110us [7110us] (46.21%; 46.21%)
+FoldScaleAxis: 8277us [6us] (53.79%; 53.79%)
+ FoldConstant: 8271us [1680us] (53.75%; 99.93%)
+ InferType: 6591us [6591us] (42.83%; 79.69%)
</pre></div>
</div>
</div>
@@ -551,10 +551,10 @@ 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: 6687us [6687us] (44.81%; 44.81%)
-FoldScaleAxis: 8235us [5us] (55.19%; 55.19%)
- FoldConstant: 8230us [1705us] (55.15%; 99.94%)
- InferType: 6525us [6525us] (43.73%; 79.29%)
+InferType: 6652us [6652us] (45.20%; 45.20%)
+FoldScaleAxis: 8065us [5us] (54.80%; 54.80%)
+ FoldConstant: 8060us [1656us] (54.77%; 99.94%)
+ InferType: 6404us [6404us] (43.52%; 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 624f7ba2eb..ad4219562a 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -578,7 +578,7 @@ 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: 54.204128 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 40.375934 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 debde1df3f..f7cb00094f 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -915,7 +915,7 @@ 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: 13.386995 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.351292 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 4b3887cb51..850106d3f2 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -475,8 +475,8 @@ 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: 0.019434
-Baseline: 3.455880
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018283
+Baseline: 3.461599
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -535,7 +535,7 @@ 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: 0.300253
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.301409
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -601,7 +601,7 @@ 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: 0.335396
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.329831
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -661,7 +661,7 @@ 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: 0.117203
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.115119
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -743,7 +743,7 @@ 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: 0.109657
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109342
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -828,7 +828,7 @@ 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: 0.111716
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.112251
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -917,7 +917,7 @@ 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: 0.147122
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147203
</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 f045d7952a..1797dec8d0 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:35.181</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.003</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +349,15 @@
</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>00:32.562</p></td>
+<td><p>00:32.361</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>00:01.521</p></td>
+<td><p>00:01.536</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>00:01.098</p></td>
+<td><p>00:01.106</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 d1a67c2ee6..a83ae0db80 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>09:28.786</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>08:55.689</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -349,27 +349,27 @@
</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>05:42.208</p></td>
+<td><p>05:32.273</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>01:32.179</p></td>
+<td><p>01:31.115</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>01:01.921</p></td>
+<td><p>01:01.790</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>00:49.065</p></td>
+<td><p>00:27.382</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:12.089</p></td>
+<td><p>00:12.079</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:11.324</p></td>
+<td><p>00:11.050</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 c37dc3b655..192c47edb9 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
@@ -504,183 +504,580 @@ cooperative fetching, unrolling and operator fusion.</p>
bias: Buffer(bias_2: Pointer(float32), float32, [1, 512, 1, 1], []),
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 128;
- allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [384]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
- conv2d_nchw_1[2] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 8;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [28]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [1008]), 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, [49], [], scope="local", align=16)[0] = 0f32
+ conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[14] = 0f32
+ conv2d_nchw_1[21] = 0f32
conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[15] = 0f32
+ conv2d_nchw_1[22] = 0f32
+ conv2d_nchw_1[2] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[16] = 0f32
+ conv2d_nchw_1[23] = 0f32
conv2d_nchw_1[3] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
- for (rx.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*1568)
- let cse_var_1: int32 = (rc.outer.outer*288)
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[17] = 0f32
+ conv2d_nchw_1[24] = 0f32
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[18] = 0f32
+ conv2d_nchw_1[25] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[19] = 0f32
+ conv2d_nchw_1[26] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ conv2d_nchw_1[20] = 0f32
+ conv2d_nchw_1[27] = 0f32
+ for (rc.outer.outer: int32, 0, 32) {
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_4: int32 = (rc.outer.outer*784)
+ let cse_var_3: int32 = (ry.outer.outer*7)
+ let cse_var_2: int32 = (rc.outer.outer*144)
+ let cse_var_1: int32 = (ry.outer.outer*3)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], 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_3: Buffer(data_2, float32, [25088], [])[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 49)] = @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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 49), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 98), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 147)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 147), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- 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_3[(((((cse_var_2 + (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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 245)] = @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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 245), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 294)] = @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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 294), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 343)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 343), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 441)] = @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_3[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 335)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 490)] = @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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 490), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 539)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 539), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 588), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 637)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 637), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 686)] = @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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 686), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 735)] = @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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 735), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 833)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 833), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 882)] = @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_3[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 678)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 931)] = @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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 931), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 980), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1029)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1029), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1078)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1078), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1127)] = @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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1127), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- 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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1225)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1225), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1274)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1274), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1323)] = @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_3[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 1021)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- 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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1372), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1421)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1421), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1470)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1470), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1519)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1519), 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" = 49;
- 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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1568), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1617)] = @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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1617), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1666)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1666), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1715)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1715), 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" = 49;
- 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_3[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 1364)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1813)] = @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_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1813), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1862)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1862), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1911)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1911), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- 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_3[(((((cse_var_2 + (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" = 49;
- if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 2009)] = 0f32
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1: Buffer(kernel.shared, float32, [384], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((blockIdx.x*18432) + cse_var_1) + (threadIdx.x_2*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 49)] = kernel_3[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 49), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 49), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 98), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 2), 96)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 147)] = kernel_3[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 147), 96)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 17), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel_3[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 196), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 245)] = kernel_3[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 245), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 53), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 294)] = kernel_3[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 294), 96)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 2)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_2 < 41), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 343)] = kernel_3[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 343), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 55), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1008], [], 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_3: Buffer(data_2, float32, [25088], [])[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) [...]
+ 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_3[((((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_3[((((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_3[((((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_3[((((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_3[((((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_3[((((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_3[((((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_3[((((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_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 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_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 112), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 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_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 224), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 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_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 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 + 448)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 448), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 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_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 560), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 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_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 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 + 784)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 784), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 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_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 896), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 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_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 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 + 1120)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1120), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 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_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1232), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 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_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 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 + 1456)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1456), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 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_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1568), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 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_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 161280)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1792), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 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_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1904), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 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_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 193536)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2128), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 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_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2240), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 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_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 225792)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2464), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 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_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2576), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 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_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2800), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 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_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2912), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 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_3[((((((blockIdx.x*294912) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 290304)]
}
- for (rc.outer.inner: int32, 0, 8) {
- let cse_var_3: int32 = (rc.outer.inner*12)
- {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*252) + threadIdx.x)]*kernel.shared_1[cse_var_3]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rc.outer.inner*252) + threadIdx.x)]*kernel.shared_1[(cse_var_3 + 192)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rc.outer.inner*252) + threadIdx.x)]*kernel.shared_1[(cse_var_3 + 96)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rc.outer.inner*252) + threadIdx.x)]*kernel.shared_1[(cse_var_3 + 288)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_3 + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_3 + 195)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_3 + 99)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_3 + 291)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_3 + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_3 + 198)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_3 + 102)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_3 + 294)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_3 + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_3 + 201)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_3 + 105)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_3 + 297)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_3 + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_3 + 193)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_3 + 97)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_3 + 289)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_3 + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_3 + 196)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_3 + 100)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_3 + 292)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_3 + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_3 + 199)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_3 + 103)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_3 + 295)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_3 + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_3 + 202)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_3 + 106)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_3 + 298)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_3 + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_3 + 194)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_3 + 98)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_3 + 290)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_3 + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_3 + 197)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_3 + 101)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_3 + 293)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_3 + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_3 + 200)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_3 + 104)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_3 + 296)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_3 + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_3 + 203)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_3 + 107)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_3 + 299)]))
- }
+ for (rx.outer.inner: int32, 0, 3) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(rx.outer.inner + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + rx.outer.inner)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(rx.outer.inner + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 768)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(rx.outer.inner + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1536)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(rx.outer.inner + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2304)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 771)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1539)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2307)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 6)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 774)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1542)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2310)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 777)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1545)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2313)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 12)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 780)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1548)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2316)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 783)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1551)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2319)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 786)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1554)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2322)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 789)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1557)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2325)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 792)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1560)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2328)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 795)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1563)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2331)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 798)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1566)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2334)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 33)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 801)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1569)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2337)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 804)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1572)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2340)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 39)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 807)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1575)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2343)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 810)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1578)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2346)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 813)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1581)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2349)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + rx.outer.inner)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 768)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1536)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2304)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 3)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 771)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1539)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2307)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 6)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 774)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1542)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2310)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 777)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1545)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2313)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 12)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 780)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1548)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2316)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 15)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 783)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1551)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2319)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 387)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 387)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 786)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 387)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1554)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 387)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2322)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 21)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 789)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1557)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2325)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 513)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 513)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 792)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 513)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1560)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 513)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2328)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 795)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1563)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2331)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 639)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 639)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 798)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 639)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1566)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 639)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2334)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 702)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 702)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 801)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 702)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1569)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 702)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2337)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 765)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 765)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 804)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 765)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1572)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 765)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2340)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 807)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1575)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2343)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 810)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1578)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2346)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 954)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 954)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 813)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 954)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1581)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 954)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2349)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + rx.outer.inner)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 768)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1536)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2304)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 3)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 771)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1539)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2307)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 6)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 774)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1542)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2310)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 777)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1545)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2313)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 12)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 780)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1548)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2316)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 15)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 783)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1551)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2319)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 396)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 396)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 786)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 396)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1554)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 396)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2322)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 21)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 789)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1557)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2325)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 522)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 522)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 792)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 522)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1560)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 522)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2328)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 795)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1563)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2331)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 798)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1566)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2334)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 711)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 711)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 801)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 711)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1569)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 711)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2337)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 774)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 774)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 804)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 774)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1572)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 774)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2340)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 837)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 837)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 807)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 837)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1575)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 837)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2343)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 810)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1578)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2346)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 963)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 963)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 813)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 963)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1581)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 963)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2349)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + rx.outer.inner)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 768)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1536)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2304)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 3)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 771)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1539)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2307)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 6)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 774)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1542)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2310)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 777)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1545)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2313)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 12)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 780)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1548)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2316)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 15)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 783)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1551)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2319)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 786)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1554)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2322)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 468)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 21)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 468)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 789)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 468)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1557)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 468)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2325)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 531)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 531)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 792)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 531)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1560)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 531)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2328)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 594)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 594)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 795)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 594)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1563)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 594)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2331)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 798)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1566)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2334)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 720)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 720)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 801)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 720)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1569)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 720)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2337)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 783)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 783)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 804)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 783)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1572)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 783)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2340)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 846)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 846)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 807)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 846)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1575)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 846)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2343)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 810)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1578)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2346)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 813)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1581)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2349)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + rx.outer.inner)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 768)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1536)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2304)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 3)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 771)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1539)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2307)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 6)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 774)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1542)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2310)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 777)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1545)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2313)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 12)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 780)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1548)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2316)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 15)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 783)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1551)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2319)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 786)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1554)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2322)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 477)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 21)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 477)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 789)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 477)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1557)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 477)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2325)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 540)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 540)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 792)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 540)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1560)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 540)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2328)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 603)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 603)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 795)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 603)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1563)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 603)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2331)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 798)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1566)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2334)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 801)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1569)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2337)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 792)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 792)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 804)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 792)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1572)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 792)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2340)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 855)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 855)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 807)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 855)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1575)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 855)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2343)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 918)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 918)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 810)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 918)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1578)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 918)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2346)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 813)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1581)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2349)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + rx.outer.inner)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 768)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1536)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2304)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 3)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 771)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1539)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2307)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 6)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 774)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1542)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2310)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 777)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1545)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2313)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 12)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 780)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1548)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2316)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 15)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 783)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1551)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2319)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 786)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1554)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2322)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 21)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 789)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1557)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2325)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 549)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 549)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 792)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 549)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1560)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 549)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2328)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 612)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 612)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 795)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 612)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1563)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 612)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2331)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 675)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 675)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 798)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 675)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1566)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 675)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2334)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 801)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1569)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2337)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 801)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 801)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 804)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 801)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1572)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 801)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2340)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 864)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 864)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 807)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 864)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1575)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 864)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2343)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 927)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 927)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 810)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 927)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1578)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 927)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2346)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 813)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1581)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2349)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + rx.outer.inner)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 768)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1536)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2304)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 3)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 771)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1539)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2307)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 6)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 774)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1542)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2310)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 777)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1545)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2313)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 12)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 780)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1548)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2316)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 15)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 783)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1551)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2319)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 786)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1554)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2322)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 21)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 789)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1557)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2325)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 558)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 558)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 792)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 558)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1560)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 558)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2328)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 621)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 621)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 795)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 621)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1563)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 621)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2331)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 684)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 684)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 798)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 684)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1566)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 684)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2334)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 801)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1569)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2337)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 804)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1572)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2340)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 873)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 873)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 807)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 873)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1575)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 873)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2343)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 936)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 936)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 810)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 936)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1578)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 936)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2346)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 999)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 999)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 813)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 999)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 1581)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 999)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + rx.outer.inner) + 2349)]))
}
}
}
}
- for (i1.inner: int32, 0, 2) {
- compute_3: Buffer(compute_2, float32, [25088], [])[(((blockIdx.x*196) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*4) + i1.inner)]), 0f32)
- compute_3[((((blockIdx.x*196) + (i1.inner*49)) + threadIdx.x) + 98)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias_3[(((blockIdx.x*4) + i1.inner) + 2)]), 0f32)
+ for (i2.inner: int32, 0, 7) {
+ compute_3: Buffer(compute_2, float32, [25088], [])[((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*64) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute_3[(((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7)) + 784)] = max((conv2d_nchw_1[(i2.inner + 7)] + bias_3[(((blockIdx.x*64) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
+ compute_3[(((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7)) + 1568)] = max((conv2d_nchw_1[(i2.inner + 14)] + bias_3[(((blockIdx.x*64) + floordiv(threadIdx.x, 7)) + 32)]), 0f32)
+ compute_3[(((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7)) + 2352)] = max((conv2d_nchw_1[(i2.inner + 21)] + bias_3[(((blockIdx.x*64) + floordiv(threadIdx.x, 7)) + 48)]), 0f32)
}
}
}
@@ -717,7 +1114,7 @@ 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: 0.244 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.415 ms
</pre></div>
</div>
</div>
@@ -746,33 +1143,33 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
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=2)
+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=1)
-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=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=4)
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=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=4)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
+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=1)
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=3)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
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=1)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
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=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
-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_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=4)
+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=7)
@@ -795,14 +1192,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
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)
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=49)
+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)
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=49)
+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)
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:
@@ -820,127 +1217,538 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[4];
- __shared__ float pad_temp_shared[2016];
- __shared__ float kernel_shared[384];
+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[28];
+ __shared__ float pad_temp_shared[1008];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[14] = 0.000000e+00f;
+ conv2d_nchw[21] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[15] = 0.000000e+00f;
+ conv2d_nchw[22] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[16] = 0.000000e+00f;
+ conv2d_nchw[23] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
- for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[17] = 0.000000e+00f;
+ conv2d_nchw[24] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[18] = 0.000000e+00f;
+ conv2d_nchw[25] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[19] = 0.000000e+00f;
+ conv2d_nchw[26] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ conv2d_nchw[20] = 0.000000e+00f;
+ conv2d_nchw[27] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
__syncthreads();
- 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 * 1568) + ((int)threadIdx.x)) + rx_outer_outer) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((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 * 1568) + (((((int)threadIdx.x) + 49) / 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) + 98)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 98) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 147) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 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 * 1568) + (((((int)threadIdx.x) + 196) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 245)] = (((((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 * 1568) + (((((int)threadIdx.x) + 245) / 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) + 294)] = (((((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 * 1568) + (((((int)threadIdx.x) + 294) / 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) + 343)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 343) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 441)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 1568) + ((int)threadIdx.x)) + rx_outer_outer) + 335)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 490)] = (((((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 * 1568) + (((((int)threadIdx.x) + 490) / 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) + 539)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 539) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 588) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 637)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 637) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((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 * 1568) + (((((int)threadIdx.x) + 686) / 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) + 735)] = (((((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 * 1568) + (((((int)threadIdx.x) + 735) / 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) + 784)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 833)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 833) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 882)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 1568) + ((int)threadIdx.x)) + rx_outer_outer) + 678)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 931)] = (((((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 * 1568) + (((((int)threadIdx.x) + 931) / 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) + 980)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 980) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1029)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1029) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1078)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1078) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1127)] = (((((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 * 1568) + (((((int)threadIdx.x) + 1127) / 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) + 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 * 1568) + (((((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) + 1225)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1225) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1274)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1274) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1323)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 1568) + ((int)threadIdx.x)) + rx_outer_outer) + 1021)] : 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 * 1568) + (((((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) + 1421)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1421) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1470)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1470) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1519)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1519) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 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 * 1568) + (((((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) + 1617)] = (((((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 * 1568) + (((((int)threadIdx.x) + 1617) / 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) + 1666)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1666) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1715)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1715) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 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 * 1568) + ((int)threadIdx.x)) + rx_outer_outer) + 1364)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1813)] = (((((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 * 1568) + (((((int)threadIdx.x) + 1813) / 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) + 1862)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1862) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1911)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1911) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 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 * 1568) + (((((int)threadIdx.x) + 1960) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 7) {
- pad_temp_shared[(((int)threadIdx.x) + 2009)] = 0.000000e+00f;
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 49) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 49) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 98) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) + 2) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 147)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 147) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 17) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 196) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 4) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 245)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 245) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 53) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 294) / 96) * 4608)) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 18)];
- if (((int)threadIdx.x) < 41) {
- kernel_shared[(((int)threadIdx.x) + 343)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 343) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 55) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ 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 * 784) + ((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((int)threadIdx.x) + 896) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 448) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 560) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 784) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 896) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1120) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1232) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1456) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1568) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 161280)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1792) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1904) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 193536)];
+ kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2128) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2240) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 225792)];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2464) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2576) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2800) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2912) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 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) * 294912) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 290304)];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[(rc_outer_inner * 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 192)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 96)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 288)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 195)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 99)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 291)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 198)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 102)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 294)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 201)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 105)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 297)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 193)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 97)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 289)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 196)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 100)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 292)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 199)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 103)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 295)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 202)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 106)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 298)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 194)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 98)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 290)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 197)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 101)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 293)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 200)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 104)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 296)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 203)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 107)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 299)]));
+ for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + rx_outer_inner)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 768)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1536)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2304)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 771)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1539)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2307)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 6)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 774)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1542)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2310)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 777)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1545)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2313)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 12)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 780)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1548)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2316)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 783)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1551)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2319)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 18)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 786)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1554)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2322)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 789)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1557)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2325)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 792)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1560)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2328)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 27)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 795)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1563)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2331)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 798)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1566)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2334)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 33)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 801)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1569)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2337)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 804)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1572)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2340)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 39)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 807)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1575)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2343)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 810)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1578)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2346)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 45)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 813)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1581)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2349)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + rx_outer_inner)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 768)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1536)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2304)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 3)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 771)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1539)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2307)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 6)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 774)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1542)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2310)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 777)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1545)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2313)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 12)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 780)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1548)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2316)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 15)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 783)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1551)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2319)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 18)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 786)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1554)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2322)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 21)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 789)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1557)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2325)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 792)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1560)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2328)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 795)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1563)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2331)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 639)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 639)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 798)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 639)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1566)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 639)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2334)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 702)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 702)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 801)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 702)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1569)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 702)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2337)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 765)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 765)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 804)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 765)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1572)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 765)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2340)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 807)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1575)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2343)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 810)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1578)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2346)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 954)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 954)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 813)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 954)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1581)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 954)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2349)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + rx_outer_inner)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 768)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1536)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2304)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 3)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 771)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1539)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2307)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 6)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 774)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1542)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2310)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 9)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 777)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1545)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2313)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 12)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 780)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1548)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2316)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 15)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 783)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1551)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2319)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 18)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 786)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1554)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2322)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 21)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 789)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1557)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2325)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 792)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1560)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2328)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 795)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1563)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2331)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 798)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1566)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2334)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 711)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 711)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 801)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 711)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1569)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 711)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2337)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 774)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 774)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 804)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 774)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1572)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 774)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2340)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 837)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 837)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 807)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 837)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1575)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 837)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2343)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 810)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1578)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2346)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 963)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 963)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 813)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 963)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1581)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 963)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2349)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + rx_outer_inner)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 768)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1536)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2304)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 3)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 771)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1539)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2307)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 6)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 774)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1542)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2310)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 9)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 777)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1545)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2313)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 12)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 780)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1548)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2316)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 15)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 783)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1551)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2319)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 18)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 786)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1554)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2322)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 21)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 789)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1557)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2325)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 792)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1560)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2328)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 795)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1563)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2331)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 798)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1566)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2334)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 720)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 720)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 801)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 720)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1569)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 720)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2337)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 783)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 783)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 804)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 783)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1572)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 783)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2340)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 846)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 846)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 807)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 846)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1575)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 846)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2343)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 810)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1578)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2346)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 813)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1581)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2349)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + rx_outer_inner)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 768)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1536)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2304)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 3)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 771)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1539)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2307)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 6)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 774)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1542)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2310)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 9)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 777)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1545)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2313)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 12)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 780)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1548)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2316)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 15)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 783)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1551)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2319)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 18)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 786)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1554)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2322)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 21)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 789)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1557)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2325)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 792)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1560)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2328)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 795)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1563)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2331)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 798)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1566)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2334)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 801)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1569)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2337)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 792)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 792)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 804)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 792)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1572)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 792)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2340)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 855)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 855)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 807)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 855)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1575)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 855)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2343)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 918)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 918)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 810)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 918)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1578)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 918)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2346)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 813)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1581)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2349)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + rx_outer_inner)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 768)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1536)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2304)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 3)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 771)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1539)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2307)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 6)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 774)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1542)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2310)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 777)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1545)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2313)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 12)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 780)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1548)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2316)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 15)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 783)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1551)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2319)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 18)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 786)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1554)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2322)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 21)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 789)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1557)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2325)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 549)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 549)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 792)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 549)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1560)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 549)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2328)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 795)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1563)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2331)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 675)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 675)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 798)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 675)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1566)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 675)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2334)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 801)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1569)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2337)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 801)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 801)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 804)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 801)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1572)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 801)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2340)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 864)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 864)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 807)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 864)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1575)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 864)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2343)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 927)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 927)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 810)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 927)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1578)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 927)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2346)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 813)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1581)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2349)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + rx_outer_inner)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 768)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1536)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2304)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 3)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 771)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1539)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2307)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 6)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 774)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1542)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2310)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 9)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 777)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1545)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2313)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 12)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 780)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1548)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2316)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 15)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 783)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1551)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2319)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 18)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 786)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1554)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2322)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 21)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 789)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1557)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2325)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 558)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 558)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 792)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 558)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1560)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 558)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2328)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 795)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1563)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2331)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 684)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 684)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 798)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 684)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1566)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 684)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2334)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 801)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1569)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2337)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 804)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1572)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2340)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 873)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 873)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 807)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 873)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1575)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 873)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2343)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 936)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 936)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 810)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 936)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1578)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 936)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2346)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 999)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 999)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 813)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 999)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 1581)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 999)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + rx_outer_inner) + 2349)]));
}
}
}
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[(((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 4) + i1_inner)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x)) + 98)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 4) + i1_inner) + 2)]), 0.000000e+00f);
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 64) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 784)] = max((conv2d_nchw[(i2_inner + 7)] + bias[(((((int)blockIdx.x) * 64) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 1568)] = max((conv2d_nchw[(i2_inner + 14)] + bias[(((((int)blockIdx.x) * 64) + (((int)threadIdx.x) / 7)) + 32)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 2352)] = max((conv2d_nchw[(i2_inner + 21)] + bias[(((((int)blockIdx.x) * 64) + (((int)threadIdx.x) / 7)) + 48)]), 0.000000e+00f);
}
}
</pre></div>
@@ -977,7 +1785,7 @@ 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> ( 5 minutes 42.208 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 32.273 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 8af7f03e1b..fbe7fe3d38 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -916,7 +916,7 @@ 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)
- 7.8874 7.8938 7.8943 7.8741 0.0094
+ 7.8737 7.8755 7.8770 7.8685 0.0037
</pre></div>
</div>
</div>
@@ -938,7 +938,7 @@ 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 1.921 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.790 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/eafe360d52540634c9eea0fa89e804bd/tune_network_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_network_cuda.py</span></code></a></p>
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 620b5a04b8..105ce999bf 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -935,7 +935,7 @@ 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)
- 749.6636 749.6433 749.9993 749.3483 0.2661
+ 753.1270 753.0658 753.7329 752.5821 0.4718
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ 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 32.179 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 31.115 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 f80119c3bd..3622aaed35 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -633,28 +633,28 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [1024]), storage_scope = global {
- for (i.outer.inner: int32, 0, 16) {
+ for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 4) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 16) {
for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [1024], [])[((((i.outer.inner*64) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
+ compute_4: Buffer(compute_3, float32, [2048], [])[((((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
}
}
for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
- for (i.inner: int32, 0, 2) {
+ for (i.inner: int32, 0, 16) {
for (j: int32, 0, 16) {
let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_2: int32 = ((((i.outer.inner*64) + (i.inner*32)) + (nb_j.inner*16)) + j)
- compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.outer.inner*512)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ let cse_var_2: int32 = ((((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16)) + j)
+ compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ for (i0.inner: int32, 0, 64) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_4, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
}
}
@@ -693,7 +693,7 @@ 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: 2.130 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.504 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 ee8a7ad035..47c53597b4 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:33.178</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:40.880</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,18 +349,18 @@
</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>00:33.143</p></td>
+<td><p>00:40.845</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>00:00.020</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><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>
+<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>0.0 MB</p></td>
</tr>
-<tr class="row-even"><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>
+<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>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
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 5c083a8dd7..2d8c4a3b63 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -568,7 +568,8 @@ 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: 115.61/115.61 result: MeasureResult(costs=(0.0020025195660377357,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.174020767211914, timestamp=1673240573.1018007) [('tile_f', [-1, 8, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7651630
+No: 2 GFLOPS: 0.00/115.61 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -690,8 +691,8 @@ 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 875, 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, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2218954
-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, 32, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1275857
+No: 3 GFLOPS: 0.00/115.61 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -813,8 +814,8 @@ 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 875, 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, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4094784
-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, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2768102
+No: 4 GFLOPS: 0.00/115.61 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -936,8 +937,8 @@ 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 875, 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, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2373231
-No: 4 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, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9359252
+No: 5 GFLOPS: 0.00/115.61 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1059,8 +1060,8 @@ 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 875, 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, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6703601
-No: 5 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, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2021690
+No: 6 GFLOPS: 0.00/115.61 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1182,8 +1183,8 @@ 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 875, 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, 128, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754811
-No: 6 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, 2, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6672351
+No: 7 GFLOPS: 0.00/115.61 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1305,10 +1306,8 @@ 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 875, 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, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2688852
-No: 7 GFLOPS: 81.13/81.13 result: MeasureResult(costs=(0.002853425575,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.593247652053833, timestamp=1673207944.3081067) [('tile_f', [-1, 1, 64, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3494833
-No: 8 GFLOPS: 565.24/565.24 result: MeasureResult(costs=(0.00040955998465473144,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5637280941009521, timestamp=1673207945.3138244) [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5081626
-No: 9 GFLOPS: 0.00/565.24 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8191521
+No: 8 GFLOPS: 0.00/115.61 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1430,8 +1429,9 @@ 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 875, 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, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8284183
-No: 10 GFLOPS: 0.00/565.24 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2544456
+No: 9 GFLOPS: 1.67/115.61 result: MeasureResult(costs=(0.13828141775,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8109846115112305, timestamp=1673240579.1649926) [('tile_f', [-1, 1, 2, 128]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6455893
+No: 10 GFLOPS: 0.00/115.61 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1553,10 +1553,8 @@ 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 875, 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, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2580423
-No: 11 GFLOPS: 6.14/565.24 result: MeasureResult(costs=(0.03770536025,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2243459224700928, timestamp=1673207948.3442025) [('tile_f', [-1, 64, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2331153
-No: 12 GFLOPS: 212.14/565.24 result: MeasureResult(costs=(0.0010912774489795919,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7804789543151855, timestamp=1673207949.3513148) [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7053461
-No: 13 GFLOPS: 0.00/565.24 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7923929
+No: 11 GFLOPS: 0.00/115.61 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1678,8 +1676,8 @@ 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 875, 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, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3857813
-No: 14 GFLOPS: 0.00/565.24 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 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,519531
+No: 12 GFLOPS: 0.00/115.61 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1801,161 +1799,133 @@ 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 875, 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, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7109464
-No: 15 GFLOPS: 0.00/565.24 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
- blob = feval(*args)
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9868970
+No: 13 GFLOPS: 124.87/124.87 result: MeasureResult(costs=(0.0018539882985074627,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2893645763397217, timestamp=1673240581.8125648) [('tile_f', [-1, 4, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,38322
+No: 14 GFLOPS: 0.00/124.87 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, 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 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/./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):
- 4: TVMFuncCall
+ 24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ 23: 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:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
-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 706, 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 746, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 144, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 72, 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: 0x00007f9e4d319fa2
- 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:185
- 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:1007
- 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:223
- 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
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 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:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:395
+ 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:381
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:276
+ 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:454
+ 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:1749
+ 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:1693
+ 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:1617
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:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
-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
+ 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 875, 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):
- 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, 32, 1, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5456389
-No: 16 GFLOPS: 0.00/565.24 result: 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:1730
+ 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:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:395
+ 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:381
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:276
+ 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:454
+ 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:1749
+ 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:1693
+ 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:1617
+ 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 875, 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, 32, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1607482
+No: 15 GFLOPS: 0.95/124.87 result: MeasureResult(costs=(0.24270285025000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.071226596832275, timestamp=1673240585.3610103) [('tile_f', [-1, 1, 1, 32]), ('tile_y', [-1, 7, 1, 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,9732325
+No: 16 GFLOPS: 0.00/124.87 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2077,8 +2047,8 @@ 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 875, 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, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6723322
-No: 17 GFLOPS: 0.00/565.24 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7162256
+No: 17 GFLOPS: 0.00/124.87 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2200,8 +2170,26 @@ 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 875, 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, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3441340
-No: 18 GFLOPS: 0.00/565.24 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1721740
+No: 18 GFLOPS: 0.00/124.87 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 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+TimeoutError
+
+ [('tile_f', [-1, 8, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('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', 512), ('unroll_explicit', 1)],None,7403718
+No: 19 GFLOPS: 0.00/124.87 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2323,8 +2311,8 @@ 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 875, 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, 64, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,982788
-No: 19 GFLOPS: 0.00/565.24 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10192803
+No: 20 GFLOPS: 0.00/124.87 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2446,8 +2434,7 @@ 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 875, 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, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2930145
-No: 20 GFLOPS: 5.25/565.24 result: MeasureResult(costs=(0.044077056749999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.035950183868408, timestamp=1673207957.5529802) [('tile_f', [-1, 1, 2, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5326610
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8559880
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2486,9 +2473,9 @@ 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, 4, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5081626
+[('tile_f', [-1, 4, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,38322
Finish loading 20 records
-Time cost of this operator: 0.000721
+Time cost of this operator: 0.001924
</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 a5a4b3e92c..f271a31b0e 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -663,10 +663,10 @@ 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 310.6 98.715 (1, 2, 10, 10, 3) 2 1 [310.6]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.076 0.978 (1, 6, 10, 10) 1 1 [3.076]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.308 (1, 1, 10, 10, 3) 1 1 [0.969]
-Total_time - 314.644 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.3 98.702 (1, 2, 10, 10, 3) 2 1 [311.3]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.134 0.994 (1, 6, 10, 10) 1 1 [3.134]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.96 0.305 (1, 1, 10, 10, 3) 1 1 [0.96]
+Total_time - 315.395 - - - - -
</pre></div>
</div>
</div>
@@ -718,10 +718,10 @@ 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 105.1 97.451 (1, 6, 10, 10, 1) 2 1 [105.1]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.787 1.657 (1, 6, 10, 10) 1 1 [1.787]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.963 0.893 (1, 1, 10, 10, 3) 1 1 [0.963]
-Total_time - 107.849 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 134.1 97.943 (1, 6, 10, 10, 1) 2 1 [134.1]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.856 1.356 (1, 6, 10, 10) 1 1 [1.856]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.96 0.701 (1, 1, 10, 10, 3) 1 1 [0.96]
+Total_time - 136.916 - - - - -
</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_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index c1355196c5..4cbbabd44b 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -453,7 +453,7 @@ download a cat image and preprocess it to use as the model input.</p>
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
0%| | 0.00/3.42M [00:00<?, ?B/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 114MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 36.3MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -577,7 +577,7 @@ via the host <cite>main.cc`</cite> or if a Zephyr emulated board is selected as
Torch top-1 id: 282, class name: tiger cat
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.488 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.762 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/12b9ecc04c41abaa12022061771821d1/micro_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">micro_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index de730ff120..c365763144 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -523,7 +523,7 @@ 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/tmpd4y05yt_/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp350nmquk/images/random'
</pre></div>
</div>
</div>
@@ -583,8 +583,8 @@ 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="[0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpd4y05yt_/images/target contains 8144 images
-/tmp/tmpd4y05yt_/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], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp350nmquk/images/target contains 8144 images
+/tmp/tmp350nmquk/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -696,13 +696,13 @@ 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: 0.1971 - accuracy: 0.9311 - val_loss: 0.2416 - val_accuracy: 0.9139 - 47s/epoch - 143ms/step
+328/328 - 47s - loss: 0.2178 - accuracy: 0.9226 - val_loss: 0.2906 - val_accuracy: 0.9048 - 47s/epoch - 143ms/step
Epoch 2/3
-328/328 - 44s - loss: 0.0919 - accuracy: 0.9670 - val_loss: 0.1066 - val_accuracy: 0.9698 - 44s/epoch - 133ms/step
+328/328 - 43s - loss: 0.0973 - accuracy: 0.9636 - val_loss: 0.1064 - val_accuracy: 0.9634 - 43s/epoch - 132ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0586 - accuracy: 0.9781 - val_loss: 0.1025 - val_accuracy: 0.9690 - 43s/epoch - 133ms/step
+328/328 - 43s - loss: 0.0753 - accuracy: 0.9725 - val_loss: 0.0871 - val_accuracy: 0.9687 - 43s/epoch - 131ms/step
-<keras.callbacks.History object at 0x7f2f09e55910>
+<keras.callbacks.History object at 0x7f5cfce22e10>
</pre></div>
</div>
</div>
@@ -962,7 +962,7 @@ 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 17.521 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 24.563 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 c17391829a..b190f92d6f 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>06:25.983</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:29.692</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,23 +349,23 @@
</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>04:17.521</p></td>
+<td><p>04:24.563</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:04.488</p></td>
+<td><p>01:02.762</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:52.163</p></td>
+<td><p>00:50.810</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:07.974</p></td>
+<td><p>00:07.775</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:03.834</p></td>
+<td><p>00:03.780</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.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 50a3178b47..ec100a1fb1 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:44.747</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:44.343</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</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>00:32.865</p></td>
+<td><p>00:32.213</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>00:10.206</p></td>
+<td><p>00:10.526</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>00:01.669</p></td>
+<td><p>00:01.597</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>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index a5c2b7ac24..a2c3131983 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -536,7 +536,7 @@ 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 0x7f2f0a77d8c0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f5d861fbdd0>
</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 29f9da9687..5038291c2b 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:07.699</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:07.257</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,27 +349,27 @@
</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>00:05.211</p></td>
+<td><p>00:04.749</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>00:01.120</p></td>
+<td><p>00:01.154</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>00:00.581</p></td>
+<td><p>00:00.577</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>00:00.569</p></td>
+<td><p>00:00.561</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>00:00.116</p></td>
+<td><p>00:00.114</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>
-<td><p>00:00.050</p></td>
+<td><p>00:00.049</p></td>
<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>
@@ -377,7 +377,7 @@
<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>00:00.024</p></td>
+<td><p>00:00.023</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 ac240b84d6..dab9b6ab80 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -587,7 +587,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp1re09rxh/input0.cc'\nsource_filename = \"/tmp/tmp1re09rxh/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/tmpfe44yf11/input0.cc'\nsource_filename = \"/tmp/tmpfe44yf11/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 1ef28de467..23d2181e9d 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -229,7 +229,17 @@
<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"><a class="reference internal" href="from_source.html">Install from Source</a></li>
+<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="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 3bc0016a03..f947d3cdde 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1615,7 +1615,7 @@ 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>
@@ -1899,7 +1899,7 @@ 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 0bf9609c31..dbd2317230 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/a99f0c154/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 b964d3df75..809d47c0d5 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/a99f0c154/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 73373656b5..5bd5ddb51f 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/a99f0c154/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 7ee4a3277f..0d37eb6a1d 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/a99f0c154/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 94ba3b5c4e..f07975587d 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/a99f0c154/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 0664c40649..f402d6407d 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/a99f0c154/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 69248bc92b..040c8fe68f 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/a99f0c154/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 236620389c..cc67394f11 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/a99f0c154/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 768cfbb8b1..f711056ad3 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/a99f0c154/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 a579f1f9cb..66b894604f 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/a99f0c154/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 bc640cbba8..6dd73f7ab9 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/a99f0c154/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 d53d8dc925..a7b5bb5ec5 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/a99f0c154/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 0aecd2a5ad..5644dd392e 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/a99f0c154/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 7b130e0521..c98c11941c 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/a99f0c154/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 b209eee915..3477f1dfdf 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/a99f0c154/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 147b2dd203..ec8c00b41d 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/a99f0c154/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 da991f42b0..2a38702752 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/a99f0c154/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 6e079d49aa..32948fffd6 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/a99f0c154/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 419b95f49c..6074c4c15b 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/a99f0c154/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 fc44c6aa5f..1553e7fe81 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/a99f0c154/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 d18419a52c..7b6cc4ad35 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/a99f0c154/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 61099bfcc6..9df34da4c8 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/a99f0c154/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 1bad68f39a..93d66cb526 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/a99f0c154/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 8fb760c12f..da37aab14d 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/a99f0c154/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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/a99f0c154/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a435cbb3b/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 1218eaafda..964f11ead0 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 7ea8acfbce..8810834520 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:26.490</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:25.973</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,7 +349,7 @@
</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>00:26.484</p></td>
+<td><p>00:25.966</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>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 981462a92f..d32e9bd4c9 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -583,7 +583,7 @@ 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 29.20s!
+resnet18_v1 inference graph built in 28.36s!
</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 de8f2019d0..0a7982387c 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -601,7 +601,7 @@ 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 19.78s!
+yolov3-tiny inference graph built in 19.34s!
</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 cb07316056..7b59827c5b 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>01:32.432</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:31.283</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</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>00:46.372</p></td>
+<td><p>00:46.068</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>00:46.060</p></td>
+<td><p>00:45.214</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 e404aba46f..8d767c8799 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:03.193</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.129</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</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>00:02.729</p></td>
+<td><p>00:02.673</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>00:00.464</p></td>
+<td><p>00:00.456</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 03c72b9ec8..390a2e9f5b 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -349,11 +349,11 @@
</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>00:00.442</p></td>
+<td><p>00:00.448</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>00:00.382</p></td>
+<td><p>00:00.376</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 5110c02bd3..0b575201b0 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -578,7 +578,7 @@ 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: 93.969 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 97.153 ms
</pre></div>
</div>
</div>
@@ -652,7 +652,7 @@ 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 7.591 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.747 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 a3e5c248b3..79c5ccbdc9 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -680,16 +680,16 @@ 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: 9.62/9.62 result: MeasureResult(costs=(0.027898718,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6814179420471191, timestamp=1673206541.7217193) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 3.31/9.62 result: MeasureResult(costs=(0.081053556,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5457041263580322, timestamp=1673206543.2708719) [('tile_y', [-1, 64]), ('tile_x', [-1, 8])],None,36
-No: 3 GFLOPS: 1.81/9.62 result: MeasureResult(costs=(0.1486419228,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6199307441711426, timestamp=1673206546.717056) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 4 GFLOPS: 11.74/11.74 result: MeasureResult(costs=(0.0228617026,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5938427448272705, timestamp=1673206547.3465004) [('tile_y', [-1, 256]), ('tile_x', [-1, 512])],None,98
-No: 5 GFLOPS: 1.86/11.74 result: MeasureResult(costs=(0.144347768,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5399982929229736, timestamp=1673206550.092905) [('tile_y', [-1, 512]), ('tile_x', [-1, 8])],None,39
-No: 6 GFLOPS: 2.71/11.74 result: MeasureResult(costs=(0.0989268586,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8124949932098389, timestamp=1673206552.6885347) [('tile_y', [-1, 2]), ('tile_x', [-1, 8])],None,31
-No: 7 GFLOPS: 12.73/12.73 result: MeasureResult(costs=(0.021078582399999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5693621635437012, timestamp=1673206554.0728147) [('tile_y', [-1, 32]), ('tile_x', [-1, 512])],None,95
-No: 8 GFLOPS: 12.68/12.73 result: MeasureResult(costs=(0.021176568200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.652878999710083, timestamp=1673206554.6630762) [('tile_y', [-1, 1]), ('tile_x', [-1, 64])],None,60
-No: 9 GFLOPS: 12.24/12.73 result: MeasureResult(costs=(0.0219353664,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5713191032409668, timestamp=1673206555.346897) [('tile_y', [-1, 8]), ('tile_x', [-1, 256])],None,83
-No: 10 GFLOPS: 1.75/12.73 result: MeasureResult(costs=(0.15359519800000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6658265590667725, timestamp=1673206558.0598083) [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
+No: 1 GFLOPS: 0.50/0.50 result: MeasureResult(costs=(0.5390616124000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.850629091262817, timestamp=1673239170.5277846) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
+No: 2 GFLOPS: 9.12/9.12 result: MeasureResult(costs=(0.029428969399999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7751691341400146, timestamp=1673239172.0044737) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
+No: 3 GFLOPS: 11.41/11.41 result: MeasureResult(costs=(0.023520208,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6208279132843018, timestamp=1673239172.6393936) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
+No: 4 GFLOPS: 1.72/11.41 result: MeasureResult(costs=(0.1564901232,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.722008466720581, timestamp=1673239176.1454906) [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
+No: 5 GFLOPS: 2.06/11.41 result: MeasureResult(costs=(0.1301242782,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3213050365448, timestamp=1673239178.6602304) [('tile_y', [-1, 256]), ('tile_x', [-1, 4])],None,28
+No: 6 GFLOPS: 3.95/11.41 result: MeasureResult(costs=(0.0679048804,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3706169128417969, timestamp=1673239179.9976563) [('tile_y', [-1, 64]), ('tile_x', [-1, 16])],None,46
+No: 7 GFLOPS: 13.14/13.14 result: MeasureResult(costs=(0.020434777199999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6490328311920166, timestamp=1673239181.3323748) [('tile_y', [-1, 128]), ('tile_x', [-1, 128])],None,77
+No: 8 GFLOPS: 10.44/13.14 result: MeasureResult(costs=(0.025721925200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6830213069915771, timestamp=1673239182.00092) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
+No: 9 GFLOPS: 1.47/13.14 result: MeasureResult(costs=(0.1827412212,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.1473960876464844, timestamp=1673239185.2715592) [('tile_y', [-1, 4]), ('tile_x', [-1, 1])],None,2
+No: 10 GFLOPS: 0.89/13.14 result: MeasureResult(costs=(0.3000508844,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.023648738861084, timestamp=1673239190.318813) [('tile_y', [-1, 64]), ('tile_x', [-1, 2])],None,16
</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 1a63cc29bf..035fbbff7c 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -561,7 +561,7 @@ 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': 512.9814760500005, 'median': 513.116963899995, 'std': 2.1695880671952343}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 511.56517501999707, 'median': 511.7573987999947, 'std': 2.2377189524267567}
</pre></div>
</div>
</div>
@@ -713,179 +713,177 @@ 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: 9.44/ 16.64 GFLOPS | Progress: (4/20) | 7.85 s
-[Task 1/25] Current/Best: 11.19/ 16.64 GFLOPS | Progress: (8/20) | 11.81 s
-[Task 1/25] Current/Best: 14.30/ 22.29 GFLOPS | Progress: (12/20) | 14.30 s
-[Task 1/25] Current/Best: 11.04/ 22.29 GFLOPS | Progress: (16/20) | 17.25 s
-[Task 1/25] Current/Best: 23.94/ 23.94 GFLOPS | Progress: (20/20) | 19.21 s Done.
+[Task 1/25] Current/Best: 9.52/ 22.23 GFLOPS | Progress: (4/20) | 7.22 s
+[Task 1/25] Current/Best: 12.91/ 22.23 GFLOPS | Progress: (8/20) | 10.84 s
+[Task 1/25] Current/Best: 10.18/ 22.23 GFLOPS | Progress: (12/20) | 14.69 s
+[Task 1/25] Current/Best: 16.62/ 22.23 GFLOPS | Progress: (16/20) | 17.48 s
+[Task 1/25] Current/Best: 14.32/ 22.23 GFLOPS | Progress: (20/20) | 19.42 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.87/ 12.92 GFLOPS | Progress: (4/20) | 4.11 s
-[Task 2/25] Current/Best: 11.01/ 18.58 GFLOPS | Progress: (8/20) | 5.81 s
-[Task 2/25] Current/Best: 15.19/ 23.00 GFLOPS | Progress: (12/20) | 7.51 s
-[Task 2/25] Current/Best: 19.23/ 23.00 GFLOPS | Progress: (16/20) | 9.20 s
-[Task 2/25] Current/Best: 12.68/ 23.00 GFLOPS | Progress: (20/20) | 10.61 s Done.
+[Task 2/25] Current/Best: 9.62/ 21.06 GFLOPS | Progress: (4/20) | 3.37 s
+[Task 2/25] Current/Best: 16.78/ 21.06 GFLOPS | Progress: (8/20) | 4.95 s
+[Task 2/25] Current/Best: 14.95/ 21.06 GFLOPS | Progress: (12/20) | 6.86 s
+[Task 2/25] Current/Best: 19.56/ 21.06 GFLOPS | Progress: (16/20) | 8.67 s
+[Task 2/25] Current/Best: 9.79/ 21.06 GFLOPS | Progress: (20/20) | 10.29 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 15.86/ 22.40 GFLOPS | Progress: (4/20) | 3.88 s
-[Task 3/25] Current/Best: 23.37/ 23.37 GFLOPS | Progress: (8/20) | 6.04 s
-[Task 3/25] Current/Best: 3.17/ 23.37 GFLOPS | Progress: (12/20) | 10.15 s
-[Task 3/25] Current/Best: 3.14/ 23.37 GFLOPS | Progress: (16/20) | 13.40 s
-[Task 3/25] Current/Best: 19.33/ 23.37 GFLOPS | Progress: (20/20) | 15.40 s Done.
+[Task 3/25] Current/Best: 11.18/ 13.23 GFLOPS | Progress: (4/20) | 4.49 s
+[Task 3/25] Current/Best: 14.60/ 14.84 GFLOPS | Progress: (8/20) | 7.31 s
+[Task 3/25] Current/Best: 17.77/ 17.77 GFLOPS | Progress: (12/20) | 9.90 s
+[Task 3/25] Current/Best: 14.56/ 23.83 GFLOPS | Progress: (16/20) | 12.26 s
+[Task 3/25] Current/Best: 9.16/ 23.83 GFLOPS | Progress: (20/20) | 15.47 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 13.25/ 16.98 GFLOPS | Progress: (4/20) | 4.00 s
-[Task 4/25] Current/Best: 8.45/ 20.64 GFLOPS | Progress: (8/20) | 6.02 s
-[Task 4/25] Current/Best: 16.85/ 20.64 GFLOPS | Progress: (12/20) | 8.04 s
-[Task 4/25] Current/Best: 13.77/ 20.64 GFLOPS | Progress: (16/20) | 11.11 s
-[Task 4/25] Current/Best: 11.21/ 20.64 GFLOPS | Progress: (20/20) | 14.23 s Done.
+[Task 4/25] Current/Best: 13.48/ 13.48 GFLOPS | Progress: (4/20) | 4.26 s
+[Task 4/25] Current/Best: 10.62/ 13.48 GFLOPS | Progress: (8/20) | 9.18 s
+[Task 4/25] Current/Best: 12.80/ 18.61 GFLOPS | Progress: (12/20) | 11.94 s
+[Task 4/25] Current/Best: 11.02/ 18.61 GFLOPS | Progress: (16/20) | 14.36 s
+[Task 4/25] Current/Best: 14.36/ 21.45 GFLOPS | Progress: (20/20) | 16.68 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 10.67/ 11.44 GFLOPS | Progress: (4/20) | 4.20 s
-[Task 5/25] Current/Best: 13.26/ 13.26 GFLOPS | Progress: (8/20) | 6.94 s
-[Task 5/25] Current/Best: 6.01/ 13.26 GFLOPS | Progress: (12/20) | 9.21 s
-[Task 5/25] Current/Best: 9.55/ 13.49 GFLOPS | Progress: (16/20) | 11.37 s
-[Task 5/25] Current/Best: 3.62/ 18.22 GFLOPS | Progress: (20/20) | 13.84 s Done.
+[Task 5/25] Current/Best: 13.04/ 13.53 GFLOPS | Progress: (4/20) | 3.89 s
+[Task 5/25] Current/Best: 5.79/ 20.35 GFLOPS | Progress: (8/20) | 6.64 s
+[Task 5/25] Current/Best: 11.87/ 20.35 GFLOPS | Progress: (12/20) | 8.89 s
+[Task 5/25] Current/Best: 5.07/ 20.35 GFLOPS | Progress: (16/20) | 10.94 s
+[Task 5/25] Current/Best: 11.76/ 20.35 GFLOPS | Progress: (20/20) | 14.19 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 13.17/ 14.65 GFLOPS | Progress: (4/20) | 4.35 s
-[Task 6/25] Current/Best: 9.66/ 19.63 GFLOPS | Progress: (8/20) | 6.63 s
-[Task 6/25] Current/Best: 8.86/ 19.63 GFLOPS | Progress: (12/20) | 8.97 s
-[Task 6/25] Current/Best: 11.10/ 19.63 GFLOPS | Progress: (16/20) | 12.36 s
-[Task 6/25] Current/Best: 6.08/ 19.63 GFLOPS | Progress: (20/20) | 15.42 s Done.
+[Task 6/25] Current/Best: 2.62/ 16.97 GFLOPS | Progress: (4/20) | 5.29 s
+[Task 6/25] Current/Best: 2.94/ 20.35 GFLOPS | Progress: (8/20) | 8.73 s
+[Task 6/25] Current/Best: 13.17/ 20.35 GFLOPS | Progress: (12/20) | 11.57 s
+[Task 6/25] Current/Best: 9.02/ 20.36 GFLOPS | Progress: (16/20) | 14.04 s
+[Task 6/25] Current/Best: 3.19/ 20.36 GFLOPS | Progress: (20/20) | 17.98 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.75/ 20.02 GFLOPS | Progress: (4/20) | 4.79 s
-[Task 7/25] Current/Best: 13.52/ 20.02 GFLOPS | Progress: (8/20) | 7.79 s
-[Task 7/25] Current/Best: 8.81/ 20.02 GFLOPS | Progress: (12/20) | 10.28 s
-[Task 7/25] Current/Best: 6.11/ 20.02 GFLOPS | Progress: (16/20) | 12.86 s
-[Task 7/25] Current/Best: 18.44/ 20.02 GFLOPS | Progress: (20/20) | 15.39 s Done.
+[Task 7/25] Current/Best: 16.08/ 16.08 GFLOPS | Progress: (4/20) | 4.11 s
+[Task 7/25] Current/Best: 8.74/ 16.08 GFLOPS | Progress: (8/20) | 7.85 s
+[Task 7/25] Current/Best: 9.18/ 19.39 GFLOPS | Progress: (12/20) | 10.88 s
+[Task 7/25] Current/Best: 11.23/ 19.39 GFLOPS | Progress: (16/20) | 13.87 s
+[Task 7/25] Current/Best: 15.32/ 19.39 GFLOPS | Progress: (20/20) | 16.13 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 8.86/ 13.74 GFLOPS | Progress: (4/20) | 4.86 s
-[Task 8/25] Current/Best: 2.10/ 18.54 GFLOPS | Progress: (8/20) | 8.07 s
-[Task 8/25] Current/Best: 10.50/ 18.54 GFLOPS | Progress: (12/20) | 20.06 s
-[Task 8/25] Current/Best: 2.77/ 18.54 GFLOPS | Progress: (16/20) | 23.05 s
-[Task 8/25] Current/Best: 12.51/ 18.54 GFLOPS | Progress: (20/20) | 34.43 s
+[Task 8/25] Current/Best: 2.55/ 12.26 GFLOPS | Progress: (4/20) | 10.89 s
+[Task 8/25] Current/Best: 8.08/ 12.26 GFLOPS | Progress: (8/20) | 19.18 s
+[Task 8/25] Current/Best: 5.97/ 12.26 GFLOPS | Progress: (12/20) | 25.91 s
+[Task 8/25] Current/Best: 13.11/ 13.11 GFLOPS | Progress: (16/20) | 29.88 s
+[Task 8/25] Current/Best: 13.86/ 13.86 GFLOPS | Progress: (20/20) | 32.50 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 11.53/ 21.54 GFLOPS | Progress: (4/20) | 8.03 s
-[Task 9/25] Current/Best: 6.49/ 21.54 GFLOPS | Progress: (8/20) | 9.82 s
-[Task 9/25] Current/Best: 14.49/ 21.54 GFLOPS | Progress: (12/20) | 14.09 s
-[Task 9/25] Current/Best: 11.36/ 21.54 GFLOPS | Progress: (16/20) | 16.31 s
-[Task 9/25] Current/Best: 16.49/ 21.54 GFLOPS | Progress: (20/20) | 18.17 s Done.
+[Task 9/25] Current/Best: 11.73/ 18.62 GFLOPS | Progress: (4/20) | 4.56 s
+[Task 9/25] Current/Best: 11.20/ 18.62 GFLOPS | Progress: (8/20) | 11.70 s
+[Task 9/25] Current/Best: 9.68/ 19.95 GFLOPS | Progress: (12/20) | 15.22 s
+[Task 9/25] Current/Best: 5.21/ 19.95 GFLOPS | Progress: (16/20) | 20.65 s
+[Task 9/25] Current/Best: 16.01/ 19.95 GFLOPS | Progress: (20/20) | 22.31 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 4.27/ 12.90 GFLOPS | Progress: (4/20) | 3.84 s
-[Task 10/25] Current/Best: 11.56/ 16.10 GFLOPS | Progress: (8/20) | 6.40 s
-[Task 10/25] Current/Best: 15.00/ 16.10 GFLOPS | Progress: (12/20) | 9.89 s
-[Task 10/25] Current/Best: 14.47/ 16.10 GFLOPS | Progress: (16/20) | 12.17 s
-[Task 10/25] Current/Best: 10.07/ 17.27 GFLOPS | Progress: (20/20) | 14.95 s Done.
+[Task 10/25] Current/Best: 4.31/ 18.63 GFLOPS | Progress: (4/20) | 4.72 s
+[Task 10/25] Current/Best: 15.53/ 18.63 GFLOPS | Progress: (8/20) | 6.71 s
+[Task 10/25] Current/Best: 3.14/ 18.63 GFLOPS | Progress: (12/20) | 9.53 s
+[Task 10/25] Current/Best: 14.31/ 18.63 GFLOPS | Progress: (16/20) | 11.34 s
+[Task 10/25] Current/Best: 10.33/ 18.63 GFLOPS | Progress: (20/20) | 13.16 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 7.05/ 23.97 GFLOPS | Progress: (4/20) | 4.22 s
-[Task 11/25] Current/Best: 11.56/ 23.97 GFLOPS | Progress: (8/20) | 8.07 s
-[Task 11/25] Current/Best: 3.13/ 23.97 GFLOPS | Progress: (12/20) | 10.93 s
-[Task 11/25] Current/Best: 15.95/ 23.97 GFLOPS | Progress: (16/20) | 13.79 s
-[Task 11/25] Current/Best: 17.29/ 23.97 GFLOPS | Progress: (20/20) | 16.05 s Done.
+[Task 11/25] Current/Best: 8.43/ 23.15 GFLOPS | Progress: (4/20) | 4.32 s
+[Task 11/25] Current/Best: 16.38/ 23.15 GFLOPS | Progress: (8/20) | 7.45 s
+[Task 11/25] Current/Best: 16.44/ 23.15 GFLOPS | Progress: (12/20) | 9.85 s
+[Task 11/25] Current/Best: 6.84/ 23.15 GFLOPS | Progress: (16/20) | 13.09 s
+[Task 11/25] Current/Best: 19.14/ 23.15 GFLOPS | Progress: (20/20) | 15.71 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 4.46/ 15.48 GFLOPS | Progress: (4/20) | 8.06 s
-[Task 12/25] Current/Best: 13.49/ 15.48 GFLOPS | Progress: (8/20) | 11.96 s
-[Task 12/25] Current/Best: 13.07/ 17.99 GFLOPS | Progress: (12/20) | 15.00 s
-[Task 12/25] Current/Best: 17.50/ 18.36 GFLOPS | Progress: (16/20) | 17.30 s
-[Task 12/25] Current/Best: 2.94/ 18.36 GFLOPS | Progress: (20/20) | 22.28 s Done.
+[Task 12/25] Current/Best: 3.10/ 14.10 GFLOPS | Progress: (4/20) | 5.56 s
+[Task 12/25] Current/Best: 5.85/ 18.71 GFLOPS | Progress: (8/20) | 7.65 s
+[Task 12/25] Current/Best: 15.05/ 18.71 GFLOPS | Progress: (12/20) | 10.82 s
+[Task 12/25] Current/Best: 5.18/ 20.96 GFLOPS | Progress: (16/20) | 14.50 s
+[Task 12/25] Current/Best: 11.00/ 20.96 GFLOPS | Progress: (20/20) | 17.59 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 13.96/ 19.63 GFLOPS | Progress: (4/20) | 4.50 s
-[Task 13/25] Current/Best: 6.38/ 19.63 GFLOPS | Progress: (8/20) | 7.19 s
-[Task 13/25] Current/Best: 15.51/ 21.63 GFLOPS | Progress: (12/20) | 9.52 s
-[Task 13/25] Current/Best: 19.83/ 21.63 GFLOPS | Progress: (16/20) | 12.86 s
-[Task 13/25] Current/Best: 6.21/ 21.63 GFLOPS | Progress: (20/20) | 16.54 s Done.
+[Task 13/25] Current/Best: 9.48/ 21.39 GFLOPS | Progress: (4/20) | 4.14 s
+[Task 13/25] Current/Best: 15.63/ 21.39 GFLOPS | Progress: (8/20) | 6.07 s
+[Task 13/25] Current/Best: 16.12/ 21.39 GFLOPS | Progress: (12/20) | 9.01 s
+[Task 13/25] Current/Best: 18.64/ 21.39 GFLOPS | Progress: (16/20) | 13.34 s
+[Task 13/25] Current/Best: 8.76/ 21.39 GFLOPS | Progress: (20/20) | 16.08 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 9.86/ 13.25 GFLOPS | Progress: (4/20) | 5.13 s
-[Task 14/25] Current/Best: 12.93/ 16.26 GFLOPS | Progress: (8/20) | 8.76 s
-[Task 14/25] Current/Best: 17.65/ 17.65 GFLOPS | Progress: (12/20) | 10.55 s
-[Task 14/25] Current/Best: 6.16/ 17.65 GFLOPS | Progress: (16/20) | 14.31 s
-[Task 14/25] Current/Best: 19.69/ 19.69 GFLOPS | Progress: (20/20) | 17.56 s
-[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 6.63/ 15.46 GFLOPS | Progress: (4/20) | 7.98 s Done.
- Done.
-
-[Task 15/25] Current/Best: 6.41/ 15.46 GFLOPS | Progress: (8/20) | 13.32 s
-[Task 15/25] Current/Best: 9.40/ 20.68 GFLOPS | Progress: (12/20) | 15.64 s
-[Task 15/25] Current/Best: 13.80/ 20.68 GFLOPS | Progress: (16/20) | 17.21 s
-[Task 15/25] Current/Best: 22.44/ 22.44 GFLOPS | Progress: (20/20) | 19.06 s Done.
+[Task 14/25] Current/Best: 15.25/ 22.25 GFLOPS | Progress: (4/20) | 4.24 s
+[Task 14/25] Current/Best: 13.88/ 22.25 GFLOPS | Progress: (8/20) | 8.57 s
+[Task 14/25] Current/Best: 9.17/ 22.25 GFLOPS | Progress: (12/20) | 14.89 s
+[Task 14/25] Current/Best: 10.72/ 22.25 GFLOPS | Progress: (16/20) | 21.00 s
+[Task 14/25] Current/Best: 17.61/ 22.25 GFLOPS | Progress: (20/20) | 23.63 s Done.
+[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 15/25] Current/Best: 12.36/ 19.35 GFLOPS | Progress: (4/20) | 3.77 s
+[Task 15/25] Current/Best: 13.98/ 19.35 GFLOPS | Progress: (8/20) | 5.79 s
+[Task 15/25] Current/Best: 17.28/ 21.09 GFLOPS | Progress: (12/20) | 7.27 s
+[Task 15/25] Current/Best: 21.02/ 21.09 GFLOPS | Progress: (16/20) | 8.98 s
+[Task 15/25] Current/Best: 11.23/ 21.09 GFLOPS | Progress: (20/20) | 11.22 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 8.90/ 19.15 GFLOPS | Progress: (4/20) | 3.36 s
-[Task 16/25] Current/Best: 18.50/ 19.15 GFLOPS | Progress: (8/20) | 5.81 s
-[Task 16/25] Current/Best: 18.30/ 19.15 GFLOPS | Progress: (12/20) | 7.43 s
-[Task 16/25] Current/Best: 14.68/ 19.15 GFLOPS | Progress: (16/20) | 9.77 s
-[Task 16/25] Current/Best: 11.12/ 19.15 GFLOPS | Progress: (20/20) | 11.43 s Done.
+[Task 16/25] Current/Best: 17.99/ 17.99 GFLOPS | Progress: (4/20) | 3.62 s
+[Task 16/25] Current/Best: 13.51/ 17.99 GFLOPS | Progress: (8/20) | 5.47 s
+[Task 16/25] Current/Best: 14.24/ 17.99 GFLOPS | Progress: (12/20) | 7.64 s
+[Task 16/25] Current/Best: 11.34/ 17.99 GFLOPS | Progress: (16/20) | 11.57 s
+[Task 16/25] Current/Best: 10.00/ 18.50 GFLOPS | Progress: (20/20) | 15.21 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 17.11/ 17.94 GFLOPS | Progress: (4/20) | 4.51 s
-[Task 17/25] Current/Best: 17.67/ 23.04 GFLOPS | Progress: (8/20) | 6.45 s
-[Task 17/25] Current/Best: 13.11/ 23.04 GFLOPS | Progress: (12/20) | 8.33 s
-[Task 17/25] Current/Best: 11.98/ 23.04 GFLOPS | Progress: (16/20) | 10.87 s
-[Task 17/25] Current/Best: 14.08/ 23.04 GFLOPS | Progress: (20/20) | 13.63 s Done.
+[Task 17/25] Current/Best: 22.31/ 22.31 GFLOPS | Progress: (4/20) | 4.11 s
+[Task 17/25] Current/Best: 6.14/ 22.31 GFLOPS | Progress: (8/20) | 6.41 s
+[Task 17/25] Current/Best: 12.87/ 22.31 GFLOPS | Progress: (12/20) | 9.03 s
+[Task 17/25] Current/Best: 12.20/ 22.31 GFLOPS | Progress: (16/20) | 11.68 s
+[Task 17/25] Current/Best: 10.32/ 22.31 GFLOPS | Progress: (20/20) | 16.83 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 4.34/ 17.17 GFLOPS | Progress: (4/20) | 4.25 s
-[Task 18/25] Current/Best: 19.33/ 19.86 GFLOPS | Progress: (8/20) | 7.18 s
-[Task 18/25] Current/Best: 8.96/ 19.86 GFLOPS | Progress: (12/20) | 9.95 s
-[Task 18/25] Current/Best: 5.61/ 19.86 GFLOPS | Progress: (16/20) | 16.09 s
-[Task 18/25] Current/Best: 15.71/ 19.86 GFLOPS | Progress: (20/20) | 18.67 s Done.
+[Task 18/25] Current/Best: 2.86/ 19.07 GFLOPS | Progress: (4/20) | 5.24 s
+[Task 18/25] Current/Best: 16.98/ 19.07 GFLOPS | Progress: (8/20) | 7.31 s
+[Task 18/25] Current/Best: 18.68/ 19.07 GFLOPS | Progress: (12/20) | 10.69 s
+[Task 18/25] Current/Best: 4.98/ 19.07 GFLOPS | Progress: (16/20) | 13.00 s
+[Task 18/25] Current/Best: 1.57/ 19.07 GFLOPS | Progress: (20/20) | 16.32 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 11.34/ 11.34 GFLOPS | Progress: (4/20) | 5.79 s
-[Task 19/25] Current/Best: 17.77/ 17.77 GFLOPS | Progress: (8/20) | 10.95 s
-[Task 19/25] Current/Best: 5.28/ 19.19 GFLOPS | Progress: (12/20) | 14.44 s
-[Task 19/25] Current/Best: 8.94/ 23.19 GFLOPS | Progress: (16/20) | 17.37 s
-[Task 19/25] Current/Best: 5.33/ 23.19 GFLOPS | Progress: (20/20) | 20.07 s Done.
+[Task 19/25] Current/Best: 8.93/ 20.13 GFLOPS | Progress: (4/20) | 4.60 s
+[Task 19/25] Current/Best: 9.55/ 20.13 GFLOPS | Progress: (8/20) | 7.38 s
+[Task 19/25] Current/Best: 17.10/ 20.13 GFLOPS | Progress: (12/20) | 10.48 s
+[Task 19/25] Current/Best: 9.27/ 20.13 GFLOPS | Progress: (16/20) | 13.74 s
+[Task 19/25] Current/Best: 17.51/ 20.13 GFLOPS | Progress: (20/20) | 17.80 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 8.85/ 12.88 GFLOPS | Progress: (4/20) | 5.36 s
-[Task 20/25] Current/Best: 4.78/ 15.08 GFLOPS | Progress: (8/20) | 9.11 s
-[Task 20/25] Current/Best: 1.58/ 16.87 GFLOPS | Progress: (12/20) | 12.50 s
-[Task 20/25] Current/Best: 15.85/ 16.87 GFLOPS | Progress: (16/20) | 16.26 s
-[Task 20/25] Current/Best: 7.34/ 19.61 GFLOPS | Progress: (20/20) | 19.08 s
+[Task 20/25] Current/Best: 18.15/ 18.15 GFLOPS | Progress: (4/20) | 4.23 s
+[Task 20/25] Current/Best: 7.43/ 18.15 GFLOPS | Progress: (8/20) | 7.45 s
+[Task 20/25] Current/Best: 10.97/ 18.15 GFLOPS | Progress: (12/20) | 11.54 s Done.
+
+[Task 20/25] Current/Best: 8.87/ 18.15 GFLOPS | Progress: (16/20) | 13.54 s
+[Task 20/25] Current/Best: 16.43/ 18.15 GFLOPS | Progress: (20/20) | 16.75 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 7.99/ 16.32 GFLOPS | Progress: (4/20) | 3.87 s
-[Task 21/25] Current/Best: 13.72/ 21.63 GFLOPS | Progress: (8/20) | 6.35 s
-[Task 21/25] Current/Best: 5.31/ 21.63 GFLOPS | Progress: (12/20) | 8.59 s
-[Task 21/25] Current/Best: 15.03/ 21.63 GFLOPS | Progress: (16/20) | 11.85 s
-[Task 21/25] Current/Best: 8.25/ 21.63 GFLOPS | Progress: (20/20) | 14.34 s
+[Task 21/25] Current/Best: 8.39/ 12.96 GFLOPS | Progress: (4/20) | 4.96 s
+[Task 21/25] Current/Best: 4.49/ 16.93 GFLOPS | Progress: (8/20) | 7.37 s
+[Task 21/25] Current/Best: 5.43/ 16.93 GFLOPS | Progress: (12/20) | 10.03 s
+[Task 21/25] Current/Best: 17.45/ 22.50 GFLOPS | Progress: (16/20) | 11.96 s
+[Task 21/25] Current/Best: 16.63/ 22.50 GFLOPS | Progress: (20/20) | 14.85 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 12.82/ 12.82 GFLOPS | Progress: (4/20) | 4.36 s Done.
- Done.
-
-[Task 22/25] Current/Best: 5.30/ 15.88 GFLOPS | Progress: (8/20) | 9.28 s
-[Task 22/25] Current/Best: 11.36/ 18.43 GFLOPS | Progress: (12/20) | 11.41 s
-[Task 22/25] Current/Best: 14.04/ 22.02 GFLOPS | Progress: (16/20) | 13.52 s
-[Task 22/25] Current/Best: 15.99/ 22.02 GFLOPS | Progress: (20/20) | 15.22 s Done.
+[Task 22/25] Current/Best: 10.59/ 19.78 GFLOPS | Progress: (4/20) | 3.95 s
+[Task 22/25] Current/Best: 10.91/ 21.11 GFLOPS | Progress: (8/20) | 5.99 s
+[Task 22/25] Current/Best: 10.14/ 21.11 GFLOPS | Progress: (12/20) | 8.53 s
+[Task 22/25] Current/Best: 18.11/ 21.11 GFLOPS | Progress: (16/20) | 10.71 s
+[Task 22/25] Current/Best: 15.90/ 21.11 GFLOPS | Progress: (20/20) | 12.32 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 14.25/ 14.25 GFLOPS | Progress: (4/20) | 5.16 s
-[Task 23/25] Current/Best: 10.59/ 22.87 GFLOPS | Progress: (8/20) | 7.67 s
-[Task 23/25] Current/Best: 18.50/ 22.87 GFLOPS | Progress: (12/20) | 9.81 s
-[Task 23/25] Current/Best: 6.13/ 22.87 GFLOPS | Progress: (16/20) | 13.76 s
-[Task 23/25] Current/Best: 10.69/ 22.87 GFLOPS | Progress: (20/20) | 17.43 s Done.
+[Task 23/25] Current/Best: 11.50/ 20.74 GFLOPS | Progress: (4/20) | 5.36 s
+[Task 23/25] Current/Best: 12.13/ 20.74 GFLOPS | Progress: (8/20) | 8.37 s
+[Task 23/25] Current/Best: 2.63/ 20.74 GFLOPS | Progress: (12/20) | 12.25 s
+[Task 23/25] Current/Best: 9.58/ 20.74 GFLOPS | Progress: (16/20) | 15.80 s
+[Task 23/25] Current/Best: 16.92/ 20.74 GFLOPS | Progress: (20/20) | 18.39 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 3.50/ 3.50 GFLOPS | Progress: (4/20) | 10.28 s
-[Task 24/25] Current/Best: 7.50/ 7.50 GFLOPS | Progress: (8/20) | 17.66 s
-[Task 24/25] Current/Best: 6.85/ 7.50 GFLOPS | Progress: (12/20) | 28.59 s
-[Task 24/25] Current/Best: 0.68/ 7.50 GFLOPS | Progress: (16/20) | 39.58 s
-[Task 24/25] Current/Best: 9.07/ 9.07 GFLOPS | Progress: (20/20) | 47.55 s
-[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 3.49/ 8.60 GFLOPS | Progress: (4/20) | 7.30 s
-[Task 25/25] Current/Best: 2.86/ 8.60 GFLOPS | Progress: (8/20) | 9.06 s
-[Task 25/25] Current/Best: 0.00/ 8.60 GFLOPS | Progress: (12/20) | 19.15 s Done.
+[Task 24/25] Current/Best: 0.74/ 8.01 GFLOPS | Progress: (4/20) | 12.78 s
+[Task 24/25] Current/Best: 3.61/ 9.24 GFLOPS | Progress: (8/20) | 23.71 s Done.
-[Task 25/25] Current/Best: 2.87/ 8.60 GFLOPS | Progress: (16/20) | 22.03 s
-[Task 25/25] Current/Best: 1.55/ 8.60 GFLOPS | Progress: (20/20) | 23.42 s Done.
+[Task 24/25] Current/Best: 3.71/ 10.24 GFLOPS | Progress: (12/20) | 34.64 s
+[Task 24/25] Current/Best: 1.69/ 10.24 GFLOPS | Progress: (16/20) | 45.69 s
+[Task 24/25] Current/Best: 3.92/ 10.24 GFLOPS | Progress: (20/20) | 48.19 s
+[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 25/25] Current/Best: 3.01/ 8.38 GFLOPS | Progress: (4/20) | 5.16 s
+[Task 25/25] Current/Best: 5.02/ 8.49 GFLOPS | Progress: (8/20) | 6.69 s
+[Task 25/25] Current/Best: 1.55/ 9.25 GFLOPS | Progress: (12/20) | 8.27 s
+[Task 25/25] Current/Best: 8.48/ 9.25 GFLOPS | Progress: (16/20) | 9.63 s
+[Task 25/25] Current/Best: 7.21/ 9.25 GFLOPS | Progress: (20/20) | 18.54 s Done.
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -946,9 +944,9 @@ model using optimized operators to speed up our computations.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"class='</span><span class="si">%s</span><span class="s2">' with probability=</span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621104
-class='n02123159 tiger cat' with probability=0.356377
-class='n02124075 Egyptian cat' with probability=0.019713
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621103
+class='n02123159 tiger cat' with probability=0.356379
+class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
</pre></div>
@@ -984,8 +982,8 @@ 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': 408.15722969999797, 'median': 408.19497814999295, 'std': 2.4655740798439547}
-unoptimized: {'mean': 512.9814760500005, 'median': 513.116963899995, 'std': 2.1695880671952343}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 418.37471445000347, 'median': 418.23366605000274, 'std': 0.4591835005156814}
+unoptimized: {'mean': 511.56517501999707, 'median': 511.7573987999947, 'std': 2.2377189524267567}
</pre></div>
</div>
</div>
@@ -999,7 +997,7 @@ 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> ( 11 minutes 11.378 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 11 minutes 4.451 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 e79cfe201c..b4146975e2 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -538,7 +538,7 @@ 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>1.245e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.203e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 513265d437..c004e67ac3 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -495,7 +495,7 @@ 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>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x17e034a0)), stage(b, placeholder(b, 0x5306300)), 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=[i [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x23312e10)), stage(b, placeholder(b, 0x6ab6f10)), 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=[i [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index 2defad6846..abbd3d4861 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>14:19.345</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>14:37.512</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,39 +349,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>11:11.378</p></td>
+<td><p>11:04.451</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>01:07.591</p></td>
+<td><p>01:23.747</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:02.668</p></td>
+<td><p>00:59.991</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:34.021</p></td>
+<td><p>00:33.693</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:21.240</p></td>
+<td><p>00:32.911</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:01.439</p></td>
+<td><p>00:01.711</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.818</p></td>
+<td><p>00:00.822</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></td>
-<td><p>00:00.179</p></td>
+<td><p>00:00.172</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.009</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 096bf9b83f..f14d6db073 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -552,7 +552,7 @@ helper function to run a profile of the TVM generated code.</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
naive: 0.000007
</pre></div>
</div>
@@ -601,7 +601,7 @@ compile and run this new schedule with the parallel operation applied:</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd_parallel</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"parallel"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.h [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000006
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000007
</pre></div>
</div>
</div>
@@ -640,7 +640,7 @@ factor to be the number of threads on your CPU.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><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 [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000025
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000042
@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, [n: int32], [stride: int32], type="auto"),
@@ -672,10 +672,10 @@ factor to be the number of threads on your CPU.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.756029999654856e-06 1.0
- naive 6.6697e-06 0.8599373649014769
-parallel 6.0653999999999996e-06 0.7820237931351361
- vector 2.4616699999999998e-05 3.1738789046838964
+ numpy 7.306019999759883e-06 1.0
+ naive 7.489e-06 1.0250450998281049
+parallel 6.970399999999999e-06 0.9540625402379251
+ vector 4.18898e-05 5.733600510452577
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -991,7 +991,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</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: 0.018343
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018771
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1032,7 +1032,7 @@ optimizations.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><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">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.535982
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.339059
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1096,7 +1096,7 @@ schedule.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><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">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.299280
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.292577
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1154,7 +1154,7 @@ already cache friendly from our previous optimizations.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><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 [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.335652
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.333358
@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, [1024, 1024], []),
@@ -1208,7 +1208,7 @@ more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><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 [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.119530
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.116399
@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, [1024, 1024], []),
@@ -1283,7 +1283,7 @@ optimized schedule.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><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 [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.109487
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.109907
@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, [1024, 1024], []),
@@ -1356,7 +1356,7 @@ to `C</cite> when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><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 [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110940
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.111226
@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, [1024, 1024], []),
@@ -1422,7 +1422,7 @@ of thread-level parallelization.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><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 [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146024
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146855
@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, [1024, 1024], []),
@@ -1483,13 +1483,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.535982266 1.0
- blocking 0.2992804805 0.08463856942318726
- vectorization 0.3356515825 0.094924566146
-loop permutation 0.11952960940000001 0.033803792103068206
- array packing 0.1094872316 0.03096373888884204
- block caching 0.11093986420000002 0.03137455333606586
- parallelization 0.1460238378 0.04129654133282353
+ none 3.3390590394 1.0
+ blocking 0.2925770818 0.08762261413999245
+ vectorization 0.3333578841 0.0998358759657935
+loop permutation 0.1163994854 0.03485996624393799
+ array packing 0.1099073437 0.032915663485767355
+ block caching 0.11122612800000001 0.03331062035368694
+ parallelization 0.1468552615 0.043981031711972554
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1521,7 +1521,6 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.668 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-tensor-expr-get-started-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/40a01cffb015a67aaec0fad7e27cf80d/tensor_expr_get_started.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">tensor_expr_get_started.py</span></code></a></p>