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 23:49:24 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@687ec7883be48c4e371d565d50ed2f29fec755f5)
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 52fab9512a deploying docs (apache/tvm@687ec7883be48c4e371d565d50ed2f29fec755f5)
52fab9512a is described below
commit 52fab9512aa0fa855e80a7af3daa0b8abb835df5
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Mon Jan 9 23:49:18 2023 +0000
deploying docs (apache/tvm@687ec7883be48c4e371d565d50ed2f29fec755f5)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 330120 -> 335230 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 23754 -> 23974 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 | 10 +-
.../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 | 1314 ++++++--------------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 110 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 4 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 355 +-----
.../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 | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 6 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 63 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 45 +-
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 | 12 +-
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 | 35 +-
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 | 36 +-
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 | 10 +-
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 | 1314 ++++++--------------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 110 +-
.../tune_with_autotvm/sg_execution_times.html | 4 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 355 +-----
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 6 +-
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 | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 5 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 279 +++--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 22 +-
docs/tutorial/tensor_expr_get_started.html | 41 +-
130 files changed, 1855 insertions(+), 3328 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 749f250b96..4730ebaecb 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 eb961b1b9c..4f63c99e35 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 d0ffb590dc..410bfc457a 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 8.507 seconds)
+ **Total running time of the script:** ( 1 minutes 10.716 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 a9009a1d88..15fec1da51 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 941ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 975ms/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 dc02173780..1e7e429c72 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.zipef3d8b0c-9315-48ac-b8aa-2cc5c899a199 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip0832fa66-0b78-448f-8ad0-117c59271f16 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 6e57132dae..c1dbe8bc4d 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, 64.4MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 48.4MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 56.4MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 63.9MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 62.8MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 58.9MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 55.7MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 60.2MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 55.8MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 53.0MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 53.3MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 55.4MB/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 c8f110ddda..a58b0612d1 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]
23%|##2 | 10.1M/44.7M [00:00<00:00, 102MB/s]
44%|####4 | 19.8M/44.7M [00:00<00:00, 102MB/s]
72%|#######1 | 32.0M/44.7M [00:00<00:00, 107MB/s]
98%|#########8| 43.9M/44.7M [00:00<00:00, 114MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 110MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
27%|##7 | 12.2M/44.7M [00:00<00:00, 128MB/s]
55%|#####4 | 24.4M/44.7M [00:00<00:00, 108MB/s]
78%|#######8 | 34.9M/44.7M [00:00<00:00, 106MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 86.3MB/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 870c3dceb6..0e6c383fea 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 10.327 seconds)
+ **Total running time of the script:** ( 1 minutes 14.098 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 8e17ddd7a1..3d9f2000dc 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
=================
-**05:35.495** total execution time for **how_to_compile_models** files:
+**05:48.487** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:10.327 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:14.098 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:08.507 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:10.716 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:45.111 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:47.436 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:31.720 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:33.202 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:28.460 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.301 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:25.887 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.975 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.261 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.142 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:21.492 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.418 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.331 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.747 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.399 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.451 | 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 034cacb45b..eea62cb507 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)
- 2684.0773 2684.0619 2686.3851 2681.6193 1.5952
+ 2687.9779 2686.1206 2702.8615 2682.0912 5.8631
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 6cf5c75c25..c46f720429 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)
- 15.7012 15.5594 16.5362 15.4742 0.3134
+ 16.4942 16.4020 17.2558 16.2129 0.2964
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 6f7696ed7c..a7529c7e6c 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<00:03, 49.8MB/s]
9%|9 | 16.0M/170M [00:00<00:03, 51.2MB/s]
14%|#4 | 24.0M/170M [00:00<00:02, 56.0MB/s]
19%|#8 | 32.0M/170M [00:00<00:03, 41.4MB/s]
24%|##3 | 40.0M/170M [00:00<00:02, 50.2MB/s]
27%|##7 | 46.3M/170M [00:00<00:02, 53.8MB/s]
33%|###2 | 56.0M/170M [00:01<00:01, 60.0MB/s]
38%|###7 | 64.0M/170M [00:01<00:01, 65.8MB/s]
46%|####6 | 78.9M/170M [00:01<00:01, 89.4MB/s]
52%|#####1 | 88.2M/170M [00:01<00:00, 86.1MB/s]
59%|#####9 | 101M/170M [00:01<00:00, 97.6MB/s]
65%|######5 | 110M/170M [00:01<00:00, 95.0MB/s]
71%|####### | 120M/170M [00:01<00:00, 93.0MB/s]
76%|#######6 | 129M/170M [00:01<00:00, 87.6MB/s]
83%|########3 | 142M/170M [00:01<00:00, 99.7MB/s]
89%|########9 | 152M/170M [00:02<00:00, 92.4MB/s]
95%|#########4| 161M/170M [00:02<00:00, 87.9MB/s]
100%|##########| 170M/170M [00:02<00:00, 78.3MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
7%|7 | 12.1M/170M [00:00<00:01, 125MB/s]
14%|#4 | 24.0M/170M [00:00<00:01, 97.5MB/s]
20%|#9 | 33.6M/170M [00:00<00:01, 94.4MB/s]
25%|##5 | 42.8M/170M [00:00<00:01, 90.6MB/s]
33%|###2 | 56.0M/170M [00:00<00:01, 103MB/s]
39%|###8 | 66.0M/170M [00:00<00:01, 103MB/s]
45%|####4 | 75.8M/170M [00:00<00:01, 77.9MB/s]
52%|#####1 | 88.0M/170M [00:01<00:00, 88.4MB/s]
62%|######1 | 105M/170M [00:01<00:00, 112MB/s]
69%|######8 | 117M/170M [00:01<00:00, 94.8MB/s]
79%|#######8 | 134M/170M [00:01<00:00, 115MB/s]
86%|########5 | 146M/170M [00:01<00:00, 104MB/s]
93%|#########2| 158M/170M [00:01<00:00, 109MB/s]
100%|#########9| 169M/170M [00:01<00:00, 106MB/s]
100%|##########| 170M/170M [00:01<00:00, 101MB/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 9.677 seconds)
+ **Total running time of the script:** ( 3 minutes 20.927 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 352df2a6e8..5b4d76f399 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, 64.5MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 53.3MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
97%|#########7| 13.2M/13.6M [00:00<00:00, 130MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 131MB/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)
- 90.0153 89.9739 90.6402 89.7660 0.1737
+ 90.4064 90.3095 94.8287 90.0603 0.5013
@@ -471,7 +471,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.113 seconds)
+ **Total running time of the script:** ( 1 minutes 7.814 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 7e440e11a0..a7b378f1f9 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)
- 119.5602 119.4898 123.0814 118.2387 0.8463
+ 120.8371 120.7579 122.1898 119.9457 0.4836
@@ -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 22.167 seconds)
+ **Total running time of the script:** ( 2 minutes 24.915 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 76997b661f..223b0a4dd5 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 22.317 seconds)
+ **Total running time of the script:** ( 1 minutes 29.536 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 190ecc5065..b5e6343577 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%|3 | 5273/132723 [00:00<00:02, 51040.74KB/s]
10%|# | 13569/132723 [00:00<00:01, 69558.31KB/s]
17%|#6 | 22177/132723 [00:00<00:01, 77044.94KB/s]
23%|##2 | 30111/132723 [00:00<00:01, 77943.88KB/s]
29%|##9 | 38625/132723 [00:00<00:01, 80525.95KB/s]
36%|###5 | 47234/132723 [00:00<00:01, 82411.57KB/s]
42%|####1 | 55598/132723 [00:00<00:00, 82808.99KB/s]
48%|####8 | 64233/132723 [00:00<00:00, 83932.31KB/s]
55%|#####4 | 72825/132723 [00:00<00:00, 84547.38KB/s]
61%|######1 | 81473/132723 [00:01<00:00, 85141.86KB/s]
68%|######7 | 90037/132723 [00:01<00:00, 85290.67KB/s]
74%|#######4 | 98673/132723 [00:01<00:00, 85614.60KB/s]
81%|######## | 107285/132723 [00:01<00:00, 85764.35KB/s]
87%|########7 | 115961/132723 [00:01<00:00, 86060.78KB/s]
94%|#########3| 124568/132723 [00:01<00:00, 86052.83KB/s]
100%|########
##| 132723/132723 [00:01<00:00, 82915.56KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|3 | 5256/132723 [00:00<00:02, 52552.41KB/s]
9%|9 | 12533/132723 [00:00<00:01, 64440.28KB/s]
15%|#5 | 19933/132723 [00:00<00:01, 68800.47KB/s]
21%|## | 27211/132723 [00:00<00:01, 70368.59KB/s]
26%|##6 | 34657/132723 [00:00<00:01, 71839.88KB/s]
32%|###1 | 42066/132723 [00:00<00:01, 72602.64KB/s]
37%|###7 | 49451/132723 [00:00<00:01, 73007.75KB/s]
43%|####2 | 56957/132723 [00:00<00:01, 73658.77KB/s]
49%|####8 | 64401/132723 [00:00<00:00, 73900.85KB/s]
54%|#####4 | 72334/132723 [00:01<00:00, 75574.73KB/s]
60%|###### | 80142/132723 [00:01<00:00, 76339.21KB/s]
66%|######6 | 87996/132723 [00:01<00:00, 77002.88KB/s]
72%|#######2 | 95844/132723 [00:01<00:00, 77419.30KB/s]
78%|#######8 | 103714/132723 [00:01<00:00, 77802.16KB/s]
84%|########4 | 111803/132723 [00:01<00:00, 78731.50KB/s]
90%|#########
| 119967/132723 [00:01<00:00, 79605.66KB/s]
97%|#########6| 128141/132723 [00:01<00:00, 80244.56KB/s]
100%|##########| 132723/132723 [00:01<00:00, 75547.13KB/s]
@@ -246,7 +246,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 3.426 seconds)
+ **Total running time of the script:** ( 3 minutes 11.845 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 1d4188e445..8e7e71313c 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
=================
-**13:18.971** total execution time for **how_to_deploy_models** files:
+**13:56.524** 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``) | 03:09.677 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:20.927 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:03.426 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:11.845 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:22.167 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:24.915 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:22.317 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:29.536 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:05.113 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:07.814 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:52.721 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:53.657 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:34.760 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:37.121 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:24.498 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.539 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.285 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.163 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 44763ff1b0..dafb6f55e4 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.zipd7bc48a8-3164-4aaf-b97c-466db0e5f4e7 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip8f52a413-ff8f-44e9-9f93-db41fca75762 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 2a5e3a7139..6f5739e423 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
=================
-**00:47.012** total execution time for **how_to_extend_tvm** files:
+**00:49.105** 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``) | 00:43.653 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:45.513 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.349 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.520 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.003 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.064 | 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 |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 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 b020e8f8ef..8d7b25ff15 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: 7188us [7188us] (46.52%; 46.52%)
- FoldScaleAxis: 8263us [7us] (53.48%; 53.48%)
- FoldConstant: 8257us [1680us] (53.44%; 99.92%)
- InferType: 6576us [6576us] (42.56%; 79.65%)
+ InferType: 7480us [7480us] (46.51%; 46.51%)
+ FoldScaleAxis: 8601us [8us] (53.49%; 53.49%)
+ FoldConstant: 8594us [1743us] (53.44%; 99.91%)
+ InferType: 6851us [6851us] (42.60%; 79.72%)
@@ -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: 6674us [6674us] (45.26%; 45.26%)
- FoldScaleAxis: 8071us [4us] (54.74%; 54.74%)
- FoldConstant: 8066us [1651us] (54.71%; 99.94%)
- InferType: 6415us [6415us] (43.51%; 79.53%)
+ InferType: 7037us [7037us] (45.02%; 45.02%)
+ FoldScaleAxis: 8595us [6us] (54.98%; 54.98%)
+ FoldConstant: 8589us [1767us] (54.94%; 99.92%)
+ InferType: 6821us [6821us] (43.63%; 79.42%)
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 7e2bee2999..b128878ba2 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: 54.261760 ms
+ Convolution: 40.648704 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 21079bb04d..d70647eed4 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: 12.508758 ms
+ conv2d with tensor core: 13.364697 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 61a3c90f71..a488b6e79d 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: 0.017815
- Baseline: 3.430320
+ Numpy running time: 0.018833
+ Baseline: 3.266789
@@ -242,7 +242,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.296640
+ Opt1: 0.319605
@@ -344,7 +344,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.325978
+ Opt2: 0.351155
@@ -439,7 +439,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.114212
+ Opt3: 0.118612
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109902
+ Opt4: 0.110010
@@ -684,7 +684,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111817
+ Opt5: 0.111043
@@ -808,7 +808,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.144713
+ Opt6: 0.147301
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 dd2c18204f..ecef886fb3 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.520** total execution time for **how_to_optimize_operators** files:
+**00:34.978** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.991 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.418 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.479 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.498 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.049 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.062 | 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 6eaa5c06ff..fadb3f636e 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
=================
-**08:57.180** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:01.605** 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``) | 05:32.419 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:32.783 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:31.133 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:34.030 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:00.966 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:02.989 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:29.831 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:27.717 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.812 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.486 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.018 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.601 | 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 1f63d3ba7f..7bcbcb7826 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
@@ -243,487 +243,203 @@ 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" = 32;
- allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), 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" = 196 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=16)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 256;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [2]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [144]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [2], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
- for (rc.outer.outer: int32, 0, 8) {
- for (rx.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*3136)
- let cse_var_1: int32 = (rc.outer.outer*576)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (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 + (floordiv(threadIdx.x_1, 63)*49)) + rx.outer.outer) + floormod(threadIdx.x_1, 63)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 1), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 1), 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 + 196), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 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" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 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 + 392), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 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" = 196;
- 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" = 196;
- 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" = 196;
- 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" = 196;
- 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" = 196;
- 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" = 196;
- 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" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else(((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (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, 63)*49)) + rx.outer.outer) + floormod(threadIdx.x_1, 63)) + 1364)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 1), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 1), 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 + 1960), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 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" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 2156)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 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 + 2156), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 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" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @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 + 2352), 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" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 2548)] = @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 + 2548), 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" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 2744)] = @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 + 2744), 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" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 2940)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2940), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3136), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 3332)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3332), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 3528)] = @tir.if_then_else(((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (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, 63)*49)) + rx.outer.outer) + floormod(threadIdx.x_1, 63)) + 2736)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 3724)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 1), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 1), 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 + 3724), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 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" = 196;
- if @tir.likely((threadIdx.x_1 < 112), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 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 + 3920), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[(threadIdx.x_2*4)] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_1) + (floordiv((floormod(threadIdx.x_2, 48)*4), 3)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- kernel.shared_1[((threadIdx.x_2*4) + 1)] = kernel_3[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 48)*4) + 1), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- kernel.shared_1[((threadIdx.x_2*4) + 2)] = kernel_3[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 48)*4) + 2), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- kernel.shared_1[((threadIdx.x_2*4) + 3)] = kernel_3[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*4), 3) + 1), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*4) + 784)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 48)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*4) + 16), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- kernel.shared_1[((threadIdx.x_2*4) + 785)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 48)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*4) + 17), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- kernel.shared_1[((threadIdx.x_2*4) + 786)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 48)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*4), 3) + 6), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- kernel.shared_1[((threadIdx.x_2*4) + 787)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 48)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*4) + 784), 3) + 1), 64)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*4) + 1568)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 48)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*4) + 32), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- kernel.shared_1[((threadIdx.x_2*4) + 1569)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 48)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*4), 3) + 11), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- kernel.shared_1[((threadIdx.x_2*4) + 1570)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 48)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*4) + 34), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- kernel.shared_1[((threadIdx.x_2*4) + 1571)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 48)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*4) + 1568), 3) + 1), 64)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- if @tir.likely((threadIdx.x_2 < 180), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*4) + 2352)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 588), 48)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*4), 3) + 16), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- }
- if @tir.likely((threadIdx.x_2 < 180), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*4) + 2353)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 588), 48)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*4) + 49), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- }
- if @tir.likely((threadIdx.x_2 < 180), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*4) + 2354)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 588), 48)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*4) + 50), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- }
- if @tir.likely((threadIdx.x_2 < 180), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*4) + 2355)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 588), 48)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*4), 3) + 17), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- }
- }
- for (rc.outer.inner: int32, 0, 2) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*2016) + floormod(threadIdx.x, 49))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rc.outer.inner*2016) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 192)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rc.outer.inner*2016) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 384)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rc.outer.inner*2016) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 576)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 195)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 387)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 579)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 198)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 390)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 582)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 201)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 393)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 585)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 204)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 396)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 588)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 207)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 399)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 591)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 210)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 402)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 594)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 213)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 405)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 597)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 216)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 408)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 600)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 219)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 411)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 603)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 222)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 414)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 606)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 33)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 225)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 417)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 609)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 36)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 228)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 420)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 612)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 39)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 231)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 423)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 615)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 42)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 234)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 426)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 618)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 45)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 237)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 429)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 621)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 240)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 432)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 624)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 51)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 243)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 435)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 627)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 54)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 246)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 438)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 630)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 57)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 249)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 441)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 633)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 60)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 252)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 444)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 636)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 63)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 255)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 447)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 639)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 66)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 258)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 450)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 642)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 69)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 261)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 453)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 645)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 72)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 264)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 456)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 648)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 75)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 267)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 459)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 651)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 78)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 270)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 462)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 654)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 81)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 273)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 465)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 657)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 84)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 276)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 468)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 660)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 87)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 279)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 471)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 663)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 90)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 282)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 474)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 666)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 93)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 285)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 477)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 669)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 193)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 385)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 577)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 196)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 388)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 580)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 199)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 391)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 583)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 202)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 394)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 586)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 205)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 397)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 589)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 208)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 400)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 592)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 211)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 403)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 595)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 214)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 406)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 598)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 25)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 217)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 409)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 601)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 220)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 412)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 604)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 31)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 223)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 415)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 607)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 34)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 226)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 418)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 610)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 37)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 229)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 421)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 613)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 40)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 232)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 424)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 616)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 43)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 235)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 427)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 619)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 46)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 238)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 430)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 622)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 49)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 241)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 433)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 625)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 52)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 244)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 436)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 628)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 55)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 247)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 439)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 631)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 58)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 250)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 442)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 634)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 61)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 253)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 445)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 637)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 64)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 256)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 448)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 640)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 67)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 259)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 451)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 643)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 70)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 262)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 454)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 646)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 73)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 265)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 457)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 649)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 76)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 268)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 460)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 652)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 79)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 271)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 463)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 655)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 82)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 274)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 466)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 658)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 85)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 277)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 469)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 661)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 88)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 280)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 472)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 664)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 91)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 283)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 475)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 667)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 94)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 286)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 478)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 670)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 194)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 386)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 578)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 197)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 389)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 581)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 200)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 392)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 584)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 203)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 395)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 587)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 206)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 398)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 590)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 209)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 401)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 593)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 212)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 404)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 596)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 215)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 407)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 599)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 26)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 218)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 410)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 602)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 221)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 413)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 605)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 32)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 224)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 416)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 608)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 35)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 227)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 419)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 611)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 38)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 230)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 422)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 614)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 41)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 233)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 425)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 617)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 44)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 236)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 428)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 620)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 47)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 239)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 431)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 623)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1022)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 50)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1022)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 242)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1022)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 434)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1022)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 626)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1085)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 53)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1085)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 245)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1085)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 437)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1085)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 629)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1148)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 56)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1148)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 248)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1148)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 440)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1148)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 632)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1211)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 59)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1211)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 251)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1211)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 443)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1211)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 635)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1274)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 62)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1274)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 254)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1274)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 446)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1274)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 638)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1337)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 65)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1337)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 257)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1337)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 449)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1337)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 641)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1400)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 68)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1400)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 260)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1400)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 452)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1400)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 644)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1463)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 71)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1463)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 263)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1463)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 455)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1463)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 647)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1526)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 74)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1526)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 266)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1526)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 458)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1526)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 650)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1589)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 77)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1589)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 269)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1589)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 461)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1589)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 653)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1652)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 80)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1652)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 272)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1652)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 464)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1652)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 656)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1715)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 83)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1715)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 275)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1715)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 467)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1715)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 659)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1778)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 86)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1778)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 278)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1778)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 470)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1778)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 662)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1841)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 89)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1841)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 281)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1841)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 473)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1841)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 665)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1904)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 92)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1904)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 284)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1904)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 476)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1904)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 668)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1967)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 95)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1967)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 287)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1967)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 479)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1967)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 671)]))
- }
+ for (rc.outer.outer: int32, 0, 64) {
+ let cse_var_2: int32 = (rc.outer.outer*392)
+ let cse_var_1: int32 = (rc.outer.outer*72)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[(((cse_var_2 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 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(((((9 <= floormod((threadIdx.x_1 + 49), 81)) && (floormod((threadIdx.x_1 + 49), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 49), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 49), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 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((threadIdx.x_1 + 8), 9)) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 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(((((9 <= floormod((threadIdx.x_1 + 66), 81)) && (floormod((threadIdx.x_1 + 66), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 147), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 66), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 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(((((9 <= floormod((threadIdx.x_1 + 34), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 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((((9 <= floormod((threadIdx.x_1 + 2), 81)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 245), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 2), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 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(((((9 <= floormod((threadIdx.x_1 + 51), 81)) && (floormod((threadIdx.x_1 + 51), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 294), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 51), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 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((threadIdx.x_1 + 1), 9)) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 343), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 19), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 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(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 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(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 4), 9)) && (floormod((threadIdx.x_1 + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 441), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 4), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 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((((9 <= floormod((threadIdx.x_1 + 4), 81)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 490), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 4), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 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(((((9 <= floormod((threadIdx.x_1 + 53), 81)) && (floormod((threadIdx.x_1 + 53), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 539), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 53), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 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((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 588), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 21), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ if @tir.likely((threadIdx.x_1 < 11), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 637)] = @tir.if_then_else((((threadIdx.x_1 < 2) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 637), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 70), 81), 9)*7)) + (threadIdx.x_1 + 7)) - 8)], 0f32, dtype=float32)
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1: Buffer(kernel.shared, float32, [144], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((blockIdx.x*9216) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 49)] = kernel_3[(((((blockIdx.x*9216) + (floordiv((threadIdx.x_2 + 49), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 49), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ if @tir.likely((threadIdx.x_2 < 46), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 98)] = kernel_3[(((((blockIdx.x*9216) + (floordiv((threadIdx.x_2 + 98), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 26), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[0]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[72]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[9]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[81]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[18]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[90]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[27]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[99]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[36]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[108]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[45]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[117]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[54]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[126]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[63]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[135]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[1]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[73]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[10]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[82]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[19]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[91]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[28]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[100]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[37]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[109]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[46]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[118]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[55]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[127]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[64]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[136]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[2]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[74]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[11]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[83]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[20]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[92]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[29]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[101]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[38]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[110]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[47]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[119]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[56]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[128]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[65]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[137]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[3]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[75]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[12]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[84]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[21]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[93]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[30]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[102]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[39]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[111]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[48]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[120]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[57]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[129]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[66]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[138]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[4]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[76]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[13]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[85]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[22]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[94]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[31]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[103]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[40]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[112]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[49]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[121]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[58]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[130]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[67]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[139]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[5]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[77]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[14]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[86]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[23]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[95]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[32]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[104]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[41]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[113]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[50]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[122]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[59]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[131]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[68]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[140]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[6]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[78]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[15]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[87]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[24]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[96]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[33]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[105]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[42]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[114]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[51]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[123]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[60]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[132]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[69]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[141]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[7]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[79]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[16]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[88]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[25]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[97]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[34]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[106]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[43]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[115]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[52]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[124]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[61]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[133]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[70]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[142]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[8]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[80]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[17]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[89]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[26]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[98]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[35]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[107]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[44]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[116]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[53]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[125]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[62]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[134]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[71]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[143]))
}
}
- for (i1.inner: int32, 0, 4) {
- compute_3: Buffer(compute_2, float32, [25088], [])[((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[(((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ compute_3: Buffer(compute_2, float32, [25088], [])[(((blockIdx.x*98) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*2) + i1.inner)]), 0f32)
}
}
}
@@ -778,7 +494,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.395 ms
+ Execution time of this operator: 0.310 ms
@@ -826,9 +542,9 @@ 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=4)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
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=4)
+ 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=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
@@ -838,18 +554,18 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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=32)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
+ 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_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=4)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
+ 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=1)
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)
@@ -873,16 +589,16 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
+ 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=196)
+ 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)
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=196)
+ 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)
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", 512)
+ 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:
@@ -900,455 +616,183 @@ 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__(196) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[4];
- __shared__ float pad_temp_shared[4032];
- __shared__ float kernel_shared[3072];
+ 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[2];
+ __shared__ float pad_temp_shared[648];
+ __shared__ float kernel_shared[144];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
- for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((1 <= (((((int)threadIdx.x) / 7) + 1) % 9)) && ((((((int)threadIdx.x) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 196) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 1) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 392) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 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 * 3136) + (((((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) + 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 * 3136) + (((((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) + 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 * 3136) + (((((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) + 1176)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1176) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1372) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1764)] = (((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) + 1364)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((1 <= (((((int)threadIdx.x) / 7) + 1) % 9)) && ((((((int)threadIdx.x) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1960) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 1) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2156)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2156) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((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 * 3136) + (((((int)threadIdx.x) + 2352) / 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) + 2548)] = (((((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 * 3136) + (((((int)threadIdx.x) + 2548) / 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) + 2744)] = (((((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 * 3136) + (((((int)threadIdx.x) + 2744) / 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) + 2940)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2940) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3332)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3332) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3528)] = (((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) + 2736)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3724)] = (((((1 <= (((((int)threadIdx.x) / 7) + 1) % 9)) && ((((((int)threadIdx.x) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3724) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 1) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 112) {
- pad_temp_shared[(((int)threadIdx.x) + 3920)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[(((int)threadIdx.x) * 4)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 48) * 4) / 3) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 1)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 48) * 4) + 1) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 2)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 48) * 4) + 2) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 3)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 1) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 784)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 16) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 785)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 17) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 786)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 6) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 787)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 784) / 3) + 1) & 63) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 1568)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 32) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 1569)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 11) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 1570)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 34) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 1571)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 1568) / 3) + 1) & 63) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- if (((int)threadIdx.x) < 180) {
- kernel_shared[((((int)threadIdx.x) * 4) + 2352)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 16) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- }
- if (((int)threadIdx.x) < 180) {
- kernel_shared[((((int)threadIdx.x) * 4) + 2353)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 49) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- }
- if (((int)threadIdx.x) < 180) {
- kernel_shared[((((int)threadIdx.x) * 4) + 2354)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 50) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- }
- if (((int)threadIdx.x) < 180) {
- kernel_shared[((((int)threadIdx.x) * 4) + 2355)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 17) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 192)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 384)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 576)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 195)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 387)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 579)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 198)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 390)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 582)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 201)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 393)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 585)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 204)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 396)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 588)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 207)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 399)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 591)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 210)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 402)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 594)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 213)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 405)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 597)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 216)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 408)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 600)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 219)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 411)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 603)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 222)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 414)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 606)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 33)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 225)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 417)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 609)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 228)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 420)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 612)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 39)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 231)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 423)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 615)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 42)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 234)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 426)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 618)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 45)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 237)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 429)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 621)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 240)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 432)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 624)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 51)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 243)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 435)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 627)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 54)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 246)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 438)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 630)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 57)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 249)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 441)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 633)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 60)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 252)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 444)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 636)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 63)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 255)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 447)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 639)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 66)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 258)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 450)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 642)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 69)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 261)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 453)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 645)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 72)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 264)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 456)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 648)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 75)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 267)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 459)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 651)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 78)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 270)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 462)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 654)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 81)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 273)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 465)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 657)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 84)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 276)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 468)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 660)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 87)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 279)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 471)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 663)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 90)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 282)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 474)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 666)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 93)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 285)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 477)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 669)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 193)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 385)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 577)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 196)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 388)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 580)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 199)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 391)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 583)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 202)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 394)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 586)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 205)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 397)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 589)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 208)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 400)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 592)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 211)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 403)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 595)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 214)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 406)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 598)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 25)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 217)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 409)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 601)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 220)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 412)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 604)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 31)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 223)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 415)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 607)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 34)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 226)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 418)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 610)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 37)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 229)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 421)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 613)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 40)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 232)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 424)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 616)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 43)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 235)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 427)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 619)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 46)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 238)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 430)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 622)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 49)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 241)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 433)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 625)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 52)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 244)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 436)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 628)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 55)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 247)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 439)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 631)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 58)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 250)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 442)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 634)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 61)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 253)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 445)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 637)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 64)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 256)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 448)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 640)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 67)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 259)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 451)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 643)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 70)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 262)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 454)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 646)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 73)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 265)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 457)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 649)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 76)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 268)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 460)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 652)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 79)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 271)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 463)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 655)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 82)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 274)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 466)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 658)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 85)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 277)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 469)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 661)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 88)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 280)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 472)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 664)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 91)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 283)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 475)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 667)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 94)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 286)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 478)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 670)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 194)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 386)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 578)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 197)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 389)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 581)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 200)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 392)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 584)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 203)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 395)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 587)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 206)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 398)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 590)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 209)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 401)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 593)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 212)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 404)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 596)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 215)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 407)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 599)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 26)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 218)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 410)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 602)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 221)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 413)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 605)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 32)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 224)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 416)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 608)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 35)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 227)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 419)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 611)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 38)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 230)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 422)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 614)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 41)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 233)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 425)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 617)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 44)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 236)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 428)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 620)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 47)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 239)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 431)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 623)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1022)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 50)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1022)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 242)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1022)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 434)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1022)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 626)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1085)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 53)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1085)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 245)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1085)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 437)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1085)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 629)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1148)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 56)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1148)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 248)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1148)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 440)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1148)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 632)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1211)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 59)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1211)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 251)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1211)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 443)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1211)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 635)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1274)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 62)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1274)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 254)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1274)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 446)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1274)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 638)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1337)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 65)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1337)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 257)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1337)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 449)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1337)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 641)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1400)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 68)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1400)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 260)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1400)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 452)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1400)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 644)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1463)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 71)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1463)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 263)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1463)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 455)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1463)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 647)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1526)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 74)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1526)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 266)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1526)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 458)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1526)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 650)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1589)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 77)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1589)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 269)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1589)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 461)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1589)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 653)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1652)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 80)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1652)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 272)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1652)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 464)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1652)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 656)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1715)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 83)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1715)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 275)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1715)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 467)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1715)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 659)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1778)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 86)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1778)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 278)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1778)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 470)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1778)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 662)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1841)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 89)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1841)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 281)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1841)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 473)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1841)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 665)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1904)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 92)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1904)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 284)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1904)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 476)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1904)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 668)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1967)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 95)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1967)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 287)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1967)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 479)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1967)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 671)]));
- }
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 49) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 98) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((9 <= ((((int)threadIdx.x) + 66) % 81)) && (((((int)threadIdx.x) + 66) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 147) / 81) * 49)) + ((((((int)threadIdx.x) + 66) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 245)] = ((((7 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 245) / 81) * 49)) + (((((int)threadIdx.x) + 2) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((9 <= ((((int)threadIdx.x) + 51) % 81)) && (((((int)threadIdx.x) + 51) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 294) / 81) * 49)) + ((((((int)threadIdx.x) + 51) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 343)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 343) / 81) * 49)) + (((((int)threadIdx.x) + 19) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 441)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 441) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = ((((5 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 490) / 81) * 49)) + (((((int)threadIdx.x) + 4) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 539)] = (((((9 <= ((((int)threadIdx.x) + 53) % 81)) && (((((int)threadIdx.x) + 53) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 539) / 81) * 49)) + ((((((int)threadIdx.x) + 53) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 588) / 81) * 49)) + (((((int)threadIdx.x) + 21) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 11) {
+ pad_temp_shared[(((int)threadIdx.x) + 637)] = ((((((int)threadIdx.x) < 2) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 637) / 81) * 49)) + (((((int)threadIdx.x) + 70) / 9) * 7)) + ((int)threadIdx.x)) - 1)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 9216) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 49)] = kernel[(((((((int)blockIdx.x) * 9216) + (((((int)threadIdx.x) + 49) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 49) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 46) {
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 9216) + (((((int)threadIdx.x) + 98) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 26) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
}
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[0]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[72]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[9]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[81]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[18]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[90]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[27]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[99]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[36]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[108]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[45]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[117]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[54]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[126]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[63]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[135]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[1]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[73]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[10]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[82]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[19]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[91]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[28]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[100]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[37]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[109]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[46]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[118]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[55]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[127]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[64]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[136]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[2]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[74]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[11]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[83]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[20]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[92]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[29]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[101]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[38]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[110]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[47]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[119]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[56]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[128]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[65]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[137]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[3]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[75]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[12]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[84]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[21]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[93]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[30]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[102]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[39]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[111]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[48]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[120]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[57]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[129]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[66]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[138]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[4]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[76]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[13]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[85]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[22]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[94]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[31]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[103]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[40]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[112]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[49]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[121]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[58]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[130]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[67]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[139]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[5]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[77]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[14]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[86]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[23]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[95]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[32]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[104]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[41]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[113]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[50]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[122]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[59]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[131]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[68]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[140]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[6]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[78]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[15]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[87]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[24]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[96]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[33]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[105]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[42]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[114]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[51]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[123]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[60]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[132]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[69]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[141]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[7]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[79]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[16]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[88]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[25]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[97]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[34]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[106]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[43]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[115]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[52]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[124]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[61]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[133]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[70]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[142]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[8]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[80]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[17]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[89]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[26]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[98]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[35]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[107]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[44]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[116]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[53]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[125]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[62]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[134]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[71]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[143]));
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ compute[(((((int)blockIdx.x) * 98) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 2) + i1_inner)]), 0.000000e+00f);
}
}
@@ -1410,7 +854,7 @@ 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 32.419 seconds)
+ **Total running time of the script:** ( 5 minutes 32.783 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 6dcabb2b82..39690df6c4 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)
- 7.8911 7.8917 7.9009 7.8808 0.0082
+ 7.8503 7.8550 7.8621 7.8339 0.0120
@@ -675,7 +675,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.966 seconds)
+ **Total running time of the script:** ( 1 minutes 2.989 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 86f292d24e..ad7281c20d 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)
- 753.4300 753.6220 754.8865 751.7814 1.2749
+ 766.1723 766.5858 766.7852 765.1459 0.7303
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 31.133 seconds)
+ **Total running time of the script:** ( 1 minutes 34.030 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 b10230bd71..b2d5a484cf 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
@@ -390,29 +390,105 @@ 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, 32) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
+ for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [256]), storage_scope = global {
for (i.outer.inner: int32, 0, 2) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 32) {
- for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [2048], [])[((((i.outer.inner*1024) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
- }
+ for (i.inner.init: int32, 0, 8) {
+ let cse_var_1: int32 = ((i.outer.inner*128) + (i.inner.init*16))
+ {
+ compute_4: Buffer(compute_3, float32, [256], [])[cse_var_1] = 0f32
+ compute_4[(cse_var_1 + 1)] = 0f32
+ compute_4[(cse_var_1 + 2)] = 0f32
+ compute_4[(cse_var_1 + 3)] = 0f32
+ compute_4[(cse_var_1 + 4)] = 0f32
+ compute_4[(cse_var_1 + 5)] = 0f32
+ compute_4[(cse_var_1 + 6)] = 0f32
+ compute_4[(cse_var_1 + 7)] = 0f32
+ compute_4[(cse_var_1 + 8)] = 0f32
+ compute_4[(cse_var_1 + 9)] = 0f32
+ compute_4[(cse_var_1 + 10)] = 0f32
+ compute_4[(cse_var_1 + 11)] = 0f32
+ compute_4[(cse_var_1 + 12)] = 0f32
+ compute_4[(cse_var_1 + 13)] = 0f32
+ compute_4[(cse_var_1 + 14)] = 0f32
+ compute_4[(cse_var_1 + 15)] = 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, 32) {
- 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*1024) + (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*8192)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ for (elem_idx: int32, 0, let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
+ for (i.inner: int32, 0, 8) {
+ let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ {
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_4: int32 = ((i.outer.inner*128) + (i.inner*16))
+ compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_3]*16) + (elem_idx*16))]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_5: int32 = (((i.outer.inner*128) + (i.inner*16)) + 1)
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_6: int32 = (((i.outer.inner*128) + (i.inner*16)) + 2)
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_7: int32 = (((i.outer.inner*128) + (i.inner*16)) + 3)
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_8: int32 = (((i.outer.inner*128) + (i.inner*16)) + 4)
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_9: int32 = (((i.outer.inner*128) + (i.inner*16)) + 5)
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_10: int32 = (((i.outer.inner*128) + (i.inner*16)) + 6)
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_11: int32 = (((i.outer.inner*128) + (i.inner*16)) + 7)
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_12: int32 = (((i.outer.inner*128) + (i.inner*16)) + 8)
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_13: int32 = (((i.outer.inner*128) + (i.inner*16)) + 9)
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_14: int32 = (((i.outer.inner*128) + (i.inner*16)) + 10)
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_15: int32 = (((i.outer.inner*128) + (i.inner*16)) + 11)
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_16: int32 = (((i.outer.inner*128) + (i.inner*16)) + 12)
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_17: int32 = (((i.outer.inner*128) + (i.inner*16)) + 13)
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_18: int32 = (((i.outer.inner*128) + (i.inner*16)) + 14)
+ compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_19: int32 = (((i.outer.inner*128) + (i.inner*16)) + 15)
+ compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
}
- 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))
+ for (i0.inner: int32, 0, 16) {
+ let cse_var_20: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_20, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_20, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -468,7 +544,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.639 ms
+ Execution time of this operator: 1.856 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 4d4bfddc2f..bb4ab10587 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
@@ -5,10 +5,10 @@
Computation times
=================
-**00:36.878** total execution time for **how_to_tune_with_autotvm** files:
+**00:38.348** 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``) | 00:36.842 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:38.313 | 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 |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 d92ebb4e91..7f6f67d5b8 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
@@ -391,130 +391,25 @@ 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, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4128236
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5096885
No: 2 GFLOPS: 0.00/0.00 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 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h: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
-
- 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, 8, 32, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8620573
+ 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, 4, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2453102
No: 3 GFLOPS: 0.00/0.00 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)
@@ -637,8 +532,9 @@ 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, 2, 1, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,518091
- 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, 1, 4, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6675415
+ No: 4 GFLOPS: 26.60/26.60 result: MeasureResult(costs=(0.008702390928571429,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.851181983947754, timestamp=1673306729.197973) [('tile_f', [-1, 2, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,429496
+ No: 5 GFLOPS: 0.00/26.60 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 +656,9 @@ 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, 1, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4785952
- 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, 64, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2413653
+ No: 6 GFLOPS: 296.27/296.27 result: MeasureResult(costs=(0.0007813849285714285,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.329486608505249, timestamp=1673306732.481104) [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,145674
+ No: 7 GFLOPS: 0.00/296.27 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 +780,8 @@ 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, 256, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6804443
- 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, 4, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7127002
+ No: 8 GFLOPS: 0.00/296.27 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
@@ -1006,8 +903,9 @@ 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, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6535872
- No: 7 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, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4547676
+ No: 9 GFLOPS: 266.22/296.27 result: MeasureResult(costs=(0.0008695816,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2021591663360596, timestamp=1673306734.1871915) [('tile_f', [-1, 16, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,11023
+ No: 10 GFLOPS: 0.00/296.27 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
@@ -1129,8 +1027,8 @@ 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, 16, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9805525
- No: 8 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, 1, 128, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,703475
+ No: 11 GFLOPS: 0.00/296.27 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
@@ -1252,9 +1150,10 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 128, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1106075
- No: 9 GFLOPS: 40.78/40.78 result: MeasureResult(costs=(0.005677435407407407,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.373302459716797, timestamp=1673305373.5163271) [('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9025300
- No: 10 GFLOPS: 0.00/40.78 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4541752
+ No: 12 GFLOPS: 7.69/296.27 result: MeasureResult(costs=(0.0300871675,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3995342254638672, timestamp=1673306734.9919019) [('tile_f', [-1, 8, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1235743
+ No: 13 GFLOPS: 27.54/296.27 result: MeasureResult(costs=(0.008405490833333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8662846088409424, timestamp=1673306737.0311227) [('tile_f', [-1, 8, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7941451
+ No: 14 GFLOPS: 0.00/296.27 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
@@ -1376,9 +1275,8 @@ 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, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8296123
- No: 11 GFLOPS: 2.67/40.78 result: MeasureResult(costs=(0.08682093025,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3896007537841797, timestamp=1673305375.0809305) [('tile_f', [-1, 8, 1, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3133428
- No: 12 GFLOPS: 0.00/40.78 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7479535
+ No: 15 GFLOPS: 0.00/296.27 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
@@ -1500,8 +1398,8 @@ 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, 2, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7155924
- No: 13 GFLOPS: 0.00/40.78 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7441023
+ No: 16 GFLOPS: 0.00/296.27 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
@@ -1623,8 +1521,9 @@ 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, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1599284
- No: 14 GFLOPS: 0.00/40.78 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9289788
+ No: 17 GFLOPS: 62.74/296.27 result: MeasureResult(costs=(0.0036897097857142855,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.279930591583252, timestamp=1673306738.52046) [('tile_f', [-1, 4, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6515769
+ No: 18 GFLOPS: 0.00/296.27 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
@@ -1746,163 +1645,8 @@ 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, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8324266
- No: 15 GFLOPS: 0.00/40.78 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)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 4: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc: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: 0x00007f126d019fa2
- 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
- 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
-
- 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, 128, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6510907
- No: 16 GFLOPS: 82.82/82.82 result: MeasureResult(costs=(0.002795111111111111,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2012507915496826, timestamp=1673305382.0745542) [('tile_f', [-1, 2, 64, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8178546
- No: 17 GFLOPS: 38.89/82.82 result: MeasureResult(costs=(0.005952071647058824,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7134439945220947, timestamp=1673305383.9521222) [('tile_f', [-1, 1, 64, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3165713
- No: 18 GFLOPS: 0.00/82.82 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,32809
+ No: 19 GFLOPS: 0.00/296.27 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 +1768,8 @@ 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, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7374171
- No: 19 GFLOPS: 0.00/82.82 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8221915
+ No: 20 GFLOPS: 0.00/296.27 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 +1891,7 @@ 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, 64, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4833665
- No: 20 GFLOPS: 0.98/82.82 result: MeasureResult(costs=(0.23723574825,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.420214653015137, timestamp=1673305387.4534936) [('tile_f', [-1, 128, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1256657
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3114492
@@ -2203,9 +1946,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 2, 64, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8178546
+ [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,145674
Finish loading 20 records
- Time cost of this operator: 0.003144
+ Time cost of this operator: 0.000784
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 580dd0c2ed..df8f30de8e 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 308.3 98.695 (1, 2, 10, 10, 3) 2 1 [308.3]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.114 0.997 (1, 6, 10, 10) 1 1 [3.114]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.961 0.308 (1, 1, 10, 10, 3) 1 1 [0.961]
- Total_time - 312.375 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.1 98.73 (1, 2, 10, 10, 3) 2 1 [313.1]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.036 0.957 (1, 6, 10, 10) 1 1 [3.036]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.992 0.313 (1, 1, 10, 10, 3) 1 1 [0.992]
+ Total_time - 317.128 - - - - -
@@ -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 100.3 97.353 (1, 6, 10, 10, 1) 2 1 [100.3]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.774 1.722 (1, 6, 10, 10) 1 1 [1.774]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.953 0.925 (1, 1, 10, 10, 3) 1 1 [0.953]
- Total_time - 103.028 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 134.3 97.915 (1, 6, 10, 10, 1) 2 1 [134.3]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.872 1.365 (1, 6, 10, 10) 1 1 [1.872]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.988 0.72 (1, 1, 10, 10, 3) 1 1 [0.988]
+ Total_time - 137.159 - - - - -
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 3682c131b5..ca890cac5b 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]
61%|###### | 2.09M/3.42M [00:00<00:00, 16.9MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 26.7MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
61%|###### | 2.09M/3.42M [00:00<00:00, 21.6MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 33.5MB/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 2.393 seconds)
+ **Total running time of the script:** ( 1 minutes 6.083 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 4b5630c14d..076cf71118 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/tmpcymbw0hi/images/random'
+ '/tmp/tmpv54taz41/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], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0]
+ :alt: [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0]
: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/tmpcymbw0hi/images/target contains 8144 images
- /tmp/tmpcymbw0hi/images/random contains 5000 images
+ /tmp/tmpv54taz41/images/target contains 8144 images
+ /tmp/tmpv54taz41/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: 0.2139 - accuracy: 0.9272 - val_loss: 0.1431 - val_accuracy: 0.9577 - 47s/epoch - 143ms/step
+ 328/328 - 47s - loss: 0.2265 - accuracy: 0.9215 - val_loss: 0.1252 - val_accuracy: 0.9558 - 47s/epoch - 144ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.1014 - accuracy: 0.9647 - val_loss: 0.1398 - val_accuracy: 0.9558 - 43s/epoch - 132ms/step
+ 328/328 - 43s - loss: 0.0978 - accuracy: 0.9650 - val_loss: 0.1251 - val_accuracy: 0.9581 - 43s/epoch - 133ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0645 - accuracy: 0.9771 - val_loss: 0.1135 - val_accuracy: 0.9649 - 43s/epoch - 132ms/step
+ 328/328 - 43s - loss: 0.0618 - accuracy: 0.9784 - val_loss: 0.1156 - val_accuracy: 0.9641 - 43s/epoch - 132ms/step
- <keras.callbacks.History object at 0x7f59d167f450>
+ <keras.callbacks.History object at 0x7feb1bdb0390>
@@ -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 21.479 seconds)
+ **Total running time of the script:** ( 4 minutes 23.785 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 7ed01b302c..d15c9204a3 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
=================
-**06:26.227** total execution time for **how_to_work_with_microtvm** files:
+**06:35.389** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:21.479 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:23.785 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:02.393 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:06.083 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:50.795 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:53.118 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.844 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.460 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.715 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.941 | 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 735bdcfb9e..c0efea631b 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
=================
-**00:44.065** total execution time for **how_to_work_with_relay** files:
+**00:44.956** 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``) | 00:32.202 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.970 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.154 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.306 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.703 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.672 | 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 5e0bd636b0..81ec354110 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 0x7f5a605200e0>
+ <function my_cuda_math_rule at 0x7feb1d28add0>
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 d525bcb618..6692517345 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
=================
-**00:07.000** total execution time for **how_to_work_with_schedules** files:
+**00:07.648** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.533 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.072 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.127 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.212 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.571 | 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_scan.py` (``scan.py``) | 00:00.555 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.564 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.113 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.115 | 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_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.050 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.028 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_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 |
+------------------------------------------------------------------------------------------------+-----------+--------+
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 e56697ee96..70a64cfdbd 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/tmpdx6bwzwc/input0.cc'\nsource_filename = \"/tmp/tmpdx6bwzwc/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/tmpd5et8hg8/input0.cc'\nsource_filename = \"/tmp/tmpd5et8hg8/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 b6e96b98a2..41aa6e6dcc 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
=================
-**00:25.827** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:27.176** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:25.820 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:27.169 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index a071174f61..b4f93e3465 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 28.37s!
+ resnet18_v1 inference graph built in 30.05s!
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 aa753d92f5..8dbfdb5e54 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 19.36s!
+ yolov3-tiny inference graph built in 20.46s!
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 61d30800e9..8ba975f3dd 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
=================
-**01:31.369** total execution time for **topic_vta_tutorials_frontend** files:
+**01:34.301** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:46.192 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:47.336 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:45.177 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:46.965 | 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 6575046d8c..c2ab6f514c 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
=================
-**00:03.175** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.209** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.719 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.742 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.455 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.466 | 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 eb801d6fc5..0816682ef8 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:00.790** total execution time for **topic_vta_tutorials** files:
+**00:00.813** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.419 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.436 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.371 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.377 | 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 239302fc38..8d6038ffef 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: 95.116 ms
+ Execution time of this operator: 95.338 ms
@@ -429,7 +429,7 @@ resume the status and do more 5 trials.
Resume search:
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
-
+ *E
@@ -447,7 +447,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 18.024 seconds)
+ **Total running time of the script:** ( 1 minutes 23.160 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 b4164ac3fe..6e8c25d6d2 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: 9.44/9.44 result: MeasureResult(costs=(0.028435561399999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7167747020721436, timestamp=1673303997.0058396) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
- No: 2 GFLOPS: 3.93/9.44 result: MeasureResult(costs=(0.068270972,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3535549640655518, timestamp=1673303998.3494003) [('tile_y', [-1, 32]), ('tile_x', [-1, 16])],None,45
- No: 3 GFLOPS: 12.35/12.35 result: MeasureResult(costs=(0.021736787,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5946812629699707, timestamp=1673303999.7041836) [('tile_y', [-1, 256]), ('tile_x', [-1, 256])],None,88
- No: 4 GFLOPS: 13.11/13.11 result: MeasureResult(costs=(0.020472513,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5724074840545654, timestamp=1673304000.2958043) [('tile_y', [-1, 4]), ('tile_x', [-1, 512])],None,92
- No: 5 GFLOPS: 1.62/13.11 result: MeasureResult(costs=(0.1658812922,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.883044481277466, timestamp=1673304003.3141713) [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
- No: 6 GFLOPS: 2.98/13.11 result: MeasureResult(costs=(0.0900853952,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6897482872009277, timestamp=1673304005.7602015) [('tile_y', [-1, 2]), ('tile_x', [-1, 16])],None,41
- No: 7 GFLOPS: 12.75/13.11 result: MeasureResult(costs=(0.0210565292,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5880179405212402, timestamp=1673304007.1084647) [('tile_y', [-1, 4]), ('tile_x', [-1, 256])],None,82
- No: 8 GFLOPS: 9.35/13.11 result: MeasureResult(costs=(0.028719933800000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6814696788787842, timestamp=1673304007.8179402) [('tile_y', [-1, 512]), ('tile_x', [-1, 32])],None,59
- No: 9 GFLOPS: 13.03/13.11 result: MeasureResult(costs=(0.020595084800000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5730547904968262, timestamp=1673304008.5058267) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
- No: 10 GFLOPS: 3.62/13.11 result: MeasureResult(costs=(0.0740535816,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.417675495147705, timestamp=1673304009.93929) [('tile_y', [-1, 16]), ('tile_x', [-1, 8])],None,34
+ No: 1 GFLOPS: 3.67/3.67 result: MeasureResult(costs=(0.0731285002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4283857345581055, timestamp=1673305284.870477) [('tile_y', [-1, 128]), ('tile_x', [-1, 16])],None,47
+ No: 2 GFLOPS: 12.60/12.60 result: MeasureResult(costs=(0.0213032298,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5622830390930176, timestamp=1673305285.467958) [('tile_y', [-1, 32]), ('tile_x', [-1, 512])],None,95
+ No: 3 GFLOPS: 3.02/12.60 result: MeasureResult(costs=(0.08885599620000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.665698528289795, timestamp=1673305287.9366994) [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
+ No: 4 GFLOPS: 2.30/12.60 result: MeasureResult(costs=(0.11681319539999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1048202514648438, timestamp=1673305290.849265) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
+ No: 5 GFLOPS: 9.77/12.60 result: MeasureResult(costs=(0.0274856304,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6682958602905273, timestamp=1673305291.7050538) [('tile_y', [-1, 512]), ('tile_x', [-1, 32])],None,59
+ No: 6 GFLOPS: 11.75/12.60 result: MeasureResult(costs=(0.022842706,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6717691421508789, timestamp=1673305293.127947) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 7 GFLOPS: 2.81/12.60 result: MeasureResult(costs=(0.0956754392,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7731642723083496, timestamp=1673305294.9126585) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 8 GFLOPS: 12.48/12.60 result: MeasureResult(costs=(0.021505332000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6068389415740967, timestamp=1673305295.5176377) [('tile_y', [-1, 128]), ('tile_x', [-1, 256])],None,87
+ No: 9 GFLOPS: 14.32/14.32 result: MeasureResult(costs=(0.0187473114,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5644233226776123, timestamp=1673305296.1951587) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
+ No: 10 GFLOPS: 3.79/14.32 result: MeasureResult(costs=(0.0708275778,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3460514545440674, timestamp=1673305297.580324) [('tile_y', [-1, 4]), ('tile_x', [-1, 16])],None,42
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 8402f0c240..4678d7a8e2 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': 510.13883835999985, 'median': 509.9613637999994, 'std': 1.3041026659245931}
+ {'mean': 516.4660860999993, 'median': 515.8854889500049, 'std': 2.283769529546039}
@@ -558,31 +558,30 @@ 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: 12.68/ 22.54 GFLOPS | Progress: (4/20) | 6.87 s
[Task 1/25] Current/Best: 15.64/ 22.54 GFLOPS | Progress: (8/20) | 14.31 s
[Task 1/25] Current/Best: 12.43/ 23.53 GFLOPS | Progress: (12/20) | 17.61 s
[Task 1/25] Current/Best: 8.52/ 23.53 GFLOPS | Progress: (16/20) | 20.61 s
[Task 1/25] Current/Best: 22.66/ 23.53 GFLOPS | Progress: (20/20) | 23.40 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 17.08/ 17.35 GFLOPS | Progress: (4/20) | 3.29 s
[Task 2/25] Current/Best: 11.83/ 17.69 GFLOPS | Progress: (8/20) | 6.13 s
[Task 2/25] Current/Best: 5.56/ 19.96 GFLOPS | Progress: (12/20) | 7.79 s
[Task 2/25] Current/Best: 17.47/ 19.96 GFLOPS | Progress: (16/20) | 9.26 s
[Task 2/25] Current/Best: 17.59/ 19.96 GFLOPS | Progress: (20/20) | 10.93 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 11.54/ 22.13 GFLOPS | Progress: (4/20) | 4.18 s
[Task 3/25] Current/Best: 15.05/ 22.13 GFLOPS | Progress: (8/20) | 6.56 s
[Task 3/25] Current/Best: 13.97/ 22.13 GFLOPS | Progress: (12/20) | 8.99 s
[Task 3/25] Current/Best: 8.64/ 23.84 GFLOPS | Progress: (16/20) | 11.58 s
[Task 3/25] Current/Best: 6.42/ 23.84 GFLOPS | Progress: (20/20) | 14.35 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.83/ 20.78 GFLOPS | Progress: (4/20) | 5.11 s
[Task 4/25] Current/Best: 13.63/ 20.78 GFLOPS | Progress: (8/20) | 10.18 s
[Task 4/25] Current/Best: 16.72/ 20.78 GFLOPS | Progress: (12/20) | 12.39 s
[Task 4/25] Current/Best: 10.98/ 20.78 GFLOPS | Progress: (16/20) | 16.60 s
[Task 4/25] Current/Best: 3.13/ 20.78 GFLOPS | Progress: (20/20) | 19.60 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 5.64/ 15.42 GFLOPS | Progress: (4/20) | 4.32 s
[Task 5/25] Current/Best: 8.66/ 20.02 GFLOPS | Progress: (8/20) | 6.02 s
[Task 5/25] Current/Best: 15.11/ 20.41 GFLOPS | Progress: (12/20) | 7.77 s
[Task 5/25] Current/Best: 15.73/ 20.41 GFLOPS | Progress: (16/20) | 10.09 s
[Task 5/25] Current/Best: 18.09/ 20.41 GFLOPS | Progress: (20/20) | 11.93 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 8.94/ 17.56 GFLOPS | Progress: (4/20) | 5.51 s
[Task 6/25] Current/Best: 8.90/ 17.56 GFLOPS | Progress: (8/20) | 7.89 s
[Task 6/25] Current/Best: 10.15/ 17.56 GFLOPS | Progress: (12/20) | 14.50 s
[Task 6/25] Current/Best: 13.17/ 17.56 GFLOPS | Progress: (16/20) | 17.32 s
[Task 6/25] Current/Best: 9.62/ 21.23 GFLOPS | Progress: (20/20) | 19.60 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 7.63/ 20.15 GFLOPS | Progress: (4/20) | 4.81 s
[Task 7/25] Current/Best: 8.30/ 20.15 GFLOPS | Progress: (8/20) | 7.39 s
[Task 7/25] Current/Best: 15.91/ 20.15 GFLOPS | Progress: (12/20) | 10.12 s
[Task 7/25] Current/Best: 12.72/ 20.15 GFLOPS | Progress: (16/20) | 12.36 s
[Task 7/25] Current/Best: 15.46/ 20.15 GFLOPS | Progress: (20/20) | 14.77 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.59/ 13.36 GFLOPS | Progress: (4/20) | 5.44 s
[Task 8/25] Current/Best: 13.36/ 13.36 GFLOPS | Progress: (8/20) | 8.16 s
[Task 8/25] Current/Best: 7.65/ 20.39 GFLOPS | Progress: (12/20) | 10.62 s
[Task 8/25] Current/Best: 12.80/ 20.39 GFLOPS | Progress: (16/20) | 15.06 s
[Task 8/25] Current/Best: 10.36/ 20.39 GFLOPS | Progress: (20/20) | 20.87 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 10.63/ 19.88 GFLOPS | Progress: (4/20) | 4.46 s
[Task 9/25] Current/Best: 16.76/ 22.70 GFLOPS | Progress: (8/20) | 6.07 s
[Task 9/25] Current/Best: 13.26/ 22.70 GFLOPS | Progress: (12/20) | 8.26 s
[Task 9/25] Current/Best: 1.93/ 22.70 GFLOPS | Progress: (16/20) | 15.64 s
[Task 9/25] Current/Best: 7.84/ 22.70 GFLOPS | Progress: (20/20) | 24.22 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 12.36/ 17.95 GFLOPS | Progress: (4/20) | 3.51 s
[Task 10/25] Current/Best: 9.95/ 17.95 GFLOPS | Progress: (8/20) | 5.61 s
[Task 10/25] Current/Best: 9.22/ 17.95 GFLOPS | Progress: (12/20) | 7.46 s
[Task 10/25] Current/Best: 14.24/ 20.45 GFLOPS | Progress: (16/20) | 9.42 s
[Task 10/25] Current/Best: 4.72/ 21.68 GFLOPS | Progress: (20/20) | 11.20 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/ 14.60 GFLOPS | Progress: (4/20) | 4.98 s
[Task 11/25] Current/Best: 17.06/ 20.86 GFLOPS | Progress: (8/20) | 7.52 s
[Task 11/25] Current/Best: 15.93/ 20.86 GFLOPS | Progress: (12/20) | 9.51 s
[Task 11/25] Current/Best: 12.39/ 20.86 GFLOPS | Progress: (16/20) | 13.71 s
[Task 11/25] Current/Best: 19.57/ 20.86 GFLOPS | Progress: (20/20) | 15.85 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 13.86/ 13.86 GFLOPS | Progress: (4/20) | 8.40 s
[Task 12/25] Current/Best: 12.94/ 16.17 GFLOPS | Progress: (8/20) | 10.91 s
[Task 12/25] Current/Best: 10.06/ 16.17 GFLOPS | Progress: (12/20) | 14.45 s
[Task 12/25] Current/Best: 15.62/ 16.46 GFLOPS | Progress: (16/20) | 16.38 s
[Task 12/25] Current/Best: 16.60/ 18.63 GFLOPS | Progress: (20/20) | 19.27 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 17.53/ 18.98 GFLOPS | Progress: (4/20) | 4.30 s
[Task 13/25] Current/Best: 6.23/ 20.86 GFLOPS | Progress: (8/20) | 8.35 s
[Task 13/25] Current/Best: 8.69/ 20.86 GFLOPS | Progress: (12/20) | 10.76 s
[Task 13/25] Current/Best: 23.31/ 23.31 GFLOPS | Progress: (16/20) | 15.86 s
[Task 13/25] Current/Best: 6.51/ 23.31 GFLOPS | Progress: (20/20) | 19.42 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 9.54/ 18.12 GFLOPS | Progress: (4/20) | 5.44 s
[Task 14/25] Current/Best: 5.41/ 18.12 GFLOPS | Progress: (8/20) | 8.05 s
[Task 14/25] Current/Best: 12.45/ 18.12 GFLOPS | Progress: (12/20) | 11.34 s
[Task 14/25] Current/Best: 16.54/ 18.12 GFLOPS | Progress: (16/20) | 13.83 s
[Task 14/25] Current/Best: 12.44/ 18.12 GFLOPS | Progress: (20/20) | 16.09 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 6.91/ 22.14 GFLOPS | Progress: (4/20) | 4.10 s
[Task 15/25] Current/Best: 6.72/ 22.14 GFLOPS | Progress: (8/20) | 5.85 s
[Task 15/25] Current/Best: 10.96/ 22.14 GFLOPS | Progress: (12/20) | 12.00 s
[Task 15/25] Current/Best: 13.28/ 22.14 GFLOPS | Progress: (16/20) | 14.34 s
[Task 15/25] Current/Best: 16.18/ 22.14 GFLOPS | Progress: (20/20
) | 16.83 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
[Task 16/25] Current/Best: 15.56/ 15.93 GFLOPS | Progress: (4/20) | 3.95 s
[Task 16/25] Current/Best: 8.90/ 16.70 GFLOPS | Progress: (8/20) | 5.53 s
[Task 16/25] Current/Best: 14.98/ 16.70 GFLOPS | Progress: (12/20) | 7.50 s
[Task 16/25] Current/Best: 3.02/ 20.74 GFLOPS | Progress: (16/20) | 9.51 s
[Task 16/25] Current/Best: 14.99/ 20.74 GFLOPS | Progress: (20/20) | 11.56 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 17.56/ 20.79 GFLOPS | Progress: (4/20) | 3.81 s
[Task 17/25] Current/Best: 12.48/ 20.79 GFLOPS | Progress: (8/20) | 6.58 s
[Task 17/25] Current/Best: 20.08/ 20.79 GFLOPS | Progress: (12/20) | 8.79 s
[Task 17/25] Current/Best: 6.18/ 20.79 GFLOPS | Progress: (16/20) | 11.48 s
[Task 17/25] Current/Best: 12.30/ 20.79 GFLOPS | Progress: (20/20) | 16.02 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 18.74/ 18.74 GFLOPS | Progress: (4/20) | 4.44 s
[Task 18/25] Current/Best: 12.62/ 19.42 GFLOPS | Progress: (8/20) | 7.03 s
[Task 18/25] Current/Best: 10.47/ 19.42 GFLOPS | Progress: (12/20) | 9.98 s
[Task 18/25] Current/Best: 14.73/ 19.42 GFLOPS | Progress: (16/20) | 12.46 s
[Task 18/25] Current/Best: 19.46/ 19.46 GFLOPS | Progress: (20/20) | 14.90 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 21.92/ 21.92 GFLOPS | Progress: (4/20) | 4.48 s
[Task 19/25] Current/Best: 12.31/ 21.92 GFLOPS | Progress: (8/20) | 8.84 s
[Task 19/25] Current/Best: 16.71/ 21.92 GFLOPS | Progress: (12/20) | 11.31 s
[Task 19/25] Current/Best: 17.05/ 21.92 GFLOPS | Progress: (16/20) | 15.57 s
[Task 19/25] Current/Best: 10.49/ 21.92 GFLOPS | Progress: (20/20) | 20.69 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 10.23/ 15.16 GFLOPS | Progress: (4/20) | 4.09 s
[Task 20/25] Current/Best: 14.20/ 16.14 GFLOPS | Progress: (8/20) | 6.96 s
[Task 20/25] Current/Best: 10.00/ 17.30 GFLOPS | Progress: (12/20) | 8.84 s
[Task 20/25] Current/Best: 10.55/ 17.30 GFLOPS | Progress: (16/20) | 11.65 s
[Task 20/25] Current/Best: 14.06/ 18.03 GFLOPS | Progress: (20/20) | 14.55 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 2.72/ 16.79 GFLOPS | Progress: (4/20) | 4.11 s
[Task 21/25] Current/Best: 17.12/ 19.92 GFLOPS | Progress: (8/20) | 5.63 s
[Task 21/25] Current/Best: 7.47/ 19.92 GFLOPS | Progress: (12/20) | 8.18 s
[Task 21/25] Current/Best: 3.16/ 19.92 GFLOPS | Progress: (16/20) | 11.28 s
[Task 21/25] Current/Best: 12.48/ 19.92 GFLOPS | Progress: (20/20)
| 14.30 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
[Task 22/25] Current/Best: 5.17/ 11.12 GFLOPS | Progress: (4/20) | 4.89 s
[Task 22/25] Current/Best: 10.44/ 20.14 GFLOPS | Progress: (8/20) | 8.31 s
[Task 22/25] Current/Best: 17.07/ 20.14 GFLOPS | Progress: (12/20) | 9.95 s
[Task 22/25] Current/Best: 12.16/ 20.14 GFLOPS | Progress: (16/20) | 12.00 s
[Task 22/25] Current/Best: 16.04/ 20.14 GFLOPS | Progress: (20/20) | 13.59 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 10.64/ 12.22 GFLOPS | Progress: (4/20) | 6.01 s
[Task 23/25] Current/Best: 17.32/ 19.27 GFLOPS | Progress: (8/20) | 8.42 s
[Task 23/25] Current/Best: 15.23/ 20.51 GFLOPS | Progress: (12/20) | 10.99 s
[Task 23/25] Current/Best: 17.18/ 20.51 GFLOPS | Progress: (16/20) | 13.86 s
[Task 23/25] Current/Best: 11.48/ 20.51 GFLOPS | Progress: (20/20) | 17.80 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 3.35/ 10.15 GFLOPS | Progress: (4/20) | 3.73 s
[Task 24/25] Current/Best: 3.66/ 10.15 GFLOPS | Progress: (8/20) | 14.77 s
[Task 24/25] Current/Best: 2.97/ 10.15 GFLOPS | Progress: (12/20) | 26.43 s
[Task 24/25] Current/Best: 9.74/ 10.15 GFLOPS | Progress: (16/20) | 37.34 s
[Task 24/25] Current/Best: 4.10/ 10.15 GFLOPS | Progress: (20/20) | 48.27 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 5.85/ 5.85 GFLOPS | Progress: (4/20) | 12.45 s Done.
-
[Task 25/25] Current/Best: 5.80/ 9.31 GFLOPS | Progress: (8/20) | 24.56 s
[Task 25/25] Current/Best: 7.99/ 9.31 GFLOPS | Progress: (12/20) | 26.73 s
[Task 25/25] Current/Best: 3.04/ 9.92 GFLOPS | Progress: (16/20) | 37.39 s
[Task 25/25] Current/Best: 4.47/ 9.92 GFLOPS | Progress: (20/20) | 49.52 s
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 8.45/ 21.68 GFLOPS | Progress: (4/20) | 7.75 s
[Task 1/25] Current/Best: 13.08/ 23.23 GFLOPS | Progress: (8/20) | 11.15 s
[Task 1/25] Current/Best: 19.52/ 23.23 GFLOPS | Progress: (12/20) | 15.27 s
[Task 1/25] Current/Best: 14.52/ 23.23 GFLOPS | Progress: (16/20) | 17.58 s
[Task 1/25] Current/Best: 16.80/ 23.23 GFLOPS | Progress: (20/20) | 19.70 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 11.80/ 17.90 GFLOPS | Progress: (4/20) | 3.55 s
[Task 2/25] Current/Best: 15.92/ 18.54 GFLOPS | Progress: (8/20) | 5.14 s
[Task 2/25] Current/Best: 11.08/ 18.71 GFLOPS | Progress: (12/20) | 7.23 s
[Task 2/25] Current/Best: 14.55/ 18.71 GFLOPS | Progress: (16/20) | 9.57 s
[Task 2/25] Current/Best: 11.92/ 18.71 GFLOPS | Progress: (20/20) | 11.81 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 15.16/ 18.23 GFLOPS | Progress: (4/20) | 4.03 s
[Task 3/25] Current/Best: 13.20/ 18.23 GFLOPS | Progress: (8/20) | 6.48 s
[Task 3/25] Current/Best: 8.16/ 18.23 GFLOPS | Progress: (12/20) | 9.74 s
[Task 3/25] Current/Best: 8.10/ 19.17 GFLOPS | Progress: (16/20) | 12.46 s
[Task 3/25] Current/Best: 22.69/ 22.69 GFLOPS | Progress: (20/20) | 16.28 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 3.35/ 19.36 GFLOPS | Progress: (4/20) | 8.67 s
[Task 4/25] Current/Best: 6.39/ 19.98 GFLOPS | Progress: (8/20) | 11.05 s
[Task 4/25] Current/Best: 8.65/ 21.03 GFLOPS | Progress: (12/20) | 15.27 s
[Task 4/25] Current/Best: 6.50/ 21.03 GFLOPS | Progress: (16/20) | 18.19 s
[Task 4/25] Current/Best: 18.43/ 21.03 GFLOPS | Progress: (20/20) | 20.49 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 14.68/ 18.69 GFLOPS | Progress: (4/20) | 3.85 s
[Task 5/25] Current/Best: 6.15/ 18.69 GFLOPS | Progress: (8/20) | 5.91 s
[Task 5/25] Current/Best: 11.47/ 18.69 GFLOPS | Progress: (12/20) | 9.07 s
[Task 5/25] Current/Best: 7.54/ 18.69 GFLOPS | Progress: (16/20) | 11.77 s
[Task 5/25] Current/Best: 13.73/ 18.69 GFLOPS | Progress: (20/20) | 13.97 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 18.99/ 18.99 GFLOPS | Progress: (4/20) | 4.08 s
[Task 6/25] Current/Best: 10.64/ 18.99 GFLOPS | Progress: (8/20) | 9.01 s
[Task 6/25] Current/Best: 18.32/ 18.99 GFLOPS | Progress: (12/20) | 12.04 s
[Task 6/25] Current/Best: 16.29/ 18.99 GFLOPS | Progress: (16/20) | 14.18 s
[Task 6/25] Current/Best: 13.67/ 18.99 GFLOPS | Progress: (20/20) | 18.03 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 15.42/ 17.16 GFLOPS | Progress: (4/20) | 4.10 s
[Task 7/25] Current/Best: 7.81/ 17.16 GFLOPS | Progress: (8/20) | 6.54 s
[Task 7/25] Current/Best: 14.43/ 17.16 GFLOPS | Progress: (12/20) | 9.45 s
[Task 7/25] Current/Best: 12.06/ 17.16 GFLOPS | Progress: (16/20) | 12.04 s
[Task 7/25] Current/Best: 11.64/ 18.19 GFLOPS | Progress: (20/20) | 14.43 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 11.38/ 17.65 GFLOPS | Progress: (4/20) | 4.96 s
[Task 8/25] Current/Best: 7.41/ 17.65 GFLOPS | Progress: (8/20) | 11.26 s
[Task 8/25] Current/Best: 8.42/ 17.65 GFLOPS | Progress: (12/20) | 16.38 s
[Task 8/25] Current/Best: 5.35/ 17.98 GFLOPS | Progress: (16/20) | 18.97 s
[Task 8/25] Current/Best: 7.58/ 17.98 GFLOPS | Progress: (20/20) | 23.55 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 13.20/ 17.19 GFLOPS | Progress: (4/20) | 3.83 s
[Task 9/25] Current/Best: 17.28/ 17.28 GFLOPS | Progress: (8/20) | 5.84 s
[Task 9/25] Current/Best: 9.89/ 17.28 GFLOPS | Progress: (12/20) | 12.46 s
[Task 9/25] Current/Best: 6.18/ 17.49 GFLOPS | Progress: (16/20) | 16.87 s
[Task 9/25] Current/Best: 6.23/ 17.49 GFLOPS | Progress: (20/20) | 18.75 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 19.04/ 19.04 GFLOPS | Progress: (4/20) | 3.53 s
[Task 10/25] Current/Best: 6.07/ 19.04 GFLOPS | Progress: (8/20) | 5.56 s
[Task 10/25] Current/Best: 16.13/ 19.04 GFLOPS | Progress: (12/20) | 7.13 s
[Task 10/25] Current/Best: 12.00/ 19.04 GFLOPS | Progress: (16/20) | 9.86 s
[Task 10/25] Current/Best: 20.92/ 20.92 GFLOPS | Progress: (20/20) | 12.96 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 18.38/ 19.95 GFLOPS | Progress: (4/20) | 4.20 s
[Task 11/25] Current/Best: 6.84/ 19.95 GFLOPS | Progress: (8/20) | 7.45 s
[Task 11/25] Current/Best: 19.38/ 19.95 GFLOPS | Progress: (12/20) | 9.83 s
[Task 11/25] Current/Best: 19.83/ 20.72 GFLOPS | Progress: (16/20) | 12.39 s
[Task 11/25] Current/Best: 19.65/ 23.63 GFLOPS | Progress: (20/20) | 15.21 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 15.89/ 18.14 GFLOPS | Progress: (4/20) | 3.67 s
[Task 12/25] Current/Best: 20.00/ 20.84 GFLOPS | Progress: (8/20) | 6.04 s
[Task 12/25] Current/Best: 14.10/ 20.84 GFLOPS | Progress: (12/20) | 8.71 s
[Task 12/25] Current/Best: 3.01/ 20.84 GFLOPS | Progress: (16/20) | 11.43 s
[Task 12/25] Current/Best: 15.23/ 20.84 GFLOPS | Progress: (20/20) | 15.97 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 16.18/ 20.37 GFLOPS | Progress: (4/20) | 4.51 s
[Task 13/25] Current/Best: 18.51/ 20.37 GFLOPS | Progress: (8/20) | 8.37 s
[Task 13/25] Current/Best: 18.75/ 20.37 GFLOPS | Progress: (12/20) | 10.62 s
[Task 13/25] Current/Best: 10.12/ 20.37 GFLOPS | Progress: (16/20) | 14.05 s
[Task 13/25] Current/Best: 13.03/ 20.37 GFLOPS | Progress: (20/20) | 18.10 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 11.42/ 17.18 GFLOPS | Progress: (4/20) | 4.42 s
[Task 14/25] Current/Best: 12.26/ 17.18 GFLOPS | Progress: (8/20) | 7.60 s
[Task 14/25] Current/Best: 8.23/ 17.18 GFLOPS | Progress: (12/20) | 12.06 s
[Task 14/25] Current/Best: 12.52/ 17.18 GFLOPS | Progress: (16/20) | 14.83 s
[Task 14/25] Current/Best: 3.05/ 17.18 GFLOPS | Progress: (20/20) | 17.47 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 3.09/ 17.17 GFLOPS | Progress: (4/20) | 5.20 s
[Task 15/25] Current/Best: 10.88/ 20.01 GFLOPS | Progress: (8/20) | 8.42 s
[Task 15/25] Current/Best: 17.47/ 20.01 GFLOPS | Progress: (12/20) | 9.93 s
[Task 15/25] Current/Best: 23.40/ 23.40 GFLOPS | Progress: (16/20) | 12.70 s Done.
+
[Task 15/25] Current/Best: 14.46/ 23.40 GFLOPS | Progress: (20/20) | 15.25 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 7.48/ 20.30 GFLOPS | Progress: (4/20) | 4.94 s
[Task 16/25] Current/Best: 14.87/ 21.41 GFLOPS | Progress: (8/20) | 8.55 s
[Task 16/25] Current/Best: 4.53/ 21.41 GFLOPS | Progress: (12/20) | 10.34 s
[Task 16/25] Current/Best: 14.50/ 21.41 GFLOPS | Progress: (16/20) | 14.17 s
[Task 16/25] Current/Best: 16.71/ 21.41 GFLOPS | Progress: (20/20) | 15.79 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 14.25/ 19.01 GFLOPS | Progress: (4/20) | 4.26 s
[Task 17/25] Current/Best: 6.22/ 19.01 GFLOPS | Progress: (8/20) | 7.60 s
[Task 17/25] Current/Best: 19.21/ 19.21 GFLOPS | Progress: (12/20) | 10.32 s
[Task 17/25] Current/Best: 12.14/ 21.83 GFLOPS | Progress: (16/20) | 13.23 s
[Task 17/25] Current/Best: 19.73/ 21.83 GFLOPS | Progress: (20/20) | 18.45 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 10.75/ 16.52 GFLOPS | Progress: (4/20) | 6.59 s
[Task 18/25] Current/Best: 14.19/ 17.32 GFLOPS | Progress: (8/20) | 8.52 s
[Task 18/25] Current/Best: 17.25/ 20.94 GFLOPS | Progress: (12/20) | 10.32 s
[Task 18/25] Current/Best: 11.01/ 20.94 GFLOPS | Progress: (16/20) | 13.95 s
[Task 18/25] Current/Best: 3.08/ 20.94 GFLOPS | Progress: (20/20) | 21.93 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 5.97/ 19.06 GFLOPS | Progress: (4/20) | 5.04 s
[Task 19/25] Current/Best: 14.95/ 19.06 GFLOPS | Progress: (8/20) | 8.26 s
[Task 19/25] Current/Best: 12.02/ 19.06 GFLOPS | Progress: (12/20) | 11.01 s
[Task 19/25] Current/Best: 10.88/ 19.06 GFLOPS | Progress: (16/20) | 15.13 s
[Task 19/25] Current/Best: 12.02/ 19.62 GFLOPS | Progress: (20/20) | 18.74 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 17.90/ 17.90 GFLOPS | Progress: (4/20) | 4.52 s
[Task 20/25] Current/Best: 14.66/ 19.48 GFLOPS | Progress: (8/20) | 7.62 s
[Task 20/25] Current/Best: 10.90/ 19.48 GFLOPS | Progress: (12/20) | 10.71 s
[Task 20/25] Current/Best: 9.21/ 19.48 GFLOPS | Progress: (16/20) | 13.77 s
[Task 20/25] Current/Best: 13.99/ 19.48 GFLOPS | Progress: (20/20) | 16.12 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 19.61/ 21.03 GFLOPS | Progress: (4/20) | 4.45 s
[Task 21/25] Current/Best: 2.66/ 21.03 GFLOPS | Progress: (8/20) | 6.86 s Done.
+
[Task 21/25] Current/Best: 10.50/ 21.03 GFLOPS | Progress: (12/20) | 9.10 s
[Task 21/25] Current/Best: 17.50/ 21.03 GFLOPS | Progress: (16/20) | 11.57 s
[Task 21/25] Current/Best: 6.88/ 21.03 GFLOPS | Progress: (20/20) | 13.71 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 15.06/ 16.36 GFLOPS | Progress: (4/20) | 3.60 s
[Task 22/25] Current/Best: 8.61/ 16.36 GFLOPS | Progress: (8/20) | 5.48 s
[Task 22/25] Current/Best: 11.70/ 20.10 GFLOPS | Progress: (12/20) | 7.15 s
[Task 22/25] Current/Best: 5.26/ 20.26 GFLOPS | Progress: (16/20) | 9.32 s
[Task 22/25] Current/Best: 16.70/ 20.26 GFLOPS | Progress: (20/20) | 11.59 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 14.41/ 21.84 GFLOPS | Progress: (4/20) | 4.71 s
[Task 23/25] Current/Best: 11.99/ 21.84 GFLOPS | Progress: (8/20) | 10.21 s
[Task 23/25] Current/Best: 2.66/ 21.84 GFLOPS | Progress: (12/20) | 13.31 s
[Task 23/25] Current/Best: 12.84/ 21.84 GFLOPS | Progress: (16/20) | 15.61 s
[Task 23/25] Current/Best: 2.65/ 21.84 GFLOPS | Progress: (20/20) | 19.61 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 2.25/ 2.25 GFLOPS | Progress: (4/20) | 12.22 s
[Task 24/25] Current/Best: 3.83/ 3.83 GFLOPS | Progress: (8/20) | 23.82 s
[Task 24/25] Current/Best: 10.31/ 10.31 GFLOPS | Progress: (12/20) | 29.23 s
[Task 24/25] Current/Best: 1.83/ 10.31 GFLOPS | Progress: (16/20) | 40.22 s
[Task 24/25] Current/Best: 9.22/ 10.31 GFLOPS | Progress: (20/20) | 51.15 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 25/25] Current/Best: 5.88/ 8.52 GFLOPS | Progress: (4/20) | 4.00 s
[Task 25/25] Current/Best: 9.01/ 9.01 GFLOPS | Progress: (8/20) | 6.67 s
[Task 25/25] Current/Best: 1.55/ 9.01 GFLOPS | Progress: (12/20) | 17.36 s
[Task 25/25] Current/Best: 8.11/ 9.01 GFLOPS | Progress: (16/20) | 26.84 s
[Task 25/25] Current/Best: 3.01/ 9.01 GFLOPS | Progress: (20/20) | 28.53 s
@@ -678,9 +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=0.356378
- 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
@@ -736,8 +735,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 416.40479768999967, 'median': 416.08058430000483, 'std': 1.3672791966956093}
- unoptimized: {'mean': 510.13883835999985, 'median': 509.9613637999994, 'std': 1.3041026659245931}
+ optimized: {'mean': 410.7700975800026, 'median': 409.9779158500155, 'std': 2.762561622757324}
+ unoptimized: {'mean': 516.4660860999993, 'median': 515.8854889500049, 'std': 2.283769529546039}
@@ -760,7 +759,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 11 minutes 26.734 seconds)
+ **Total running time of the script:** ( 11 minutes 18.858 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 086b7f6d99..426451bd52 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
- 1.286e-07 secs/op
+ 1.302e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 9ac6dbde9d..4b2d720008 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, 0x147150f0)), stage(b, placeholder(b, 0xd6f5700)), 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, 0x21e04570)), stage(b, placeholder(b, 0x21a130c0)), 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(mi [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index a82d74b25d..4201ae37ed 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
Computation times
=================
-**14:39.345** total execution time for **tutorial** files:
+**14:36.616** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:26.734 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:18.858 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:18.024 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:23.160 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.240 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.325 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.170 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:34.327 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:17.750 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:18.457 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.457 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.464 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.811 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.832 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.151 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.181 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 0701b451b4..910158a6a4 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -397,7 +397,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000007
+ parallel: 0.000008
@@ -503,10 +503,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.796779998443526e-06 1.0
- naive 6.7245e-06 0.8624714306857977
- parallel 7.0376999999999996e-06 0.9026418600248998
- vector 2.4567000000000004e-05 3.1509161480642423
+ numpy 7.506630001898884e-06 1.0
+ naive 6.9496e-06 0.92579493038048
+ parallel 8.158300000000001e-06 1.0868125907279658
+ vector 2.45937e-05 3.276263781987224
@@ -927,7 +927,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.017594
+ Numpy running time: 0.018913
@@ -985,7 +985,7 @@ optimizations.
.. code-block:: none
- none: 3.443148
+ none: 3.238174
@@ -1087,7 +1087,7 @@ schedule.
.. code-block:: none
- blocking: 0.302409
+ blocking: 0.317989
@@ -1182,7 +1182,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.335296
+ vectorization: 0.346038
@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: 0.113586
+ loop permutation: 0.123627
@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: 0.108001
+ array packing: 0.109439
@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: 0.110090
+ block caching: 0.111450
@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: 0.144855
+ parallelization: 0.147422
@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 3.4431479605 1.0
- blocking 0.3024088619 0.08782917997403905
- vectorization 0.3352960906 0.09738068025148407
- loop permutation 0.11358641379999998 0.032989117837243745
- array packing 0.10800138470000001 0.031367047230905665
- block caching 0.1100898034 0.03197359063942556
- parallelization 0.1448550779 0.042070535324588466
+ none 3.2381738225 1.0
+ blocking 0.3179892204 0.0982001701670541
+ vectorization 0.3460377255 0.10686199829533703
+ loop permutation 0.12362662089999998 0.03817788286749699
+ array packing 0.1094389359 0.03379649824218169
+ block caching 0.11144999250000001 0.034417544767240495
+ parallelization 0.1474216597 0.04552617239867148
@@ -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 1.240 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index b34c77a03f..cad5785435 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-d2ee4ec97e31dfd4ce2c952230ec0b03feea3c73
+687ec7883be48c4e371d565d50ed2f29fec755f5
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index d9e29b2b51..4f4d1993b6 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 8.507 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.716 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 cbdce2a81e..5a8d7dda86 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 941ms/step
+1/1 [==============================] - 1s 975ms/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 9642117d5b..fdeb122c30 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.zipef3d8b0c-9315-48ac-b8aa-2cc5c899a199 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.zip0832fa66-0b78-448f-8ad0-117c59271f16 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 57d5ff0b51..eb20e382f6 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -449,12 +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, 64.4MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:00, 48.4MB/s]
- 54%|#####3 | 22.3M/41.5M [00:00<00:00, 56.4MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 63.9MB/s]
- 92%|#########2| 38.3M/41.5M [00:00<00:00, 62.8MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 58.9MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 55.7MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 60.2MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 55.8MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 53.0MB/s]
+ 92%|#########2| 38.3M/41.5M [00:00<00:00, 53.3MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 55.4MB/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 a36917784c..44a26bbb3c 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -432,11 +432,10 @@ 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]
- 23%|##2 | 10.1M/44.7M [00:00<00:00, 102MB/s]
- 44%|####4 | 19.8M/44.7M [00:00<00:00, 102MB/s]
- 72%|#######1 | 32.0M/44.7M [00:00<00:00, 107MB/s]
- 98%|#########8| 43.9M/44.7M [00:00<00:00, 114MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 110MB/s]
+ 27%|##7 | 12.2M/44.7M [00:00<00:00, 128MB/s]
+ 55%|#####4 | 24.4M/44.7M [00:00<00:00, 108MB/s]
+ 78%|#######8 | 34.9M/44.7M [00:00<00:00, 106MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 86.3MB/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 c19a493f9b..67757a3484 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 10.327 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 14.098 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 ec20a32b66..f8d9d6d8f2 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>05:35.495</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:48.487</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>01:10.327</p></td>
+<td><p>01:14.098</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>01:08.507</p></td>
+<td><p>01:10.716</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>00:45.111</p></td>
+<td><p>00:47.436</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>00:31.720</p></td>
+<td><p>00:33.202</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>00:28.460</p></td>
+<td><p>00:29.301</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>00:25.887</p></td>
+<td><p>00:26.975</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>00:25.261</p></td>
+<td><p>00:25.142</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>00:21.492</p></td>
+<td><p>00:22.418</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>00:16.331</p></td>
+<td><p>00:16.747</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>00:02.399</p></td>
+<td><p>00:02.451</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 d01fc309c6..e311ca7463 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)
- 2684.0773 2684.0619 2686.3851 2681.6193 1.5952
+ 2687.9779 2686.1206 2702.8615 2682.0912 5.8631
</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 1eeb587c36..4f592c585c 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)
- 15.7012 15.5594 16.5362 15.4742 0.3134
+ 16.4942 16.4020 17.2558 16.2129 0.2964
</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 62a6f98710..a634a24dae 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -454,24 +454,21 @@ 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<00:03, 49.8MB/s]
- 9%|9 | 16.0M/170M [00:00<00:03, 51.2MB/s]
- 14%|#4 | 24.0M/170M [00:00<00:02, 56.0MB/s]
- 19%|#8 | 32.0M/170M [00:00<00:03, 41.4MB/s]
- 24%|##3 | 40.0M/170M [00:00<00:02, 50.2MB/s]
- 27%|##7 | 46.3M/170M [00:00<00:02, 53.8MB/s]
- 33%|###2 | 56.0M/170M [00:01<00:01, 60.0MB/s]
- 38%|###7 | 64.0M/170M [00:01<00:01, 65.8MB/s]
- 46%|####6 | 78.9M/170M [00:01<00:01, 89.4MB/s]
- 52%|#####1 | 88.2M/170M [00:01<00:00, 86.1MB/s]
- 59%|#####9 | 101M/170M [00:01<00:00, 97.6MB/s]
- 65%|######5 | 110M/170M [00:01<00:00, 95.0MB/s]
- 71%|####### | 120M/170M [00:01<00:00, 93.0MB/s]
- 76%|#######6 | 129M/170M [00:01<00:00, 87.6MB/s]
- 83%|########3 | 142M/170M [00:01<00:00, 99.7MB/s]
- 89%|########9 | 152M/170M [00:02<00:00, 92.4MB/s]
- 95%|#########4| 161M/170M [00:02<00:00, 87.9MB/s]
-100%|##########| 170M/170M [00:02<00:00, 78.3MB/s]
+ 7%|7 | 12.1M/170M [00:00<00:01, 125MB/s]
+ 14%|#4 | 24.0M/170M [00:00<00:01, 97.5MB/s]
+ 20%|#9 | 33.6M/170M [00:00<00:01, 94.4MB/s]
+ 25%|##5 | 42.8M/170M [00:00<00:01, 90.6MB/s]
+ 33%|###2 | 56.0M/170M [00:00<00:01, 103MB/s]
+ 39%|###8 | 66.0M/170M [00:00<00:01, 103MB/s]
+ 45%|####4 | 75.8M/170M [00:00<00:01, 77.9MB/s]
+ 52%|#####1 | 88.0M/170M [00:01<00:00, 88.4MB/s]
+ 62%|######1 | 105M/170M [00:01<00:00, 112MB/s]
+ 69%|######8 | 117M/170M [00:01<00:00, 94.8MB/s]
+ 79%|#######8 | 134M/170M [00:01<00:00, 115MB/s]
+ 86%|########5 | 146M/170M [00:01<00:00, 104MB/s]
+ 93%|#########2| 158M/170M [00:01<00:00, 109MB/s]
+100%|#########9| 169M/170M [00:01<00:00, 106MB/s]
+100%|##########| 170M/170M [00:01<00:00, 101MB/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=& [...]
@@ -569,7 +566,7 @@ 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 9.677 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 20.927 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 1fd9661ce0..f1ed9dfb28 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, 64.5MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 53.3MB/s]
+ 97%|#########7| 13.2M/13.6M [00:00<00:00, 130MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 131MB/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)
- 90.0153 89.9739 90.6402 89.7660 0.1737
+ 90.4064 90.3095 94.8287 90.0603 0.5013
</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 5.113 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.814 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 5287a6e0cc..7a96631b42 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)
- 119.5602 119.4898 123.0814 118.2387 0.8463
+ 120.8371 120.7579 122.1898 119.9457 0.4836
</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 22.167 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 24.915 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 3eb14e1f57..b3e707682a 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 22.317 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 29.536 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 748afe0917..43dda6ebf2 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -463,22 +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%|3 | 5273/132723 [00:00<00:02, 51040.74KB/s]
- 10%|# | 13569/132723 [00:00<00:01, 69558.31KB/s]
- 17%|#6 | 22177/132723 [00:00<00:01, 77044.94KB/s]
- 23%|##2 | 30111/132723 [00:00<00:01, 77943.88KB/s]
- 29%|##9 | 38625/132723 [00:00<00:01, 80525.95KB/s]
- 36%|###5 | 47234/132723 [00:00<00:01, 82411.57KB/s]
- 42%|####1 | 55598/132723 [00:00<00:00, 82808.99KB/s]
- 48%|####8 | 64233/132723 [00:00<00:00, 83932.31KB/s]
- 55%|#####4 | 72825/132723 [00:00<00:00, 84547.38KB/s]
- 61%|######1 | 81473/132723 [00:01<00:00, 85141.86KB/s]
- 68%|######7 | 90037/132723 [00:01<00:00, 85290.67KB/s]
- 74%|#######4 | 98673/132723 [00:01<00:00, 85614.60KB/s]
- 81%|######## | 107285/132723 [00:01<00:00, 85764.35KB/s]
- 87%|########7 | 115961/132723 [00:01<00:00, 86060.78KB/s]
- 94%|#########3| 124568/132723 [00:01<00:00, 86052.83KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 82915.56KB/s]
+ 4%|3 | 5256/132723 [00:00<00:02, 52552.41KB/s]
+ 9%|9 | 12533/132723 [00:00<00:01, 64440.28KB/s]
+ 15%|#5 | 19933/132723 [00:00<00:01, 68800.47KB/s]
+ 21%|## | 27211/132723 [00:00<00:01, 70368.59KB/s]
+ 26%|##6 | 34657/132723 [00:00<00:01, 71839.88KB/s]
+ 32%|###1 | 42066/132723 [00:00<00:01, 72602.64KB/s]
+ 37%|###7 | 49451/132723 [00:00<00:01, 73007.75KB/s]
+ 43%|####2 | 56957/132723 [00:00<00:01, 73658.77KB/s]
+ 49%|####8 | 64401/132723 [00:00<00:00, 73900.85KB/s]
+ 54%|#####4 | 72334/132723 [00:01<00:00, 75574.73KB/s]
+ 60%|###### | 80142/132723 [00:01<00:00, 76339.21KB/s]
+ 66%|######6 | 87996/132723 [00:01<00:00, 77002.88KB/s]
+ 72%|#######2 | 95844/132723 [00:01<00:00, 77419.30KB/s]
+ 78%|#######8 | 103714/132723 [00:01<00:00, 77802.16KB/s]
+ 84%|########4 | 111803/132723 [00:01<00:00, 78731.50KB/s]
+ 90%|######### | 119967/132723 [00:01<00:00, 79605.66KB/s]
+ 97%|#########6| 128141/132723 [00:01<00:00, 80244.56KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 75547.13KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -517,7 +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 3.426 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 11.845 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 322fc14fd2..aee1b521e2 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>13:18.971</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>13:56.524</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>03:09.677</p></td>
+<td><p>03:20.927</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>03:03.426</p></td>
+<td><p>03:11.845</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>02:22.167</p></td>
+<td><p>02:24.915</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>01:22.317</p></td>
+<td><p>01:29.536</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>01:05.113</p></td>
+<td><p>01:07.814</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>00:52.721</p></td>
+<td><p>00:53.657</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>00:34.760</p></td>
+<td><p>00:37.121</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>00:24.498</p></td>
+<td><p>00:25.539</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>00:24.285</p></td>
+<td><p>00:25.163</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>00:00.006</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 13eef3bb03..fa740699de 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.zipd7bc48a8-3164-4aaf-b97c-466db0e5f4e7 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.zip8f52a413-ff8f-44e9-9f93-db41fca75762 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 08abccbbb1..85f2e1bf14 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>00:47.012</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:49.105</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,19 +349,19 @@
</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>00:43.653</p></td>
+<td><p>00:45.513</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>00:02.349</p></td>
+<td><p>00:02.520</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>00:01.003</p></td>
+<td><p>00:01.064</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>
-<td><p>00:00.007</p></td>
+<td><p>00:00.008</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index d5ed673df1..4fd9d961c1 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: 7188us [7188us] (46.52%; 46.52%)
-FoldScaleAxis: 8263us [7us] (53.48%; 53.48%)
- FoldConstant: 8257us [1680us] (53.44%; 99.92%)
- InferType: 6576us [6576us] (42.56%; 79.65%)
+InferType: 7480us [7480us] (46.51%; 46.51%)
+FoldScaleAxis: 8601us [8us] (53.49%; 53.49%)
+ FoldConstant: 8594us [1743us] (53.44%; 99.91%)
+ InferType: 6851us [6851us] (42.60%; 79.72%)
</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: 6674us [6674us] (45.26%; 45.26%)
-FoldScaleAxis: 8071us [4us] (54.74%; 54.74%)
- FoldConstant: 8066us [1651us] (54.71%; 99.94%)
- InferType: 6415us [6415us] (43.51%; 79.53%)
+InferType: 7037us [7037us] (45.02%; 45.02%)
+FoldScaleAxis: 8595us [6us] (54.98%; 54.98%)
+ FoldConstant: 8589us [1767us] (54.94%; 99.92%)
+ InferType: 6821us [6821us] (43.63%; 79.42%)
</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 1d991a107b..10fce1b439 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: 54.261760 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 40.648704 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 0c01921851..49f40fc607 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: 12.508758 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.364697 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 f176716f5d..f32bf7dd1d 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: 0.017815
-Baseline: 3.430320
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018833
+Baseline: 3.266789
</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: 0.296640
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.319605
</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: 0.325978
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.351155
</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: 0.114212
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.118612
</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: 0.109902
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110010
</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: 0.111817
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111043
</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: 0.144713
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147301
</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 bb1bde2688..31ff7147af 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>00:34.520</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.978</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>00:31.991</p></td>
+<td><p>00:32.418</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>00:01.479</p></td>
+<td><p>00:01.498</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>00:01.049</p></td>
+<td><p>00:01.062</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 bfd3cf76ad..9bd4038add 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>08:57.180</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:01.605</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>05:32.419</p></td>
+<td><p>05:32.783</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>01:31.133</p></td>
+<td><p>01:34.030</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>01:00.966</p></td>
+<td><p>01:02.989</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>00:29.831</p></td>
+<td><p>00:27.717</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>00:11.812</p></td>
+<td><p>00:12.486</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>00:11.018</p></td>
+<td><p>00:11.601</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 89695936c1..ba62108536 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
@@ -504,487 +504,203 @@ 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" = 32;
- allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), 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" = 196 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=16)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 256;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [2]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [144]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [2], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
- for (rc.outer.outer: int32, 0, 8) {
- for (rx.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*3136)
- let cse_var_1: int32 = (rc.outer.outer*576)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (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 + (floordiv(threadIdx.x_1, 63)*49)) + rx.outer.outer) + floormod(thread [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 1), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 1), 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 + 196), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 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 + 392), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- 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" = 196;
- 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" = 196;
- 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" = 196;
- 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" = 196;
- 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" = 196;
- 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" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else(((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (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, 63)*49)) + rx.outer.outer) + floormod(threadIdx.x_1, 63)) + 1364)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 1), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 1), 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 + 1960), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 2156)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 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 + 2156), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @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 + 2352), 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" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 2548)] = @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 + 2548), 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" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 2744)] = @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 + 2744), 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" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 2940)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2940), 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" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3136), 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" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 3332)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3332), 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" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 3528)] = @tir.if_then_else(((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (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, 63)*49)) + rx.outer.outer) + floormod(threadIdx.x_1, 63)) + 2736)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 3724)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 1), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 1), 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 + 3724), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- if @tir.likely((threadIdx.x_1 < 112), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 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 + 3920), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(threadI [...]
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[(threadIdx.x_2*4)] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_1) + (floordiv((floormod(threadIdx.x_2, 48)*4), 3)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- kernel.shared_1[((threadIdx.x_2*4) + 1)] = kernel_3[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 48)*4) + 1), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- kernel.shared_1[((threadIdx.x_2*4) + 2)] = kernel_3[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 48)*4) + 2), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- kernel.shared_1[((threadIdx.x_2*4) + 3)] = kernel_3[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*4), 3) + 1), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*4) + 784)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 48)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*4) + 16), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- kernel.shared_1[((threadIdx.x_2*4) + 785)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 48)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*4) + 17), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- kernel.shared_1[((threadIdx.x_2*4) + 786)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 48)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*4), 3) + 6), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- kernel.shared_1[((threadIdx.x_2*4) + 787)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 48)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*4) + 784), 3) + 1), 64)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*4) + 1568)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 48)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*4) + 32), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- kernel.shared_1[((threadIdx.x_2*4) + 1569)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 48)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*4), 3) + 11), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- kernel.shared_1[((threadIdx.x_2*4) + 1570)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 48)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*4) + 34), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- kernel.shared_1[((threadIdx.x_2*4) + 1571)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 48)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*4) + 1568), 3) + 1), 64)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- if @tir.likely((threadIdx.x_2 < 180), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*4) + 2352)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 588), 48)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*4), 3) + 16), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- }
- if @tir.likely((threadIdx.x_2 < 180), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*4) + 2353)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 588), 48)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*4) + 49), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- }
- if @tir.likely((threadIdx.x_2 < 180), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*4) + 2354)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 588), 48)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*4) + 50), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- }
- if @tir.likely((threadIdx.x_2 < 180), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*4) + 2355)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 588), 48)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*4), 3) + 17), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- }
- }
- for (rc.outer.inner: int32, 0, 2) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*2016) + floormod(threadIdx.x, 49))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rc.outer.inner*2016) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 192)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rc.outer.inner*2016) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 384)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rc.outer.inner*2016) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 576)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 195)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 387)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 579)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 198)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 390)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 582)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 201)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 393)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 585)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 204)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 396)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 588)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 207)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 399)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 591)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 210)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 402)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 594)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 213)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 405)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 597)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 216)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 408)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 600)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 219)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 411)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 603)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 222)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 414)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 606)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 33)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 225)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 417)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 609)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 36)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 228)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 420)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 612)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 39)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 231)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 423)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 615)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 42)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 234)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 426)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 618)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 45)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 237)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 429)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 621)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 240)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 432)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 624)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 51)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 243)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 435)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 627)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 54)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 246)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 438)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 630)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 57)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 249)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 441)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 633)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 60)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 252)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 444)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 636)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 63)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 255)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 447)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 639)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 66)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 258)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 450)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 642)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 69)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 261)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 453)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 645)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 72)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 264)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 456)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 648)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 75)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 267)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 459)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 651)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 78)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 270)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 462)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 654)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 81)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 273)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 465)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 657)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 84)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 276)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 468)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 660)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 87)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 279)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 471)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 663)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 90)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 282)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 474)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 666)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 93)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 285)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 477)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 669)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 193)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 385)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 577)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 196)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 388)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 580)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 199)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 391)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 583)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 202)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 394)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 586)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 205)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 397)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 589)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 208)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 400)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 592)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 211)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 403)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 595)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 214)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 406)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 598)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 25)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 217)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 409)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 601)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 220)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 412)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 604)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 31)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 223)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 415)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 607)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 34)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 226)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 418)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 610)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 37)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 229)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 421)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 613)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 40)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 232)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 424)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 616)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 43)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 235)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 427)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 619)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 46)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 238)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 430)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 622)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 49)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 241)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 433)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 625)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 52)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 244)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 436)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 628)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 55)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 247)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 439)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 631)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 58)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 250)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 442)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 634)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 61)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 253)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 445)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 637)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 64)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 256)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 448)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 640)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 67)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 259)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 451)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 643)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 70)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 262)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 454)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 646)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 73)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 265)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 457)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 649)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 76)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 268)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 460)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 652)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 79)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 271)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 463)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 655)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 82)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 274)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 466)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 658)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 85)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 277)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 469)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 661)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 88)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 280)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 472)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 664)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 91)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 283)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 475)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 667)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 94)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 286)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 478)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 670)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 194)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 386)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 578)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 197)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 389)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 581)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 200)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 392)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 584)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 203)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 395)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 587)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 206)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 398)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 590)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 209)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 401)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 593)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 212)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 404)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 596)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 215)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 407)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 599)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 26)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 218)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 410)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 602)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 221)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 413)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 605)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 32)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 224)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 416)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 608)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 35)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 227)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 419)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 611)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 38)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 230)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 422)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 614)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 41)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 233)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 425)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 617)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 44)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 236)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 428)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 620)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 47)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 239)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 431)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 623)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1022)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 50)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1022)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 242)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1022)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 434)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1022)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 626)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1085)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 53)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1085)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 245)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1085)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 437)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1085)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 629)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1148)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 56)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1148)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 248)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1148)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 440)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1148)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 632)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1211)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 59)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1211)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 251)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1211)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 443)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1211)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 635)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1274)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 62)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1274)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 254)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1274)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 446)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1274)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 638)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1337)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 65)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1337)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 257)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1337)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 449)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1337)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 641)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1400)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 68)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1400)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 260)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1400)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 452)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1400)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 644)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1463)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 71)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1463)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 263)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1463)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 455)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1463)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 647)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1526)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 74)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1526)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 266)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1526)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 458)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1526)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 650)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1589)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 77)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1589)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 269)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1589)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 461)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1589)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 653)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1652)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 80)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1652)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 272)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1652)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 464)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1652)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 656)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1715)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 83)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1715)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 275)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1715)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 467)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1715)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 659)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1778)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 86)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1778)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 278)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1778)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 470)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1778)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 662)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1841)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 89)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1841)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 281)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1841)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 473)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1841)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 665)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1904)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 92)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1904)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 284)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1904)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 476)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1904)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 668)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1967)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 95)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1967)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 287)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1967)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 479)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1967)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 671)]))
- }
+ for (rc.outer.outer: int32, 0, 64) {
+ let cse_var_2: int32 = (rc.outer.outer*392)
+ let cse_var_1: int32 = (rc.outer.outer*72)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[(((cse_var_2 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 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(((((9 <= floormod((threadIdx.x_1 + 49), 81)) && (floormod((threadIdx.x_1 + 49), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 49), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 49), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 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((threadIdx.x_1 + 8), 9)) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 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(((((9 <= floormod((threadIdx.x_1 + 66), 81)) && (floormod((threadIdx.x_1 + 66), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 147), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 66), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 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(((((9 <= floormod((threadIdx.x_1 + 34), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 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((((9 <= floormod((threadIdx.x_1 + 2), 81)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 245), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 2), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 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(((((9 <= floormod((threadIdx.x_1 + 51), 81)) && (floormod((threadIdx.x_1 + 51), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 294), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 51), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 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((threadIdx.x_1 + 1), 9)) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 343), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 19), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 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(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 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(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 4), 9)) && (floormod((threadIdx.x_1 + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 441), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 4), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 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((((9 <= floormod((threadIdx.x_1 + 4), 81)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 490), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 4), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 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(((((9 <= floormod((threadIdx.x_1 + 53), 81)) && (floormod((threadIdx.x_1 + 53), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 539), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 53), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 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((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 588), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 21), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ if @tir.likely((threadIdx.x_1 < 11), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 637)] = @tir.if_then_else((((threadIdx.x_1 < 2) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 637), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 70), 81), 9)*7)) + (threadIdx.x_1 + 7)) - 8)], 0f32, dtype=float32)
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1: Buffer(kernel.shared, float32, [144], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((blockIdx.x*9216) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 49)] = kernel_3[(((((blockIdx.x*9216) + (floordiv((threadIdx.x_2 + 49), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 49), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ if @tir.likely((threadIdx.x_2 < 46), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 98)] = kernel_3[(((((blockIdx.x*9216) + (floordiv((threadIdx.x_2 + 98), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 26), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[0]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[72]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[9]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[81]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[18]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[90]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[27]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[99]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[36]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[108]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[45]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[117]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[54]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[126]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[63]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[135]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[1]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[73]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[10]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[82]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[19]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[91]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[28]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[100]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[37]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[109]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[46]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[118]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[55]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[127]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[64]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[136]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[2]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[74]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[11]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[83]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[20]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[92]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[29]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[101]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[38]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[110]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[47]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[119]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[56]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[128]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[65]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[137]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[3]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[75]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[12]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[84]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[21]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[93]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[30]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[102]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[39]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[111]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[48]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[120]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[57]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[129]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[66]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[138]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[4]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[76]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[13]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[85]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[22]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[94]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[31]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[103]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[40]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[112]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[49]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[121]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[58]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[130]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[67]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[139]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[5]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[77]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[14]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[86]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[23]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[95]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[32]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[104]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[41]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[113]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[50]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[122]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[59]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[131]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[68]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[140]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[6]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[78]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[15]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[87]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[24]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[96]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[33]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[105]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[42]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[114]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[51]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[123]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[60]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[132]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[69]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[141]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[7]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[79]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[16]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[88]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[25]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[97]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[34]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[106]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[43]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[115]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[52]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[124]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[61]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[133]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[70]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[142]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[8]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[80]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[17]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[89]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[26]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[98]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[35]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[107]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[44]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[116]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[53]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[125]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[62]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[134]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[71]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[143]))
}
}
- for (i1.inner: int32, 0, 4) {
- compute_3: Buffer(compute_2, float32, [25088], [])[((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[(((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ compute_3: Buffer(compute_2, float32, [25088], [])[(((blockIdx.x*98) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*2) + i1.inner)]), 0f32)
}
}
}
@@ -1021,7 +737,7 @@ 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: 0.395 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.310 ms
</pre></div>
</div>
</div>
@@ -1050,9 +766,9 @@ 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=4)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
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=4)
+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=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
@@ -1062,18 +778,18 @@ conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, fact
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=32)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
+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_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=4)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
+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=1)
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)
@@ -1097,16 +813,16 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
+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=196)
+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)
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=196)
+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)
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", 512)
+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:
@@ -1124,455 +840,183 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(196) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[4];
- __shared__ float pad_temp_shared[4032];
- __shared__ float kernel_shared[3072];
+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[2];
+ __shared__ float pad_temp_shared[648];
+ __shared__ float kernel_shared[144];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
- for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((1 <= (((((int)threadIdx.x) / 7) + 1) % 9)) && ((((((int)threadIdx.x) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 196) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 1) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 392) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 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 * 3136) + (((((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) + 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 * 3136) + (((((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) + 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 * 3136) + (((((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) + 1176)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1176) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1372) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1764)] = (((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) + 1364)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((1 <= (((((int)threadIdx.x) / 7) + 1) % 9)) && ((((((int)threadIdx.x) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1960) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 1) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2156)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2156) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((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 * 3136) + (((((int)threadIdx.x) + 2352) / 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) + 2548)] = (((((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 * 3136) + (((((int)threadIdx.x) + 2548) / 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) + 2744)] = (((((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 * 3136) + (((((int)threadIdx.x) + 2744) / 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) + 2940)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2940) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3332)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3332) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3528)] = (((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) + 2736)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3724)] = (((((1 <= (((((int)threadIdx.x) / 7) + 1) % 9)) && ((((((int)threadIdx.x) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3724) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 1) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 112) {
- pad_temp_shared[(((int)threadIdx.x) + 3920)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[(((int)threadIdx.x) * 4)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 48) * 4) / 3) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 1)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 48) * 4) + 1) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 2)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 48) * 4) + 2) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 3)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 1) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 784)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 16) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 785)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 17) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 786)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 6) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 787)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 784) / 3) + 1) & 63) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 1568)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 32) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 1569)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 11) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 1570)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 34) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 4) + 1571)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 1568) / 3) + 1) & 63) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- if (((int)threadIdx.x) < 180) {
- kernel_shared[((((int)threadIdx.x) * 4) + 2352)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 16) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- }
- if (((int)threadIdx.x) < 180) {
- kernel_shared[((((int)threadIdx.x) * 4) + 2353)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 49) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- }
- if (((int)threadIdx.x) < 180) {
- kernel_shared[((((int)threadIdx.x) * 4) + 2354)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 50) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- }
- if (((int)threadIdx.x) < 180) {
- kernel_shared[((((int)threadIdx.x) * 4) + 2355)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 17) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 192)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 384)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 576)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 195)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 387)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 579)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 198)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 390)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 582)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 201)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 393)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 585)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 204)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 396)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 588)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 207)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 399)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 591)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 210)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 402)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 594)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 213)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 405)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 597)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 216)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 408)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 600)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 219)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 411)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 603)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 222)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 414)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 606)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 33)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 225)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 417)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 609)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 228)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 420)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 612)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 39)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 231)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 423)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 615)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 42)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 234)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 426)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 618)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 45)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 237)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 429)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 621)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 240)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 432)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 624)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 51)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 243)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 435)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 627)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 54)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 246)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 438)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 630)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 57)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 249)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 441)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 633)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 60)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 252)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 444)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 636)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 63)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 255)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 447)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 639)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 66)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 258)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 450)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 642)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 69)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 261)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 453)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 645)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 72)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 264)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 456)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 648)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 75)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 267)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 459)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 651)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 78)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 270)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 462)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 654)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 81)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 273)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 465)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 657)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 84)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 276)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 468)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 660)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 87)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 279)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 471)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 663)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 90)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 282)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 474)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 666)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 93)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 285)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 477)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 669)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 193)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 385)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 577)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 196)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 388)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 580)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 199)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 391)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 583)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 202)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 394)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 586)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 205)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 397)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 589)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 208)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 400)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 592)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 211)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 403)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 595)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 214)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 406)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 598)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 25)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 217)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 409)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 601)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 220)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 412)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 604)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 31)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 223)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 415)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 607)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 34)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 226)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 418)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 610)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 37)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 229)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 421)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 613)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 40)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 232)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 424)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 616)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 43)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 235)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 427)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 619)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 46)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 238)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 430)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 622)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 49)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 241)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 433)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 625)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 52)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 244)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 436)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 628)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 55)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 247)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 439)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 631)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 58)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 250)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 442)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 634)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 61)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 253)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 445)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 637)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 64)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 256)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 448)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 640)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 67)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 259)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 451)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 643)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 70)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 262)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 454)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 646)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 73)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 265)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 457)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 649)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 76)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 268)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 460)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 652)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 79)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 271)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 463)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 655)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 82)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 274)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 466)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 658)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 85)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 277)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 469)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 661)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 88)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 280)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 472)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 664)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 91)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 283)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 475)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 667)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 94)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 286)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 478)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 670)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 194)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 386)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 578)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 197)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 389)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 581)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 200)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 392)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 584)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 203)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 395)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 587)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 206)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 398)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 590)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 209)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 401)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 593)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 212)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 404)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 596)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 215)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 407)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 599)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 26)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 218)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 410)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 602)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 221)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 413)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 605)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 32)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 224)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 416)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 608)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 35)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 227)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 419)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 611)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 38)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 230)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 422)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 614)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 41)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 233)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 425)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 617)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 44)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 236)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 428)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 620)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 47)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 239)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 431)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 623)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1022)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 50)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1022)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 242)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1022)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 434)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1022)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 626)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1085)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 53)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1085)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 245)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1085)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 437)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1085)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 629)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1148)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 56)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1148)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 248)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1148)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 440)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1148)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 632)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1211)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 59)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1211)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 251)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1211)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 443)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1211)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 635)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1274)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 62)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1274)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 254)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1274)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 446)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1274)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 638)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1337)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 65)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1337)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 257)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1337)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 449)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1337)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 641)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1400)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 68)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1400)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 260)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1400)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 452)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1400)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 644)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1463)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 71)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1463)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 263)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1463)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 455)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1463)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 647)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1526)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 74)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1526)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 266)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1526)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 458)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1526)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 650)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1589)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 77)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1589)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 269)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1589)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 461)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1589)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 653)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1652)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 80)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1652)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 272)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1652)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 464)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1652)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 656)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1715)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 83)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1715)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 275)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1715)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 467)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1715)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 659)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1778)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 86)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1778)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 278)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1778)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 470)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1778)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 662)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1841)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 89)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1841)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 281)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1841)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 473)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1841)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 665)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1904)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 92)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1904)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 284)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1904)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 476)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1904)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 668)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1967)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 95)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1967)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 287)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1967)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 479)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1967)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 671)]));
- }
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 49) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 98) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((9 <= ((((int)threadIdx.x) + 66) % 81)) && (((((int)threadIdx.x) + 66) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 147) / 81) * 49)) + ((((((int)threadIdx.x) + 66) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 245)] = ((((7 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 245) / 81) * 49)) + (((((int)threadIdx.x) + 2) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((9 <= ((((int)threadIdx.x) + 51) % 81)) && (((((int)threadIdx.x) + 51) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 294) / 81) * 49)) + ((((((int)threadIdx.x) + 51) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 343)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 343) / 81) * 49)) + (((((int)threadIdx.x) + 19) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 441)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 441) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = ((((5 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 490) / 81) * 49)) + (((((int)threadIdx.x) + 4) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 539)] = (((((9 <= ((((int)threadIdx.x) + 53) % 81)) && (((((int)threadIdx.x) + 53) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 539) / 81) * 49)) + ((((((int)threadIdx.x) + 53) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 588) / 81) * 49)) + (((((int)threadIdx.x) + 21) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 11) {
+ pad_temp_shared[(((int)threadIdx.x) + 637)] = ((((((int)threadIdx.x) < 2) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 637) / 81) * 49)) + (((((int)threadIdx.x) + 70) / 9) * 7)) + ((int)threadIdx.x)) - 1)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 9216) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 49)] = kernel[(((((((int)blockIdx.x) * 9216) + (((((int)threadIdx.x) + 49) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 49) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 46) {
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 9216) + (((((int)threadIdx.x) + 98) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 26) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
}
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[0]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[72]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[9]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[81]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[18]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[90]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[27]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[99]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[36]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[108]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[45]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[117]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[54]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[126]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[63]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[135]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[1]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[73]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[10]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[82]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[19]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[91]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[28]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[100]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[37]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[109]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[46]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[118]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[55]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[127]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[64]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[136]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[2]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[74]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[11]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[83]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[20]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[92]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[29]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[101]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[38]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[110]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[47]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[119]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[56]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[128]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[65]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[137]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[3]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[75]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[12]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[84]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[21]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[93]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[30]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[102]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[39]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[111]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[48]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[120]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[57]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[129]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[66]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[138]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[4]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[76]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[13]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[85]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[22]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[94]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[31]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[103]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[40]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[112]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[49]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[121]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[58]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[130]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[67]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[139]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[5]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[77]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[14]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[86]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[23]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[95]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[32]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[104]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[41]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[113]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[50]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[122]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[59]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[131]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[68]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[140]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[6]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[78]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[15]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[87]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[24]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[96]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[33]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[105]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[42]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[114]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[51]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[123]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[60]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[132]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[69]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[141]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[7]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[79]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[16]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[88]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[25]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[97]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[34]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[106]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[43]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[115]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[52]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[124]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[61]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[133]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[70]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[142]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[8]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[80]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[17]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[89]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[26]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[98]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[35]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[107]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[44]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[116]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[53]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[125]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[62]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[134]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[71]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[143]));
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ compute[(((((int)blockIdx.x) * 98) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 2) + i1_inner)]), 0.000000e+00f);
}
}
</pre></div>
@@ -1609,7 +1053,7 @@ 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 32.419 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 32.783 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 4ff424365d..04ccacbd71 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)
- 7.8911 7.8917 7.9009 7.8808 0.0082
+ 7.8503 7.8550 7.8621 7.8339 0.0120
</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 0.966 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.989 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 62165f597d..be456d0304 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)
- 753.4300 753.6220 754.8865 751.7814 1.2749
+ 766.1723 766.5858 766.7852 765.1459 0.7303
</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 31.133 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 34.030 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 1ba66be86a..ee5275af10 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -633,29 +633,105 @@ 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, 32) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
+ for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [256]), storage_scope = global {
for (i.outer.inner: int32, 0, 2) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 32) {
- for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [2048], [])[((((i.outer.inner*1024) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
- }
+ for (i.inner.init: int32, 0, 8) {
+ let cse_var_1: int32 = ((i.outer.inner*128) + (i.inner.init*16))
+ {
+ compute_4: Buffer(compute_3, float32, [256], [])[cse_var_1] = 0f32
+ compute_4[(cse_var_1 + 1)] = 0f32
+ compute_4[(cse_var_1 + 2)] = 0f32
+ compute_4[(cse_var_1 + 3)] = 0f32
+ compute_4[(cse_var_1 + 4)] = 0f32
+ compute_4[(cse_var_1 + 5)] = 0f32
+ compute_4[(cse_var_1 + 6)] = 0f32
+ compute_4[(cse_var_1 + 7)] = 0f32
+ compute_4[(cse_var_1 + 8)] = 0f32
+ compute_4[(cse_var_1 + 9)] = 0f32
+ compute_4[(cse_var_1 + 10)] = 0f32
+ compute_4[(cse_var_1 + 11)] = 0f32
+ compute_4[(cse_var_1 + 12)] = 0f32
+ compute_4[(cse_var_1 + 13)] = 0f32
+ compute_4[(cse_var_1 + 14)] = 0f32
+ compute_4[(cse_var_1 + 15)] = 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, 32) {
- 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*1024) + (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*8192)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ for (elem_idx: int32, 0, let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
+ for (i.inner: int32, 0, 8) {
+ let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ {
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_4: int32 = ((i.outer.inner*128) + (i.inner*16))
+ compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_3]*16) + (elem_idx*16))]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_5: int32 = (((i.outer.inner*128) + (i.inner*16)) + 1)
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_6: int32 = (((i.outer.inner*128) + (i.inner*16)) + 2)
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_7: int32 = (((i.outer.inner*128) + (i.inner*16)) + 3)
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_8: int32 = (((i.outer.inner*128) + (i.inner*16)) + 4)
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_9: int32 = (((i.outer.inner*128) + (i.inner*16)) + 5)
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_10: int32 = (((i.outer.inner*128) + (i.inner*16)) + 6)
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_11: int32 = (((i.outer.inner*128) + (i.inner*16)) + 7)
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_12: int32 = (((i.outer.inner*128) + (i.inner*16)) + 8)
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_13: int32 = (((i.outer.inner*128) + (i.inner*16)) + 9)
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_14: int32 = (((i.outer.inner*128) + (i.inner*16)) + 10)
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_15: int32 = (((i.outer.inner*128) + (i.inner*16)) + 11)
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_16: int32 = (((i.outer.inner*128) + (i.inner*16)) + 12)
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_17: int32 = (((i.outer.inner*128) + (i.inner*16)) + 13)
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_18: int32 = (((i.outer.inner*128) + (i.inner*16)) + 14)
+ compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_19: int32 = (((i.outer.inner*128) + (i.inner*16)) + 15)
+ compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
}
- 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))
+ for (i0.inner: int32, 0, 16) {
+ let cse_var_20: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_20, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_20, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -693,7 +769,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.639 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.856 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 6b92338b54..0beb5ed02b 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>00:36.878</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:38.348</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,7 +349,7 @@
</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>00:36.842</p></td>
+<td><p>00:38.313</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>
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 acacac6bd8..17e7aed748 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -690,130 +690,25 @@ 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, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4128236
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5096885
No: 2 GFLOPS: 0.00/0.00 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 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h: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
-
-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, 8, 32, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8620573
+ 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, 4, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2453102
No: 3 GFLOPS: 0.00/0.00 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)
@@ -936,8 +831,9 @@ 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, 2, 1, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,518091
-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, 1, 4, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6675415
+No: 4 GFLOPS: 26.60/26.60 result: MeasureResult(costs=(0.008702390928571429,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.851181983947754, timestamp=1673306729.197973) [('tile_f', [-1, 2, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,429496
+No: 5 GFLOPS: 0.00/26.60 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 +955,9 @@ 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, 1, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4785952
-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, 64, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2413653
+No: 6 GFLOPS: 296.27/296.27 result: MeasureResult(costs=(0.0007813849285714285,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.329486608505249, timestamp=1673306732.481104) [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,145674
+No: 7 GFLOPS: 0.00/296.27 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 +1079,8 @@ 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, 256, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6804443
-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, 4, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7127002
+No: 8 GFLOPS: 0.00/296.27 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
@@ -1305,8 +1202,9 @@ 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, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6535872
-No: 7 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, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4547676
+No: 9 GFLOPS: 266.22/296.27 result: MeasureResult(costs=(0.0008695816,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2021591663360596, timestamp=1673306734.1871915) [('tile_f', [-1, 16, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,11023
+No: 10 GFLOPS: 0.00/296.27 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
@@ -1428,8 +1326,8 @@ 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, 16, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9805525
-No: 8 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, 1, 128, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,703475
+No: 11 GFLOPS: 0.00/296.27 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
@@ -1551,9 +1449,10 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 128, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1106075
-No: 9 GFLOPS: 40.78/40.78 result: MeasureResult(costs=(0.005677435407407407,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.373302459716797, timestamp=1673305373.5163271) [('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9025300
-No: 10 GFLOPS: 0.00/40.78 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4541752
+No: 12 GFLOPS: 7.69/296.27 result: MeasureResult(costs=(0.0300871675,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3995342254638672, timestamp=1673306734.9919019) [('tile_f', [-1, 8, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1235743
+No: 13 GFLOPS: 27.54/296.27 result: MeasureResult(costs=(0.008405490833333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8662846088409424, timestamp=1673306737.0311227) [('tile_f', [-1, 8, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7941451
+No: 14 GFLOPS: 0.00/296.27 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
@@ -1675,9 +1574,8 @@ 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, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8296123
-No: 11 GFLOPS: 2.67/40.78 result: MeasureResult(costs=(0.08682093025,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3896007537841797, timestamp=1673305375.0809305) [('tile_f', [-1, 8, 1, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3133428
-No: 12 GFLOPS: 0.00/40.78 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7479535
+No: 15 GFLOPS: 0.00/296.27 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
@@ -1799,8 +1697,8 @@ 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, 2, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7155924
-No: 13 GFLOPS: 0.00/40.78 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7441023
+No: 16 GFLOPS: 0.00/296.27 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
@@ -1922,8 +1820,9 @@ 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, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1599284
-No: 14 GFLOPS: 0.00/40.78 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9289788
+No: 17 GFLOPS: 62.74/296.27 result: MeasureResult(costs=(0.0036897097857142855,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.279930591583252, timestamp=1673306738.52046) [('tile_f', [-1, 4, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6515769
+No: 18 GFLOPS: 0.00/296.27 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
@@ -2045,163 +1944,8 @@ 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, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8324266
-No: 15 GFLOPS: 0.00/40.78 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)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 4: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc: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: 0x00007f126d019fa2
- 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
- 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
-
-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, 128, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6510907
-No: 16 GFLOPS: 82.82/82.82 result: MeasureResult(costs=(0.002795111111111111,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2012507915496826, timestamp=1673305382.0745542) [('tile_f', [-1, 2, 64, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8178546
-No: 17 GFLOPS: 38.89/82.82 result: MeasureResult(costs=(0.005952071647058824,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7134439945220947, timestamp=1673305383.9521222) [('tile_f', [-1, 1, 64, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3165713
-No: 18 GFLOPS: 0.00/82.82 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,32809
+No: 19 GFLOPS: 0.00/296.27 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 +2067,8 @@ 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, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7374171
-No: 19 GFLOPS: 0.00/82.82 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8221915
+No: 20 GFLOPS: 0.00/296.27 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 +2190,7 @@ 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, 64, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4833665
-No: 20 GFLOPS: 0.98/82.82 result: MeasureResult(costs=(0.23723574825,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.420214653015137, timestamp=1673305387.4534936) [('tile_f', [-1, 128, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1256657
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3114492
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2486,9 +2229,9 @@ 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, 2, 64, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8178546
+[('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,145674
Finish loading 20 records
-Time cost of this operator: 0.003144
+Time cost of this operator: 0.000784
</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 2a16bfc834..3c1cee0822 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 308.3 98.695 (1, 2, 10, 10, 3) 2 1 [308.3]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.114 0.997 (1, 6, 10, 10) 1 1 [3.114]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.961 0.308 (1, 1, 10, 10, 3) 1 1 [0.961]
-Total_time - 312.375 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.1 98.73 (1, 2, 10, 10, 3) 2 1 [313.1]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.036 0.957 (1, 6, 10, 10) 1 1 [3.036]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.992 0.313 (1, 1, 10, 10, 3) 1 1 [0.992]
+Total_time - 317.128 - - - - -
</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 100.3 97.353 (1, 6, 10, 10, 1) 2 1 [100.3]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.774 1.722 (1, 6, 10, 10) 1 1 [1.774]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.953 0.925 (1, 1, 10, 10, 3) 1 1 [0.953]
-Total_time - 103.028 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 134.3 97.915 (1, 6, 10, 10, 1) 2 1 [134.3]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.872 1.365 (1, 6, 10, 10) 1 1 [1.872]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.988 0.72 (1, 1, 10, 10, 3) 1 1 [0.988]
+Total_time - 137.159 - - - - -
</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 43b2b5370b..27279ce2ed 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -453,8 +453,8 @@ 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]
- 61%|###### | 2.09M/3.42M [00:00<00:00, 16.9MB/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 26.7MB/s]
+ 61%|###### | 2.09M/3.42M [00:00<00:00, 21.6MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 33.5MB/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.
@@ -578,7 +578,7 @@ 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 2.393 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.083 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 eda9bf77d2..ad4ec5a8f8 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/tmpcymbw0hi/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpv54taz41/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], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpcymbw0hi/images/target contains 8144 images
-/tmp/tmpcymbw0hi/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpv54taz41/images/target contains 8144 images
+/tmp/tmpv54taz41/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: 0.2139 - accuracy: 0.9272 - val_loss: 0.1431 - val_accuracy: 0.9577 - 47s/epoch - 143ms/step
+328/328 - 47s - loss: 0.2265 - accuracy: 0.9215 - val_loss: 0.1252 - val_accuracy: 0.9558 - 47s/epoch - 144ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.1014 - accuracy: 0.9647 - val_loss: 0.1398 - val_accuracy: 0.9558 - 43s/epoch - 132ms/step
+328/328 - 43s - loss: 0.0978 - accuracy: 0.9650 - val_loss: 0.1251 - val_accuracy: 0.9581 - 43s/epoch - 133ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0645 - accuracy: 0.9771 - val_loss: 0.1135 - val_accuracy: 0.9649 - 43s/epoch - 132ms/step
+328/328 - 43s - loss: 0.0618 - accuracy: 0.9784 - val_loss: 0.1156 - val_accuracy: 0.9641 - 43s/epoch - 132ms/step
-<keras.callbacks.History object at 0x7f59d167f450>
+<keras.callbacks.History object at 0x7feb1bdb0390>
</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 21.479 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 23.785 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 68a1d1a7c1..a76812dac6 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>06:26.227</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:35.389</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>04:21.479</p></td>
+<td><p>04:23.785</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>01:02.393</p></td>
+<td><p>01:06.083</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>00:50.795</p></td>
+<td><p>00:53.118</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>00:07.844</p></td>
+<td><p>00:08.460</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>00:03.715</p></td>
+<td><p>00:03.941</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 b59ff51a84..cc922cb8e2 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>00:44.065</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:44.956</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>00:32.202</p></td>
+<td><p>00:32.970</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>00:10.154</p></td>
+<td><p>00:10.306</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>00:01.703</p></td>
+<td><p>00:01.672</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 79f187e5a1..c88b9fd696 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 0x7f5a605200e0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7feb1d28add0>
</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 39efc90291..7a26d5bd16 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>00:07.000</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:07.648</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,31 +349,31 @@
</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>00:04.533</p></td>
+<td><p>00:05.072</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>00:01.127</p></td>
+<td><p>00:01.212</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>00:00.571</p></td>
+<td><p>00:00.581</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>00:00.555</p></td>
+<td><p>00:00.564</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>00:00.113</p></td>
+<td><p>00:00.115</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>00:00.049</p></td>
+<td><p>00:00.050</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>
-<td><p>00:00.028</p></td>
+<td><p>00:00.029</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 4dbd355f5d..54d68e0634 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/tmpdx6bwzwc/input0.cc'\nsource_filename = \"/tmp/tmpdx6bwzwc/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/tmpd5et8hg8/input0.cc'\nsource_filename = \"/tmp/tmpd5et8hg8/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 5f46f0875d..1b353b5197 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 f5fccb499d..7c06289926 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/d2ee4ec97/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 2f0ddaa29b..aeab87ade0 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/d2ee4ec97/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 fffc2b8b1e..708e4c3ea1 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/d2ee4ec97/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 c85804b1a3..bb1d2998c1 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/d2ee4ec97/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 331be5450c..f65e01bf52 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/d2ee4ec97/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 e837186dc1..d6d9eac478 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/d2ee4ec97/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 02c69e9ea7..c6c83d950b 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/d2ee4ec97/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 3d525e5abf..57b6419a97 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/d2ee4ec97/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 10bde46634..889077d3be 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/d2ee4ec97/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 804512cb10..9bcb688ec0 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/d2ee4ec97/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 b6dfc86324..3a5a63cfba 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/d2ee4ec97/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 c08cb5f944..bd46edf3ce 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/d2ee4ec97/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 e72b613402..764c10788a 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/d2ee4ec97/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 cf8af025c7..45a5a5e7f1 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/d2ee4ec97/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 e2be4ba187..7d924f8a9c 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/d2ee4ec97/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/web/src/webgpu.ts#L172">webgpu.ts:172</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/d2ee4ec97/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 096a097ecc..957ec6f0e3 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/d2ee4ec97/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 a41cdae14a..0bc0f9e632 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/d2ee4ec97/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 06b590b8e7..f9736cbd01 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/d2ee4ec97/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 a95a7979a1..0ba01a9487 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/d2ee4ec97/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 ad2b486f8a..e49c8e8a12 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/d2ee4ec97/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 94d519b3ac..1df0502bc9 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/d2ee4ec97/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 e1a48dc716..033878181e 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/d2ee4ec97/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 2f6f8bbd0f..c4b508f371 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/d2ee4ec97/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 35928c6468..8ebedba442 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/d2ee4ec97/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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/d2ee4ec97/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/687ec7883/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 06eae6e578..ff31d98fd5 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 1bd8b24624..602c4ab51d 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>00:25.827</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:27.176</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:25.820</p></td>
+<td><p>00:27.169</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 39d58c030c..659343e27a 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 28.37s!
+resnet18_v1 inference graph built in 30.05s!
</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 a1c01058a8..ce16558ff2 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 19.36s!
+yolov3-tiny inference graph built in 20.46s!
</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 4f442a6097..93050d7400 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>01:31.369</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:34.301</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>00:46.192</p></td>
+<td><p>00:47.336</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>00:45.177</p></td>
+<td><p>00:46.965</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 38a804bbb6..480d778a92 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>00:03.175</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.209</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>00:02.719</p></td>
+<td><p>00:02.742</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>00:00.455</p></td>
+<td><p>00:00.466</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 a5b1139f9d..439063c7a8 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.790</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.813</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -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>00:00.419</p></td>
+<td><p>00:00.436</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>00:00.371</p></td>
+<td><p>00:00.377</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 b77e8c041c..c7ea330d8f 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: 95.116 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 95.338 ms
</pre></div>
</div>
</div>
@@ -642,6 +642,7 @@ resume the status and do more 5 trials.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Resume search:
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
+*E
</pre></div>
</div>
</div>
@@ -652,7 +653,7 @@ 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 18.024 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.160 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 e900bb6450..16d4de098d 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: 9.44/9.44 result: MeasureResult(costs=(0.028435561399999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7167747020721436, timestamp=1673303997.0058396) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
-No: 2 GFLOPS: 3.93/9.44 result: MeasureResult(costs=(0.068270972,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3535549640655518, timestamp=1673303998.3494003) [('tile_y', [-1, 32]), ('tile_x', [-1, 16])],None,45
-No: 3 GFLOPS: 12.35/12.35 result: MeasureResult(costs=(0.021736787,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5946812629699707, timestamp=1673303999.7041836) [('tile_y', [-1, 256]), ('tile_x', [-1, 256])],None,88
-No: 4 GFLOPS: 13.11/13.11 result: MeasureResult(costs=(0.020472513,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5724074840545654, timestamp=1673304000.2958043) [('tile_y', [-1, 4]), ('tile_x', [-1, 512])],None,92
-No: 5 GFLOPS: 1.62/13.11 result: MeasureResult(costs=(0.1658812922,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.883044481277466, timestamp=1673304003.3141713) [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
-No: 6 GFLOPS: 2.98/13.11 result: MeasureResult(costs=(0.0900853952,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6897482872009277, timestamp=1673304005.7602015) [('tile_y', [-1, 2]), ('tile_x', [-1, 16])],None,41
-No: 7 GFLOPS: 12.75/13.11 result: MeasureResult(costs=(0.0210565292,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5880179405212402, timestamp=1673304007.1084647) [('tile_y', [-1, 4]), ('tile_x', [-1, 256])],None,82
-No: 8 GFLOPS: 9.35/13.11 result: MeasureResult(costs=(0.028719933800000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6814696788787842, timestamp=1673304007.8179402) [('tile_y', [-1, 512]), ('tile_x', [-1, 32])],None,59
-No: 9 GFLOPS: 13.03/13.11 result: MeasureResult(costs=(0.020595084800000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5730547904968262, timestamp=1673304008.5058267) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
-No: 10 GFLOPS: 3.62/13.11 result: MeasureResult(costs=(0.0740535816,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.417675495147705, timestamp=1673304009.93929) [('tile_y', [-1, 16]), ('tile_x', [-1, 8])],None,34
+No: 1 GFLOPS: 3.67/3.67 result: MeasureResult(costs=(0.0731285002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4283857345581055, timestamp=1673305284.870477) [('tile_y', [-1, 128]), ('tile_x', [-1, 16])],None,47
+No: 2 GFLOPS: 12.60/12.60 result: MeasureResult(costs=(0.0213032298,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5622830390930176, timestamp=1673305285.467958) [('tile_y', [-1, 32]), ('tile_x', [-1, 512])],None,95
+No: 3 GFLOPS: 3.02/12.60 result: MeasureResult(costs=(0.08885599620000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.665698528289795, timestamp=1673305287.9366994) [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
+No: 4 GFLOPS: 2.30/12.60 result: MeasureResult(costs=(0.11681319539999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1048202514648438, timestamp=1673305290.849265) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
+No: 5 GFLOPS: 9.77/12.60 result: MeasureResult(costs=(0.0274856304,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6682958602905273, timestamp=1673305291.7050538) [('tile_y', [-1, 512]), ('tile_x', [-1, 32])],None,59
+No: 6 GFLOPS: 11.75/12.60 result: MeasureResult(costs=(0.022842706,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6717691421508789, timestamp=1673305293.127947) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 7 GFLOPS: 2.81/12.60 result: MeasureResult(costs=(0.0956754392,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7731642723083496, timestamp=1673305294.9126585) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 8 GFLOPS: 12.48/12.60 result: MeasureResult(costs=(0.021505332000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6068389415740967, timestamp=1673305295.5176377) [('tile_y', [-1, 128]), ('tile_x', [-1, 256])],None,87
+No: 9 GFLOPS: 14.32/14.32 result: MeasureResult(costs=(0.0187473114,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5644233226776123, timestamp=1673305296.1951587) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
+No: 10 GFLOPS: 3.79/14.32 result: MeasureResult(costs=(0.0708275778,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3460514545440674, timestamp=1673305297.580324) [('tile_y', [-1, 4]), ('tile_x', [-1, 16])],None,42
</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 2ea768de92..55e180ff76 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': 510.13883835999985, 'median': 509.9613637999994, 'std': 1.3041026659245931}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 516.4660860999993, 'median': 515.8854889500049, 'std': 2.283769529546039}
</pre></div>
</div>
</div>
@@ -713,179 +713,178 @@ 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: 12.68/ 22.54 GFLOPS | Progress: (4/20) | 6.87 s
-[Task 1/25] Current/Best: 15.64/ 22.54 GFLOPS | Progress: (8/20) | 14.31 s
-[Task 1/25] Current/Best: 12.43/ 23.53 GFLOPS | Progress: (12/20) | 17.61 s
-[Task 1/25] Current/Best: 8.52/ 23.53 GFLOPS | Progress: (16/20) | 20.61 s
-[Task 1/25] Current/Best: 22.66/ 23.53 GFLOPS | Progress: (20/20) | 23.40 s Done.
+[Task 1/25] Current/Best: 8.45/ 21.68 GFLOPS | Progress: (4/20) | 7.75 s
+[Task 1/25] Current/Best: 13.08/ 23.23 GFLOPS | Progress: (8/20) | 11.15 s
+[Task 1/25] Current/Best: 19.52/ 23.23 GFLOPS | Progress: (12/20) | 15.27 s
+[Task 1/25] Current/Best: 14.52/ 23.23 GFLOPS | Progress: (16/20) | 17.58 s
+[Task 1/25] Current/Best: 16.80/ 23.23 GFLOPS | Progress: (20/20) | 19.70 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 17.08/ 17.35 GFLOPS | Progress: (4/20) | 3.29 s
-[Task 2/25] Current/Best: 11.83/ 17.69 GFLOPS | Progress: (8/20) | 6.13 s
-[Task 2/25] Current/Best: 5.56/ 19.96 GFLOPS | Progress: (12/20) | 7.79 s
-[Task 2/25] Current/Best: 17.47/ 19.96 GFLOPS | Progress: (16/20) | 9.26 s
-[Task 2/25] Current/Best: 17.59/ 19.96 GFLOPS | Progress: (20/20) | 10.93 s Done.
+[Task 2/25] Current/Best: 11.80/ 17.90 GFLOPS | Progress: (4/20) | 3.55 s
+[Task 2/25] Current/Best: 15.92/ 18.54 GFLOPS | Progress: (8/20) | 5.14 s
+[Task 2/25] Current/Best: 11.08/ 18.71 GFLOPS | Progress: (12/20) | 7.23 s
+[Task 2/25] Current/Best: 14.55/ 18.71 GFLOPS | Progress: (16/20) | 9.57 s
+[Task 2/25] Current/Best: 11.92/ 18.71 GFLOPS | Progress: (20/20) | 11.81 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 11.54/ 22.13 GFLOPS | Progress: (4/20) | 4.18 s
-[Task 3/25] Current/Best: 15.05/ 22.13 GFLOPS | Progress: (8/20) | 6.56 s
-[Task 3/25] Current/Best: 13.97/ 22.13 GFLOPS | Progress: (12/20) | 8.99 s
-[Task 3/25] Current/Best: 8.64/ 23.84 GFLOPS | Progress: (16/20) | 11.58 s
-[Task 3/25] Current/Best: 6.42/ 23.84 GFLOPS | Progress: (20/20) | 14.35 s Done.
+[Task 3/25] Current/Best: 15.16/ 18.23 GFLOPS | Progress: (4/20) | 4.03 s
+[Task 3/25] Current/Best: 13.20/ 18.23 GFLOPS | Progress: (8/20) | 6.48 s
+[Task 3/25] Current/Best: 8.16/ 18.23 GFLOPS | Progress: (12/20) | 9.74 s
+[Task 3/25] Current/Best: 8.10/ 19.17 GFLOPS | Progress: (16/20) | 12.46 s
+[Task 3/25] Current/Best: 22.69/ 22.69 GFLOPS | Progress: (20/20) | 16.28 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.83/ 20.78 GFLOPS | Progress: (4/20) | 5.11 s
-[Task 4/25] Current/Best: 13.63/ 20.78 GFLOPS | Progress: (8/20) | 10.18 s
-[Task 4/25] Current/Best: 16.72/ 20.78 GFLOPS | Progress: (12/20) | 12.39 s
-[Task 4/25] Current/Best: 10.98/ 20.78 GFLOPS | Progress: (16/20) | 16.60 s
-[Task 4/25] Current/Best: 3.13/ 20.78 GFLOPS | Progress: (20/20) | 19.60 s Done.
+[Task 4/25] Current/Best: 3.35/ 19.36 GFLOPS | Progress: (4/20) | 8.67 s
+[Task 4/25] Current/Best: 6.39/ 19.98 GFLOPS | Progress: (8/20) | 11.05 s
+[Task 4/25] Current/Best: 8.65/ 21.03 GFLOPS | Progress: (12/20) | 15.27 s
+[Task 4/25] Current/Best: 6.50/ 21.03 GFLOPS | Progress: (16/20) | 18.19 s
+[Task 4/25] Current/Best: 18.43/ 21.03 GFLOPS | Progress: (20/20) | 20.49 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 5.64/ 15.42 GFLOPS | Progress: (4/20) | 4.32 s
-[Task 5/25] Current/Best: 8.66/ 20.02 GFLOPS | Progress: (8/20) | 6.02 s
-[Task 5/25] Current/Best: 15.11/ 20.41 GFLOPS | Progress: (12/20) | 7.77 s
-[Task 5/25] Current/Best: 15.73/ 20.41 GFLOPS | Progress: (16/20) | 10.09 s
-[Task 5/25] Current/Best: 18.09/ 20.41 GFLOPS | Progress: (20/20) | 11.93 s Done.
+[Task 5/25] Current/Best: 14.68/ 18.69 GFLOPS | Progress: (4/20) | 3.85 s
+[Task 5/25] Current/Best: 6.15/ 18.69 GFLOPS | Progress: (8/20) | 5.91 s
+[Task 5/25] Current/Best: 11.47/ 18.69 GFLOPS | Progress: (12/20) | 9.07 s
+[Task 5/25] Current/Best: 7.54/ 18.69 GFLOPS | Progress: (16/20) | 11.77 s
+[Task 5/25] Current/Best: 13.73/ 18.69 GFLOPS | Progress: (20/20) | 13.97 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 8.94/ 17.56 GFLOPS | Progress: (4/20) | 5.51 s
-[Task 6/25] Current/Best: 8.90/ 17.56 GFLOPS | Progress: (8/20) | 7.89 s
-[Task 6/25] Current/Best: 10.15/ 17.56 GFLOPS | Progress: (12/20) | 14.50 s
-[Task 6/25] Current/Best: 13.17/ 17.56 GFLOPS | Progress: (16/20) | 17.32 s
-[Task 6/25] Current/Best: 9.62/ 21.23 GFLOPS | Progress: (20/20) | 19.60 s Done.
+[Task 6/25] Current/Best: 18.99/ 18.99 GFLOPS | Progress: (4/20) | 4.08 s
+[Task 6/25] Current/Best: 10.64/ 18.99 GFLOPS | Progress: (8/20) | 9.01 s
+[Task 6/25] Current/Best: 18.32/ 18.99 GFLOPS | Progress: (12/20) | 12.04 s
+[Task 6/25] Current/Best: 16.29/ 18.99 GFLOPS | Progress: (16/20) | 14.18 s
+[Task 6/25] Current/Best: 13.67/ 18.99 GFLOPS | Progress: (20/20) | 18.03 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 7.63/ 20.15 GFLOPS | Progress: (4/20) | 4.81 s
-[Task 7/25] Current/Best: 8.30/ 20.15 GFLOPS | Progress: (8/20) | 7.39 s
-[Task 7/25] Current/Best: 15.91/ 20.15 GFLOPS | Progress: (12/20) | 10.12 s
-[Task 7/25] Current/Best: 12.72/ 20.15 GFLOPS | Progress: (16/20) | 12.36 s
-[Task 7/25] Current/Best: 15.46/ 20.15 GFLOPS | Progress: (20/20) | 14.77 s Done.
+[Task 7/25] Current/Best: 15.42/ 17.16 GFLOPS | Progress: (4/20) | 4.10 s
+[Task 7/25] Current/Best: 7.81/ 17.16 GFLOPS | Progress: (8/20) | 6.54 s
+[Task 7/25] Current/Best: 14.43/ 17.16 GFLOPS | Progress: (12/20) | 9.45 s
+[Task 7/25] Current/Best: 12.06/ 17.16 GFLOPS | Progress: (16/20) | 12.04 s
+[Task 7/25] Current/Best: 11.64/ 18.19 GFLOPS | Progress: (20/20) | 14.43 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 10.59/ 13.36 GFLOPS | Progress: (4/20) | 5.44 s
-[Task 8/25] Current/Best: 13.36/ 13.36 GFLOPS | Progress: (8/20) | 8.16 s
-[Task 8/25] Current/Best: 7.65/ 20.39 GFLOPS | Progress: (12/20) | 10.62 s
-[Task 8/25] Current/Best: 12.80/ 20.39 GFLOPS | Progress: (16/20) | 15.06 s
-[Task 8/25] Current/Best: 10.36/ 20.39 GFLOPS | Progress: (20/20) | 20.87 s Done.
+[Task 8/25] Current/Best: 11.38/ 17.65 GFLOPS | Progress: (4/20) | 4.96 s
+[Task 8/25] Current/Best: 7.41/ 17.65 GFLOPS | Progress: (8/20) | 11.26 s
+[Task 8/25] Current/Best: 8.42/ 17.65 GFLOPS | Progress: (12/20) | 16.38 s
+[Task 8/25] Current/Best: 5.35/ 17.98 GFLOPS | Progress: (16/20) | 18.97 s
+[Task 8/25] Current/Best: 7.58/ 17.98 GFLOPS | Progress: (20/20) | 23.55 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 10.63/ 19.88 GFLOPS | Progress: (4/20) | 4.46 s
-[Task 9/25] Current/Best: 16.76/ 22.70 GFLOPS | Progress: (8/20) | 6.07 s
-[Task 9/25] Current/Best: 13.26/ 22.70 GFLOPS | Progress: (12/20) | 8.26 s
-[Task 9/25] Current/Best: 1.93/ 22.70 GFLOPS | Progress: (16/20) | 15.64 s
-[Task 9/25] Current/Best: 7.84/ 22.70 GFLOPS | Progress: (20/20) | 24.22 s Done.
+[Task 9/25] Current/Best: 13.20/ 17.19 GFLOPS | Progress: (4/20) | 3.83 s
+[Task 9/25] Current/Best: 17.28/ 17.28 GFLOPS | Progress: (8/20) | 5.84 s
+[Task 9/25] Current/Best: 9.89/ 17.28 GFLOPS | Progress: (12/20) | 12.46 s
+[Task 9/25] Current/Best: 6.18/ 17.49 GFLOPS | Progress: (16/20) | 16.87 s
+[Task 9/25] Current/Best: 6.23/ 17.49 GFLOPS | Progress: (20/20) | 18.75 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 12.36/ 17.95 GFLOPS | Progress: (4/20) | 3.51 s
-[Task 10/25] Current/Best: 9.95/ 17.95 GFLOPS | Progress: (8/20) | 5.61 s
-[Task 10/25] Current/Best: 9.22/ 17.95 GFLOPS | Progress: (12/20) | 7.46 s
-[Task 10/25] Current/Best: 14.24/ 20.45 GFLOPS | Progress: (16/20) | 9.42 s
-[Task 10/25] Current/Best: 4.72/ 21.68 GFLOPS | Progress: (20/20) | 11.20 s Done.
+[Task 10/25] Current/Best: 19.04/ 19.04 GFLOPS | Progress: (4/20) | 3.53 s
+[Task 10/25] Current/Best: 6.07/ 19.04 GFLOPS | Progress: (8/20) | 5.56 s
+[Task 10/25] Current/Best: 16.13/ 19.04 GFLOPS | Progress: (12/20) | 7.13 s
+[Task 10/25] Current/Best: 12.00/ 19.04 GFLOPS | Progress: (16/20) | 9.86 s
+[Task 10/25] Current/Best: 20.92/ 20.92 GFLOPS | Progress: (20/20) | 12.96 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/ 14.60 GFLOPS | Progress: (4/20) | 4.98 s
-[Task 11/25] Current/Best: 17.06/ 20.86 GFLOPS | Progress: (8/20) | 7.52 s
-[Task 11/25] Current/Best: 15.93/ 20.86 GFLOPS | Progress: (12/20) | 9.51 s
-[Task 11/25] Current/Best: 12.39/ 20.86 GFLOPS | Progress: (16/20) | 13.71 s
-[Task 11/25] Current/Best: 19.57/ 20.86 GFLOPS | Progress: (20/20) | 15.85 s Done.
+[Task 11/25] Current/Best: 18.38/ 19.95 GFLOPS | Progress: (4/20) | 4.20 s
+[Task 11/25] Current/Best: 6.84/ 19.95 GFLOPS | Progress: (8/20) | 7.45 s
+[Task 11/25] Current/Best: 19.38/ 19.95 GFLOPS | Progress: (12/20) | 9.83 s
+[Task 11/25] Current/Best: 19.83/ 20.72 GFLOPS | Progress: (16/20) | 12.39 s
+[Task 11/25] Current/Best: 19.65/ 23.63 GFLOPS | Progress: (20/20) | 15.21 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 13.86/ 13.86 GFLOPS | Progress: (4/20) | 8.40 s
-[Task 12/25] Current/Best: 12.94/ 16.17 GFLOPS | Progress: (8/20) | 10.91 s
-[Task 12/25] Current/Best: 10.06/ 16.17 GFLOPS | Progress: (12/20) | 14.45 s
-[Task 12/25] Current/Best: 15.62/ 16.46 GFLOPS | Progress: (16/20) | 16.38 s
-[Task 12/25] Current/Best: 16.60/ 18.63 GFLOPS | Progress: (20/20) | 19.27 s Done.
+[Task 12/25] Current/Best: 15.89/ 18.14 GFLOPS | Progress: (4/20) | 3.67 s
+[Task 12/25] Current/Best: 20.00/ 20.84 GFLOPS | Progress: (8/20) | 6.04 s
+[Task 12/25] Current/Best: 14.10/ 20.84 GFLOPS | Progress: (12/20) | 8.71 s
+[Task 12/25] Current/Best: 3.01/ 20.84 GFLOPS | Progress: (16/20) | 11.43 s
+[Task 12/25] Current/Best: 15.23/ 20.84 GFLOPS | Progress: (20/20) | 15.97 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 17.53/ 18.98 GFLOPS | Progress: (4/20) | 4.30 s
-[Task 13/25] Current/Best: 6.23/ 20.86 GFLOPS | Progress: (8/20) | 8.35 s
-[Task 13/25] Current/Best: 8.69/ 20.86 GFLOPS | Progress: (12/20) | 10.76 s
-[Task 13/25] Current/Best: 23.31/ 23.31 GFLOPS | Progress: (16/20) | 15.86 s
-[Task 13/25] Current/Best: 6.51/ 23.31 GFLOPS | Progress: (20/20) | 19.42 s Done.
+[Task 13/25] Current/Best: 16.18/ 20.37 GFLOPS | Progress: (4/20) | 4.51 s
+[Task 13/25] Current/Best: 18.51/ 20.37 GFLOPS | Progress: (8/20) | 8.37 s
+[Task 13/25] Current/Best: 18.75/ 20.37 GFLOPS | Progress: (12/20) | 10.62 s
+[Task 13/25] Current/Best: 10.12/ 20.37 GFLOPS | Progress: (16/20) | 14.05 s
+[Task 13/25] Current/Best: 13.03/ 20.37 GFLOPS | Progress: (20/20) | 18.10 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 9.54/ 18.12 GFLOPS | Progress: (4/20) | 5.44 s
-[Task 14/25] Current/Best: 5.41/ 18.12 GFLOPS | Progress: (8/20) | 8.05 s
-[Task 14/25] Current/Best: 12.45/ 18.12 GFLOPS | Progress: (12/20) | 11.34 s
-[Task 14/25] Current/Best: 16.54/ 18.12 GFLOPS | Progress: (16/20) | 13.83 s
-[Task 14/25] Current/Best: 12.44/ 18.12 GFLOPS | Progress: (20/20) | 16.09 s
+[Task 14/25] Current/Best: 11.42/ 17.18 GFLOPS | Progress: (4/20) | 4.42 s
+[Task 14/25] Current/Best: 12.26/ 17.18 GFLOPS | Progress: (8/20) | 7.60 s
+[Task 14/25] Current/Best: 8.23/ 17.18 GFLOPS | Progress: (12/20) | 12.06 s
+[Task 14/25] Current/Best: 12.52/ 17.18 GFLOPS | Progress: (16/20) | 14.83 s
+[Task 14/25] Current/Best: 3.05/ 17.18 GFLOPS | Progress: (20/20) | 17.47 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 6.91/ 22.14 GFLOPS | Progress: (4/20) | 4.10 s
-[Task 15/25] Current/Best: 6.72/ 22.14 GFLOPS | Progress: (8/20) | 5.85 s
-[Task 15/25] Current/Best: 10.96/ 22.14 GFLOPS | Progress: (12/20) | 12.00 s
-[Task 15/25] Current/Best: 13.28/ 22.14 GFLOPS | Progress: (16/20) | 14.34 s
-[Task 15/25] Current/Best: 16.18/ 22.14 GFLOPS | Progress: (20/20) | 16.83 s
-[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
-[Task 16/25] Current/Best: 15.56/ 15.93 GFLOPS | Progress: (4/20) | 3.95 s
-[Task 16/25] Current/Best: 8.90/ 16.70 GFLOPS | Progress: (8/20) | 5.53 s
-[Task 16/25] Current/Best: 14.98/ 16.70 GFLOPS | Progress: (12/20) | 7.50 s
-[Task 16/25] Current/Best: 3.02/ 20.74 GFLOPS | Progress: (16/20) | 9.51 s
-[Task 16/25] Current/Best: 14.99/ 20.74 GFLOPS | Progress: (20/20) | 11.56 s Done.
+[Task 15/25] Current/Best: 3.09/ 17.17 GFLOPS | Progress: (4/20) | 5.20 s
+[Task 15/25] Current/Best: 10.88/ 20.01 GFLOPS | Progress: (8/20) | 8.42 s
+[Task 15/25] Current/Best: 17.47/ 20.01 GFLOPS | Progress: (12/20) | 9.93 s
+[Task 15/25] Current/Best: 23.40/ 23.40 GFLOPS | Progress: (16/20) | 12.70 s Done.
+
+[Task 15/25] Current/Best: 14.46/ 23.40 GFLOPS | Progress: (20/20) | 15.25 s Done.
+
+[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 16/25] Current/Best: 7.48/ 20.30 GFLOPS | Progress: (4/20) | 4.94 s
+[Task 16/25] Current/Best: 14.87/ 21.41 GFLOPS | Progress: (8/20) | 8.55 s
+[Task 16/25] Current/Best: 4.53/ 21.41 GFLOPS | Progress: (12/20) | 10.34 s
+[Task 16/25] Current/Best: 14.50/ 21.41 GFLOPS | Progress: (16/20) | 14.17 s
+[Task 16/25] Current/Best: 16.71/ 21.41 GFLOPS | Progress: (20/20) | 15.79 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 17.56/ 20.79 GFLOPS | Progress: (4/20) | 3.81 s
-[Task 17/25] Current/Best: 12.48/ 20.79 GFLOPS | Progress: (8/20) | 6.58 s
-[Task 17/25] Current/Best: 20.08/ 20.79 GFLOPS | Progress: (12/20) | 8.79 s
-[Task 17/25] Current/Best: 6.18/ 20.79 GFLOPS | Progress: (16/20) | 11.48 s
-[Task 17/25] Current/Best: 12.30/ 20.79 GFLOPS | Progress: (20/20) | 16.02 s Done.
+[Task 17/25] Current/Best: 14.25/ 19.01 GFLOPS | Progress: (4/20) | 4.26 s
+[Task 17/25] Current/Best: 6.22/ 19.01 GFLOPS | Progress: (8/20) | 7.60 s
+[Task 17/25] Current/Best: 19.21/ 19.21 GFLOPS | Progress: (12/20) | 10.32 s
+[Task 17/25] Current/Best: 12.14/ 21.83 GFLOPS | Progress: (16/20) | 13.23 s
+[Task 17/25] Current/Best: 19.73/ 21.83 GFLOPS | Progress: (20/20) | 18.45 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 18.74/ 18.74 GFLOPS | Progress: (4/20) | 4.44 s
-[Task 18/25] Current/Best: 12.62/ 19.42 GFLOPS | Progress: (8/20) | 7.03 s
-[Task 18/25] Current/Best: 10.47/ 19.42 GFLOPS | Progress: (12/20) | 9.98 s
-[Task 18/25] Current/Best: 14.73/ 19.42 GFLOPS | Progress: (16/20) | 12.46 s
-[Task 18/25] Current/Best: 19.46/ 19.46 GFLOPS | Progress: (20/20) | 14.90 s Done.
+[Task 18/25] Current/Best: 10.75/ 16.52 GFLOPS | Progress: (4/20) | 6.59 s
+[Task 18/25] Current/Best: 14.19/ 17.32 GFLOPS | Progress: (8/20) | 8.52 s
+[Task 18/25] Current/Best: 17.25/ 20.94 GFLOPS | Progress: (12/20) | 10.32 s
+[Task 18/25] Current/Best: 11.01/ 20.94 GFLOPS | Progress: (16/20) | 13.95 s
+[Task 18/25] Current/Best: 3.08/ 20.94 GFLOPS | Progress: (20/20) | 21.93 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 21.92/ 21.92 GFLOPS | Progress: (4/20) | 4.48 s
-[Task 19/25] Current/Best: 12.31/ 21.92 GFLOPS | Progress: (8/20) | 8.84 s
-[Task 19/25] Current/Best: 16.71/ 21.92 GFLOPS | Progress: (12/20) | 11.31 s
-[Task 19/25] Current/Best: 17.05/ 21.92 GFLOPS | Progress: (16/20) | 15.57 s
-[Task 19/25] Current/Best: 10.49/ 21.92 GFLOPS | Progress: (20/20) | 20.69 s Done.
+[Task 19/25] Current/Best: 5.97/ 19.06 GFLOPS | Progress: (4/20) | 5.04 s
+[Task 19/25] Current/Best: 14.95/ 19.06 GFLOPS | Progress: (8/20) | 8.26 s
+[Task 19/25] Current/Best: 12.02/ 19.06 GFLOPS | Progress: (12/20) | 11.01 s
+[Task 19/25] Current/Best: 10.88/ 19.06 GFLOPS | Progress: (16/20) | 15.13 s
+[Task 19/25] Current/Best: 12.02/ 19.62 GFLOPS | Progress: (20/20) | 18.74 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 10.23/ 15.16 GFLOPS | Progress: (4/20) | 4.09 s
-[Task 20/25] Current/Best: 14.20/ 16.14 GFLOPS | Progress: (8/20) | 6.96 s
-[Task 20/25] Current/Best: 10.00/ 17.30 GFLOPS | Progress: (12/20) | 8.84 s
-[Task 20/25] Current/Best: 10.55/ 17.30 GFLOPS | Progress: (16/20) | 11.65 s
-[Task 20/25] Current/Best: 14.06/ 18.03 GFLOPS | Progress: (20/20) | 14.55 s
+[Task 20/25] Current/Best: 17.90/ 17.90 GFLOPS | Progress: (4/20) | 4.52 s
+[Task 20/25] Current/Best: 14.66/ 19.48 GFLOPS | Progress: (8/20) | 7.62 s
+[Task 20/25] Current/Best: 10.90/ 19.48 GFLOPS | Progress: (12/20) | 10.71 s
+[Task 20/25] Current/Best: 9.21/ 19.48 GFLOPS | Progress: (16/20) | 13.77 s
+[Task 20/25] Current/Best: 13.99/ 19.48 GFLOPS | Progress: (20/20) | 16.12 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 2.72/ 16.79 GFLOPS | Progress: (4/20) | 4.11 s
-[Task 21/25] Current/Best: 17.12/ 19.92 GFLOPS | Progress: (8/20) | 5.63 s
-[Task 21/25] Current/Best: 7.47/ 19.92 GFLOPS | Progress: (12/20) | 8.18 s
-[Task 21/25] Current/Best: 3.16/ 19.92 GFLOPS | Progress: (16/20) | 11.28 s
-[Task 21/25] Current/Best: 12.48/ 19.92 GFLOPS | Progress: (20/20) | 14.30 s
-[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
-[Task 22/25] Current/Best: 5.17/ 11.12 GFLOPS | Progress: (4/20) | 4.89 s
-[Task 22/25] Current/Best: 10.44/ 20.14 GFLOPS | Progress: (8/20) | 8.31 s
-[Task 22/25] Current/Best: 17.07/ 20.14 GFLOPS | Progress: (12/20) | 9.95 s
-[Task 22/25] Current/Best: 12.16/ 20.14 GFLOPS | Progress: (16/20) | 12.00 s
-[Task 22/25] Current/Best: 16.04/ 20.14 GFLOPS | Progress: (20/20) | 13.59 s Done.
+[Task 21/25] Current/Best: 19.61/ 21.03 GFLOPS | Progress: (4/20) | 4.45 s
+[Task 21/25] Current/Best: 2.66/ 21.03 GFLOPS | Progress: (8/20) | 6.86 s Done.
+
+[Task 21/25] Current/Best: 10.50/ 21.03 GFLOPS | Progress: (12/20) | 9.10 s
+[Task 21/25] Current/Best: 17.50/ 21.03 GFLOPS | Progress: (16/20) | 11.57 s
+[Task 21/25] Current/Best: 6.88/ 21.03 GFLOPS | Progress: (20/20) | 13.71 s
+[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 22/25] Current/Best: 15.06/ 16.36 GFLOPS | Progress: (4/20) | 3.60 s
+[Task 22/25] Current/Best: 8.61/ 16.36 GFLOPS | Progress: (8/20) | 5.48 s
+[Task 22/25] Current/Best: 11.70/ 20.10 GFLOPS | Progress: (12/20) | 7.15 s
+[Task 22/25] Current/Best: 5.26/ 20.26 GFLOPS | Progress: (16/20) | 9.32 s
+[Task 22/25] Current/Best: 16.70/ 20.26 GFLOPS | Progress: (20/20) | 11.59 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 10.64/ 12.22 GFLOPS | Progress: (4/20) | 6.01 s
-[Task 23/25] Current/Best: 17.32/ 19.27 GFLOPS | Progress: (8/20) | 8.42 s
-[Task 23/25] Current/Best: 15.23/ 20.51 GFLOPS | Progress: (12/20) | 10.99 s
-[Task 23/25] Current/Best: 17.18/ 20.51 GFLOPS | Progress: (16/20) | 13.86 s
-[Task 23/25] Current/Best: 11.48/ 20.51 GFLOPS | Progress: (20/20) | 17.80 s Done.
+[Task 23/25] Current/Best: 14.41/ 21.84 GFLOPS | Progress: (4/20) | 4.71 s
+[Task 23/25] Current/Best: 11.99/ 21.84 GFLOPS | Progress: (8/20) | 10.21 s
+[Task 23/25] Current/Best: 2.66/ 21.84 GFLOPS | Progress: (12/20) | 13.31 s
+[Task 23/25] Current/Best: 12.84/ 21.84 GFLOPS | Progress: (16/20) | 15.61 s
+[Task 23/25] Current/Best: 2.65/ 21.84 GFLOPS | Progress: (20/20) | 19.61 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 3.35/ 10.15 GFLOPS | Progress: (4/20) | 3.73 s
-[Task 24/25] Current/Best: 3.66/ 10.15 GFLOPS | Progress: (8/20) | 14.77 s
-[Task 24/25] Current/Best: 2.97/ 10.15 GFLOPS | Progress: (12/20) | 26.43 s
-[Task 24/25] Current/Best: 9.74/ 10.15 GFLOPS | Progress: (16/20) | 37.34 s
-[Task 24/25] Current/Best: 4.10/ 10.15 GFLOPS | Progress: (20/20) | 48.27 s
-[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 5.85/ 5.85 GFLOPS | Progress: (4/20) | 12.45 s Done.
-
-[Task 25/25] Current/Best: 5.80/ 9.31 GFLOPS | Progress: (8/20) | 24.56 s
-[Task 25/25] Current/Best: 7.99/ 9.31 GFLOPS | Progress: (12/20) | 26.73 s
-[Task 25/25] Current/Best: 3.04/ 9.92 GFLOPS | Progress: (16/20) | 37.39 s
-[Task 25/25] Current/Best: 4.47/ 9.92 GFLOPS | Progress: (20/20) | 49.52 s
+[Task 24/25] Current/Best: 2.25/ 2.25 GFLOPS | Progress: (4/20) | 12.22 s
+[Task 24/25] Current/Best: 3.83/ 3.83 GFLOPS | Progress: (8/20) | 23.82 s
+[Task 24/25] Current/Best: 10.31/ 10.31 GFLOPS | Progress: (12/20) | 29.23 s
+[Task 24/25] Current/Best: 1.83/ 10.31 GFLOPS | Progress: (16/20) | 40.22 s
+[Task 24/25] Current/Best: 9.22/ 10.31 GFLOPS | Progress: (20/20) | 51.15 s
+[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
+[Task 25/25] Current/Best: 5.88/ 8.52 GFLOPS | Progress: (4/20) | 4.00 s
+[Task 25/25] Current/Best: 9.01/ 9.01 GFLOPS | Progress: (8/20) | 6.67 s
+[Task 25/25] Current/Best: 1.55/ 9.01 GFLOPS | Progress: (12/20) | 17.36 s
+[Task 25/25] Current/Best: 8.11/ 9.01 GFLOPS | Progress: (16/20) | 26.84 s
+[Task 25/25] Current/Best: 3.01/ 9.01 GFLOPS | Progress: (20/20) | 28.53 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -946,9 +945,9 @@ 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=0.356378
-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 +983,8 @@ 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': 416.40479768999967, 'median': 416.08058430000483, 'std': 1.3672791966956093}
-unoptimized: {'mean': 510.13883835999985, 'median': 509.9613637999994, 'std': 1.3041026659245931}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 410.7700975800026, 'median': 409.9779158500155, 'std': 2.762561622757324}
+unoptimized: {'mean': 516.4660860999993, 'median': 515.8854889500049, 'std': 2.283769529546039}
</pre></div>
</div>
</div>
@@ -999,7 +998,7 @@ 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 26.734 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 11 minutes 18.858 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 4a091f6885..522fe381ea 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>1.286e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.302e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index c467034ab6..62e3e1042c 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, 0x147150f0)), stage(b, placeholder(b, 0xd6f5700)), 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, 0x21e04570)), stage(b, placeholder(b, 0x21a130c0)), 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=[ [...]
</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 ce5fb88717..bc2c6d5790 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>14:39.345</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>14:36.616</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,35 +349,35 @@
</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>11:26.734</p></td>
+<td><p>11:18.858</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>01:18.024</p></td>
+<td><p>01:23.160</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>01:01.240</p></td>
+<td><p>00:59.325</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>00:33.170</p></td>
+<td><p>00:34.327</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>00:17.750</p></td>
+<td><p>00:18.457</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>00:01.457</p></td>
+<td><p>00:01.464</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>00:00.811</p></td>
+<td><p>00:00.832</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>00:00.151</p></td>
+<td><p>00:00.181</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>
@@ -388,11 +388,11 @@
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 72db99b275..5ebe4ac93f 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -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: 0.000007
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000008
</pre></div>
</div>
</div>
@@ -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 7.796779998443526e-06 1.0
- naive 6.7245e-06 0.8624714306857977
-parallel 7.0376999999999996e-06 0.9026418600248998
- vector 2.4567000000000004e-05 3.1509161480642423
+ numpy 7.506630001898884e-06 1.0
+ naive 6.9496e-06 0.92579493038048
+parallel 8.158300000000001e-06 1.0868125907279658
+ vector 2.45937e-05 3.276263781987224
</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: 0.017594
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018913
</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: 3.443148
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.238174
</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: 0.302409
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.317989
</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: 0.335296
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.346038
@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: 0.113586
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.123627
@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: 0.108001
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.109439
@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: 0.110090
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.111450
@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: 0.144855
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.147422
@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 3.4431479605 1.0
- blocking 0.3024088619 0.08782917997403905
- vectorization 0.3352960906 0.09738068025148407
-loop permutation 0.11358641379999998 0.032989117837243745
- array packing 0.10800138470000001 0.031367047230905665
- block caching 0.1100898034 0.03197359063942556
- parallelization 0.1448550779 0.042070535324588466
+ none 3.2381738225 1.0
+ blocking 0.3179892204 0.0982001701670541
+ vectorization 0.3460377255 0.10686199829533703
+loop permutation 0.12362662089999998 0.03817788286749699
+ array packing 0.1094389359 0.03379649824218169
+ block caching 0.11144999250000001 0.034417544767240495
+ parallelization 0.1474216597 0.04552617239867148
</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 1.240 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>