You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/11/05 00:03:19 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@dec74cb93d3460d686f1935f933dc24404c5e995)
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 2491a7950b deploying docs (apache/tvm@dec74cb93d3460d686f1935f933dc24404c5e995)
2491a7950b is described below
commit 2491a7950ba4bcfc29ec1c1c1b891ec98cde318c
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Sat Nov 5 00:03:12 2022 +0000
deploying docs (apache/tvm@dec74cb93d3460d686f1935f933dc24404c5e995)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 332672 -> 332113 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 24174 -> 23380 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 20 +-
.../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 | 1677 ++++++++++----------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 591 ++++++-
.../tune_with_autotvm/sg_execution_times.rst.txt | 8 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 344 +---
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 13 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 57 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 24 +-
.../tutorial/tensor_expr_get_started.rst.txt | 42 +-
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 | 15 +-
docs/how_to/compile_models/from_pytorch.html | 12 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 40 +-
docs/how_to/deploy_models/deploy_prequantized.html | 9 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 36 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../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 | 1677 ++++++++++----------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 591 ++++++-
.../tune_with_autotvm/sg_execution_times.html | 10 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 344 +---
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
...asstvm_1_1tir_1_1DataTypeLegalizer-members.html | 44 +-
.../classtvm_1_1tir_1_1DataTypeLegalizer.html | 82 +-
...vm_1_1tir_1_1DataTypeLegalizer__coll__graph.svg | 20 +-
...1_1tir_1_1DataTypeLegalizer__inherit__graph.svg | 20 +-
...sstvm_1_1tir_1_1ExprMutator__inherit__graph.svg | 20 +-
...m_1_1tir_1_1StmtExprMutator__inherit__graph.svg | 20 +-
...sstvm_1_1tir_1_1StmtMutator__inherit__graph.svg | 20 +-
.../api/doxygen/stmt__functor_8h_source.html | 4 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 8 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 269 ++--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 24 +-
docs/tutorial/tensor_expr_get_started.html | 42 +-
133 files changed, 3760 insertions(+), 3295 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 3f59a37dab..0fd9c0ef04 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 6746d44e45..2b4fe4d842 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 f83a76ced5..cd2db60c0b 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -315,7 +315,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 14.397 seconds)
+ **Total running time of the script:** ( 1 minutes 11.861 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 f07f69707a..c6182cf3f8 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -228,7 +228,7 @@ Look up prediction top 1 index in 1000 class synset.
.. code-block:: none
Relay top-1 id: 285, class name: Egyptian cat
-
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 971ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 950ms/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 67ec756309..9c640694d8 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -115,7 +115,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip3c1a07bd-ecb3-405d-9697-c477b98d1dd0 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipe232925d-da3c-4a18-bed2-a6d0928c330f 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 0c086e2e69..d4c1e1dce3 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -116,7 +116,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:01, 27.7MB/s]
22%|##1 | 8.98M/41.5M [00:00<00:01, 25.2MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 30.7MB/s]
42%|####1 | 17.3M/41.5M [00:00<00:00, 28.6MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 33.8MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 39.0MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 33.2MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 33.4MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
16%|#5 | 6.57M/41.5M [00:00<00:00, 68.8MB/s]
32%|###1 | 13.1M/41.5M [00:00<00:00, 66.9MB/s]
47%|####7 | 19.5M/41.5M [00:00<00:00, 51.7MB/s]
60%|#####9 | 24.8M/41.5M [00:00<00:00, 24.1MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 32.5MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 37.1MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 34.9MB/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 711b53e022..4176982ed7 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -98,7 +98,7 @@ 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]
5%|4 | 2.05M/44.7M [00:00<00:02, 21.2MB/s]
24%|##3 | 10.6M/44.7M [00:00<00:00, 61.2MB/s]
40%|#### | 18.0M/44.7M [00:00<00:00, 68.5MB/s]
55%|#####5 | 24.7M/44.7M [00:00<00:00, 69.3MB/s]
72%|#######1 | 32.0M/44.7M [00:00<00:00, 70.5MB/s]
90%|########9 | 40.0M/44.7M [00:00<00:00, 66.3MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 69.3MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
19%|#8 | 8.41M/44.7M [00:00<00:00, 88.1MB/s]
48%|####8 | 21.6M/44.7M [00:00<00:00, 118MB/s]
74%|#######3 | 32.8M/44.7M [00:00<00:00, 88.5MB/s]
99%|#########8| 44.2M/44.7M [00:00<00:00, 94.1MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 95.7MB/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 971b2caf3c..69b5d31303 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -416,7 +416,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 12.873 seconds)
+ **Total running time of the script:** ( 1 minutes 10.844 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 e061e70005..c5624cda92 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
=================
-**05:53.485** total execution time for **how_to_compile_models** files:
+**05:45.577** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:14.397 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:11.861 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:12.873 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:10.844 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:47.391 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:45.874 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:33.138 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.532 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:31.165 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.407 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.774 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.987 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.760 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.445 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.667 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.190 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.891 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:18.043 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.428 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.394 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 2784e3fa8f..7c20e10c4e 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -434,7 +434,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.7961 15.7501 16.1495 15.6478 0.1481
+ 16.3996 16.5399 16.8385 15.7575 0.3918
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 9a5a3f6bd0..21af748b2e 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
@@ -127,7 +127,7 @@ 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]
4%|3 | 6.30M/170M [00:00<00:08, 20.7MB/s]
5%|5 | 8.94M/170M [00:00<00:07, 22.8MB/s]
9%|9 | 16.0M/170M [00:00<00:04, 34.6MB/s]
14%|#4 | 24.0M/170M [00:00<00:03, 43.6MB/s]
19%|#8 | 32.0M/170M [00:00<00:02, 52.0MB/s]
24%|##3 | 40.0M/170M [00:00<00:02, 60.4MB/s]
29%|##8 | 49.2M/170M [00:01<00:01, 70.5MB/s]
33%|###3 | 56.5M/170M [00:01<00:01, 61.4MB/s]
38%|###7 | 64.0M/170M [00:01<00:01, 57.0MB/s]
44%|####3 | 74.1M/170M [00:01<00:01, 56.7MB/s]
47%|####7 | 80.5M/170M [00:01<00:01, 59.0MB/s]
52%|#####1 | 88.0M/170M [00:01<00:01, 57.2MB/s]
56%|#####5 | 94.3M/170M [00:01<00:01, 52.3MB/s]
59%|#####8 | 99.5M/170M [00:02<00:01, 46.3MB/s]
61%|######1 | 104M/170M [00:02<00:01, 41.7MB/s]
66%|######5 | 112M/170M [00:02<00:01, 45.1MB/s]
71%|####### | 120M/170M [00:02<00:01, 51.4MB/s]
75%|#######5 | 128M/170M [00:02<00:00, 56.4MB/s]
79%|#######9 | 134M/170M [00:02<00:00, 57.3MB/s]
83%|########3 | 141M/170M [00:02<00:00, 61.1MB/s]
87%|########6 | 147M/170M [00:02<00:00, 57.6MB/s]
90%|########9 | 153M/170M [00:03<00:00, 54.1MB/s]
94%|#########4| 160M/170M [00:03<00:00, 56.0MB/s]
98%|#########7| 166M/170M [00:03<00:00, 53.5MB/s]
100%|##########| 170M/170M [00:03<00:00, 51.8MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
9%|8 | 15.0M/170M [00:00<00:01, 157MB/s]
18%|#7 | 30.0M/170M [00:00<00:01, 108MB/s]
24%|##4 | 41.1M/170M [00:00<00:01, 108MB/s]
31%|### | 51.9M/170M [00:00<00:01, 94.9MB/s]
36%|###6 | 61.4M/170M [00:00<00:01, 66.6MB/s]
45%|####4 | 76.2M/170M [00:00<00:01, 86.7MB/s]
56%|#####5 | 94.7M/170M [00:00<00:00, 113MB/s]
64%|######4 | 109M/170M [00:01<00:00, 121MB/s]
72%|#######1 | 122M/170M [00:01<00:00, 97.5MB/s]
79%|#######9 | 134M/170M [00:01<00:00, 98.5MB/s]
87%|########7 | 148M/170M [00:01<00:00, 91.9MB/s]
99%|#########8| 168M/170M [00:01<00:00, 117MB/s]
100%|##########| 170M/170M [00:01<00:00, 103MB/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').
@@ -296,7 +296,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 17.732 seconds)
+ **Total running time of the script:** ( 3 minutes 14.701 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 4a1721622b..1b49fde6ad 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -236,7 +236,7 @@ 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, 45.3MB/s]
91%|######### | 12.3M/13.6M [00:00<00:00, 41.8MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 45.2MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 66.5MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 80.5MB/s]
@@ -418,7 +418,7 @@ 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)
- 90.5724 90.5451 95.0568 90.1166 0.5352
+ 90.5992 90.5281 95.1870 90.2380 0.4903
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.280 seconds)
+ **Total running time of the script:** ( 1 minutes 6.201 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 b790ed694d..117ed86fa8 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -432,7 +432,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.2797 120.2911 122.2328 117.7436 0.4171
+ 120.1178 119.9952 125.3989 119.3251 0.6637
@@ -469,7 +469,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 23.376 seconds)
+ **Total running time of the script:** ( 2 minutes 22.886 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 c51088bc9d..6b44fa563d 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -253,7 +253,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 38.363 seconds)
+ **Total running time of the script:** ( 1 minutes 35.136 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 92d569ffaa..16779a3579 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
@@ -166,7 +166,7 @@ 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 | 4889/132723 [00:00<00:02, 48884.69KB/s]
9%|8 | 11927/132723 [00:00<00:01, 61522.68KB/s]
16%|#5 | 20597/132723 [00:00<00:01, 73015.88KB/s]
22%|##2 | 29298/132723 [00:00<00:01, 78538.42KB/s]
28%|##7 | 37152/132723 [00:00<00:01, 51508.86KB/s]
34%|###4 | 45789/132723 [00:00<00:01, 60311.25KB/s]
40%|###9 | 52802/132723 [00:00<00:01, 60264.44KB/s]
46%|####6 | 61565/132723 [00:00<00:01, 67545.57KB/s]
53%|#####2 | 70178/132723 [00:01<00:00, 72663.19KB/s]
59%|#####9 | 78924/132723 [00:01<00:00, 76839.67KB/s]
66%|######5 | 86976/132723 [00:01<00:00, 69110.32KB/s]
72%|#######2 | 95685/132723 [00:01<00:00, 73909.34KB/s]
78%|#######7 | 103411/132723 [00:01<00:00, 65338.15KB/s]
84%|########4 | 112111/132723 [00:01<00:00, 70886.39KB/s]
90%|######### | 119568/132723 [00:01<00:00, 69278.44KB/s]
97%|########
#6| 128191/132723 [00:01<00:00, 73845.31KB/s]
100%|##########| 132723/132723 [00:01<00:00, 68686.19KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6073/132723 [00:00<00:02, 60726.00KB/s]
11%|# | 14266/132723 [00:00<00:01, 73191.15KB/s]
16%|#6 | 21586/132723 [00:00<00:01, 63785.78KB/s]
22%|##2 | 29818/132723 [00:00<00:01, 70500.02KB/s]
28%|##7 | 37004/132723 [00:00<00:01, 69388.81KB/s]
34%|###4 | 45227/132723 [00:00<00:01, 73532.01KB/s]
40%|###9 | 52659/132723 [00:00<00:01, 68612.56KB/s]
46%|####5 | 60890/132723 [00:00<00:00, 72652.91KB/s]
52%|#####2 | 69047/132723 [00:00<00:00, 75294.74KB/s]
58%|#####8 | 77304/132723 [00:01<00:00, 77455.29KB/s]
64%|######4 | 85116/132723 [00:01<00:00, 74894.97KB/s]
70%|####### | 93223/132723 [00:01<00:00, 76692.38KB/s]
76%|#######6 | 101429/132723 [00:01<00:00, 78267.18KB/s]
83%|########2 | 109560/132723 [00:01<00:00, 79164.39KB/s]
89%|########8 | 117769/132723 [00:01<00:00, 80031.60KB/s]
95%|########
#4| 126032/132723 [00:01<00:00, 80794.05KB/s]
100%|##########| 132723/132723 [00:01<00:00, 74773.55KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 1.135 seconds)
+ **Total running time of the script:** ( 2 minutes 59.158 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 a171c8054a..9185896348 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**12:53.187** total execution time for **how_to_deploy_models** files:
+**12:43.650** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:17.732 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:14.701 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:01.135 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:59.158 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:23.376 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:22.886 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:38.363 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:35.136 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:06.280 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:06.201 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:36.584 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.965 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.163 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:24.957 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.547 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.640 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 598f7b0af7..fffde0d31c 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -472,7 +472,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipa01ac5e8-0e00-4793-8d4f-7a3a0f0bdd52 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipd5949416-3aab-4080-b5de-b79dd81af330 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 2c62ca1330..3dd161b275 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
=================
-**00:47.708** total execution time for **how_to_extend_tvm** files:
+**00:47.430** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:44.242 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:43.996 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.425 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.405 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.034 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.022 | 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 0f4fc3ae51..295b2176e2 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -216,10 +216,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6939us [6939us] (46.29%; 46.29%)
- FoldScaleAxis: 8050us [7us] (53.71%; 53.71%)
- FoldConstant: 8043us [1588us] (53.66%; 99.91%)
- InferType: 6455us [6455us] (43.06%; 80.26%)
+ InferType: 6658us [6658us] (46.18%; 46.18%)
+ FoldScaleAxis: 7759us [5us] (53.82%; 53.82%)
+ FoldConstant: 7753us [1594us] (53.78%; 99.93%)
+ InferType: 6159us [6159us] (42.72%; 79.44%)
@@ -258,10 +258,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6542us [6542us] (45.46%; 45.46%)
- FoldScaleAxis: 7849us [6us] (54.54%; 54.54%)
- FoldConstant: 7843us [1611us] (54.50%; 99.92%)
- InferType: 6232us [6232us] (43.31%; 79.46%)
+ InferType: 6256us [6256us] (44.66%; 44.66%)
+ FoldScaleAxis: 7752us [5us] (55.34%; 55.34%)
+ FoldConstant: 7747us [1624us] (55.31%; 99.94%)
+ InferType: 6123us [6123us] (43.71%; 79.03%)
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 0c9b82aba7..16ac321e06 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 41.513088 ms
+ Convolution: 35.942497 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 f3debc41e0..03270725a1 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
@@ -659,7 +659,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 13.325258 ms
+ conv2d with tensor core: 12.026060 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 b5bf521db9..8872d5265e 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -143,8 +143,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.018412
- Baseline: 3.447995
+ Numpy running time: 0.018568
+ Baseline: 3.441783
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.298499
+ Opt1: 0.296655
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.340025
+ Opt2: 0.331357
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.119436
+ Opt3: 0.115943
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109824
+ Opt4: 0.109887
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111595
+ Opt5: 0.112823
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147733
+ Opt6: 0.147258
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 1f0e319a1f..068599152f 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:35.163** total execution time for **how_to_optimize_operators** files:
+**00:34.862** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.519 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.351 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.555 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.458 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.088 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.054 | 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 5dd54c76bc..71ddf30929 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**09:16.328** total execution time for **how_to_tune_with_autoscheduler** files:
+**08:59.762** 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``) | 05:49.520 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:32.526 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:32.538 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:32.468 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:03.512 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:03.203 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:27.714 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:28.524 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.838 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.928 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.206 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.112 | 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 daef53327d..28c36a091e 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -240,11 +240,11 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [1152]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), 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" = 64 {
conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
@@ -260,422 +260,462 @@ cooperative fetching, unrolling and operator fusion.
conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
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" = 56;
- 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[(((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" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 56), 81)) && (floormod((threadIdx.x_1 + 56), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 56), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 31), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 6), 81)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 6), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 62), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 37), 81)) && (floormod((threadIdx.x_1 + 37), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 37), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- 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[((((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" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 43), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else((((threadIdx.x_1 < 54) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 504), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 2)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 74), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 74), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else((((threadIdx.x_1 < 23) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 616), 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_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 56), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 112), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 168), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 224), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 280), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 336), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 448), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 560), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 616), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 672), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 728), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 784), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 840), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 896), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 952), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1064), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_2 < 32), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1120), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- }
- for (ry.outer.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 327)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 408)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 489)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 570)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 328)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 409)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 490)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 571)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 410)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 491)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 572)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 330)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 411)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 492)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 573)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 327)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 408)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 489)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 570)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 328)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 409)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 490)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 571)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 410)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 491)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 572)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 330)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 411)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 492)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 573)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 327)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 408)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 489)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 570)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 328)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 409)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 490)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 571)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 410)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 491)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 572)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 330)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 411)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 492)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 573)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 331)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 412)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 493)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 327)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 408)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 489)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 570)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 328)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 409)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 490)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 571)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 410)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 491)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 572)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 330)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 411)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 492)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 573)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 331)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 412)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 493)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 327)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 408)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 489)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 570)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 328)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 409)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 490)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 571)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 410)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 491)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 572)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 330)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 411)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 492)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 573)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 331)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 412)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 493)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 89)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 170)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 251)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 332)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 413)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 494)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 575)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 327)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 408)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 489)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 570)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 328)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 409)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 490)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 571)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 410)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 491)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 572)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 330)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 411)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 492)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 573)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 331)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 412)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 493)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 89)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 170)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 251)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 332)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 413)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 494)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 575)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*72)
+ let cse_var_1: int32 = (ry.outer.outer*3)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f3 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
for (i1.inner: int32, 0, 2) {
for (i3.inner: int32, 0, 7) {
- compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
}
}
}
@@ -731,7 +771,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.256 ms
+ Execution time of this operator: 0.367 ms
@@ -781,20 +821,20 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- 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_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=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 [...]
@@ -802,10 +842,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
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)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
@@ -828,12 +868,12 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+ 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=64)
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)
+ 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=4)
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=56)
+ 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=64)
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, "unroll_explicit", True)
@@ -853,10 +893,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[1152];
+ __shared__ float pad_temp_shared[72];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -872,387 +912,410 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
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) + 56)] = (((((9 <= ((((int)threadIdx.x) + 56) % 81)) && (((((int)threadIdx.x) + 56) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 81) * 49)) + ((((((int)threadIdx.x) + 56) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 81) * 49)) + (((((int)threadIdx.x) + 6) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((9 <= ((((int)threadIdx.x) + 37) % 81)) && (((((int)threadIdx.x) + 37) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 81) * 49)) + ((((((int)threadIdx.x) + 37) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 81) * 49)) + (((((int)threadIdx.x) + 12) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 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) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 504)] = ((((((int)threadIdx.x) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 504) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[(((int)threadIdx.x) + 616)] = ((((((int)threadIdx.x) < 23) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 616) / 81) * 49)) + (((((int)threadIdx.x) + 49) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 73728) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 616)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 616) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 728)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 728) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 840)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 840) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 952)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 952) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1064) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 32) {
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- }
- __syncthreads();
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 327)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 408)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 489)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 328)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 409)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 490)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 410)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 491)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 330)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 411)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 492)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 327)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 408)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 489)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 328)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 409)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 490)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 410)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 491)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 330)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 411)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 492)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 327)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 408)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 489)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 328)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 409)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 490)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 410)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 491)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 330)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 411)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 492)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 331)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 412)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 493)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 327)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 408)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 489)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 328)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 409)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 490)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 410)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 491)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 330)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 411)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 492)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 331)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 412)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 493)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 327)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 408)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 489)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 328)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 409)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 490)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 410)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 491)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 330)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 411)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 492)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 331)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 412)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 493)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 89)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 170)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 251)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 332)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 413)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 494)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 575)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 327)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 408)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 489)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 328)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 409)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 490)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 410)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 491)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 330)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 411)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 492)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 331)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 412)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 493)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 89)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 170)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 251)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 332)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 413)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 494)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 575)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
}
@@ -1315,7 +1378,7 @@ 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 49.520 seconds)
+ **Total running time of the script:** ( 5 minutes 32.526 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 0fb643de80..a39e0da216 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -643,7 +643,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.2173 8.2218 8.2245 8.2056 0.0084
+ 8.1633 8.1624 8.1698 8.1577 0.0050
@@ -671,7 +671,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 3.512 seconds)
+ **Total running time of the script:** ( 1 minutes 3.203 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 24b6859701..2aad4a086d 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -662,7 +662,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 757.1168 757.0810 757.9855 756.2840 0.6951
+ 762.6226 762.3649 764.3096 761.1933 1.2852
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 32.538 seconds)
+ **Total running time of the script:** ( 1 minutes 32.468 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 0017a67f34..2cf12805f6 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
@@ -386,78 +386,527 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
- for (i.outer.inner: int32, 0, 8) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 4) {
- let cse_var_1: int32 = (((i.outer.inner*128) + (i.inner.init*32)) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [1024], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
- }
- }
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 4) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_19: int32 = (((i.outer.inner*128) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_18: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.outer.inner*1024)) + (i.inner*256))
- let cse_var_17: int32 = (cse_var_19 + 9)
- let cse_var_16: int32 = (cse_var_19 + 8)
- let cse_var_15: int32 = (cse_var_19 + 7)
- let cse_var_14: int32 = (cse_var_19 + 6)
- let cse_var_13: int32 = (cse_var_19 + 5)
- let cse_var_12: int32 = (cse_var_19 + 4)
- let cse_var_11: int32 = (cse_var_19 + 3)
- let cse_var_10: int32 = (cse_var_19 + 2)
- let cse_var_9: int32 = (cse_var_19 + 15)
- let cse_var_8: int32 = (cse_var_19 + 14)
- let cse_var_7: int32 = (cse_var_19 + 13)
- let cse_var_6: int32 = (cse_var_19 + 12)
- let cse_var_5: int32 = (cse_var_19 + 11)
- let cse_var_4: int32 = (cse_var_19 + 10)
- let cse_var_3: int32 = (cse_var_19 + 1)
- {
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- }
- }
- }
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+ for (i0.outer: int32, 0, 16) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global;
+ for (i1.outer: int32, 0, 32) {
+ compute_5: Buffer(compute_4, float32, [128], [])[0] = 0f32
+ compute_5[1] = 0f32
+ compute_5[2] = 0f32
+ compute_5[3] = 0f32
+ compute_5[4] = 0f32
+ compute_5[5] = 0f32
+ compute_5[6] = 0f32
+ compute_5[7] = 0f32
+ compute_5[8] = 0f32
+ compute_5[9] = 0f32
+ compute_5[10] = 0f32
+ compute_5[11] = 0f32
+ compute_5[12] = 0f32
+ compute_5[13] = 0f32
+ compute_5[14] = 0f32
+ compute_5[15] = 0f32
+ compute_5[16] = 0f32
+ compute_5[17] = 0f32
+ compute_5[18] = 0f32
+ compute_5[19] = 0f32
+ compute_5[20] = 0f32
+ compute_5[21] = 0f32
+ compute_5[22] = 0f32
+ compute_5[23] = 0f32
+ compute_5[24] = 0f32
+ compute_5[25] = 0f32
+ compute_5[26] = 0f32
+ compute_5[27] = 0f32
+ compute_5[28] = 0f32
+ compute_5[29] = 0f32
+ compute_5[30] = 0f32
+ compute_5[31] = 0f32
+ compute_5[32] = 0f32
+ compute_5[33] = 0f32
+ compute_5[34] = 0f32
+ compute_5[35] = 0f32
+ compute_5[36] = 0f32
+ compute_5[37] = 0f32
+ compute_5[38] = 0f32
+ compute_5[39] = 0f32
+ compute_5[40] = 0f32
+ compute_5[41] = 0f32
+ compute_5[42] = 0f32
+ compute_5[43] = 0f32
+ compute_5[44] = 0f32
+ compute_5[45] = 0f32
+ compute_5[46] = 0f32
+ compute_5[47] = 0f32
+ compute_5[48] = 0f32
+ compute_5[49] = 0f32
+ compute_5[50] = 0f32
+ compute_5[51] = 0f32
+ compute_5[52] = 0f32
+ compute_5[53] = 0f32
+ compute_5[54] = 0f32
+ compute_5[55] = 0f32
+ compute_5[56] = 0f32
+ compute_5[57] = 0f32
+ compute_5[58] = 0f32
+ compute_5[59] = 0f32
+ compute_5[60] = 0f32
+ compute_5[61] = 0f32
+ compute_5[62] = 0f32
+ compute_5[63] = 0f32
+ compute_5[64] = 0f32
+ compute_5[65] = 0f32
+ compute_5[66] = 0f32
+ compute_5[67] = 0f32
+ compute_5[68] = 0f32
+ compute_5[69] = 0f32
+ compute_5[70] = 0f32
+ compute_5[71] = 0f32
+ compute_5[72] = 0f32
+ compute_5[73] = 0f32
+ compute_5[74] = 0f32
+ compute_5[75] = 0f32
+ compute_5[76] = 0f32
+ compute_5[77] = 0f32
+ compute_5[78] = 0f32
+ compute_5[79] = 0f32
+ compute_5[80] = 0f32
+ compute_5[81] = 0f32
+ compute_5[82] = 0f32
+ compute_5[83] = 0f32
+ compute_5[84] = 0f32
+ compute_5[85] = 0f32
+ compute_5[86] = 0f32
+ compute_5[87] = 0f32
+ compute_5[88] = 0f32
+ compute_5[89] = 0f32
+ compute_5[90] = 0f32
+ compute_5[91] = 0f32
+ compute_5[92] = 0f32
+ compute_5[93] = 0f32
+ compute_5[94] = 0f32
+ compute_5[95] = 0f32
+ compute_5[96] = 0f32
+ compute_5[97] = 0f32
+ compute_5[98] = 0f32
+ compute_5[99] = 0f32
+ compute_5[100] = 0f32
+ compute_5[101] = 0f32
+ compute_5[102] = 0f32
+ compute_5[103] = 0f32
+ compute_5[104] = 0f32
+ compute_5[105] = 0f32
+ compute_5[106] = 0f32
+ compute_5[107] = 0f32
+ compute_5[108] = 0f32
+ compute_5[109] = 0f32
+ compute_5[110] = 0f32
+ compute_5[111] = 0f32
+ compute_5[112] = 0f32
+ compute_5[113] = 0f32
+ compute_5[114] = 0f32
+ compute_5[115] = 0f32
+ compute_5[116] = 0f32
+ compute_5[117] = 0f32
+ compute_5[118] = 0f32
+ compute_5[119] = 0f32
+ compute_5[120] = 0f32
+ compute_5[121] = 0f32
+ compute_5[122] = 0f32
+ compute_5[123] = 0f32
+ compute_5[124] = 0f32
+ compute_5[125] = 0f32
+ compute_5[126] = 0f32
+ compute_5[127] = 0f32
+ for (elem_idx: int32, 0, (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])) {
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[0] = (compute_5[0] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[1] = (compute_5[1] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[2] = (compute_5[2] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[3] = (compute_5[3] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[4] = (compute_5[4] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[5] = (compute_5[5] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[6] = (compute_5[6] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[7] = (compute_5[7] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[8] = (compute_5[8] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[9] = (compute_5[9] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[10] = (compute_5[10] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[11] = (compute_5[11] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[12] = (compute_5[12] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[13] = (compute_5[13] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[14] = (compute_5[14] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[15] = (compute_5[15] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[16] = (compute_5[16] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[17] = (compute_5[17] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[18] = (compute_5[18] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[19] = (compute_5[19] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[20] = (compute_5[20] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[21] = (compute_5[21] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[22] = (compute_5[22] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[23] = (compute_5[23] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[24] = (compute_5[24] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[25] = (compute_5[25] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[26] = (compute_5[26] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[27] = (compute_5[27] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[28] = (compute_5[28] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[29] = (compute_5[29] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[30] = (compute_5[30] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[31] = (compute_5[31] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[32] = (compute_5[32] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[33] = (compute_5[33] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[34] = (compute_5[34] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[35] = (compute_5[35] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[36] = (compute_5[36] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[37] = (compute_5[37] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[38] = (compute_5[38] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[39] = (compute_5[39] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[40] = (compute_5[40] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[41] = (compute_5[41] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[42] = (compute_5[42] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[43] = (compute_5[43] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[44] = (compute_5[44] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[45] = (compute_5[45] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[46] = (compute_5[46] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[47] = (compute_5[47] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[48] = (compute_5[48] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[49] = (compute_5[49] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[50] = (compute_5[50] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[51] = (compute_5[51] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[52] = (compute_5[52] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[53] = (compute_5[53] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[54] = (compute_5[54] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[55] = (compute_5[55] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[56] = (compute_5[56] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[57] = (compute_5[57] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[58] = (compute_5[58] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[59] = (compute_5[59] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[60] = (compute_5[60] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[61] = (compute_5[61] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[62] = (compute_5[62] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[63] = (compute_5[63] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[64] = (compute_5[64] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[65] = (compute_5[65] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[66] = (compute_5[66] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[67] = (compute_5[67] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[68] = (compute_5[68] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[69] = (compute_5[69] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[70] = (compute_5[70] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[71] = (compute_5[71] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[72] = (compute_5[72] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[73] = (compute_5[73] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[74] = (compute_5[74] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[75] = (compute_5[75] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[76] = (compute_5[76] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[77] = (compute_5[77] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[78] = (compute_5[78] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[79] = (compute_5[79] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[80] = (compute_5[80] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[81] = (compute_5[81] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[82] = (compute_5[82] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[83] = (compute_5[83] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[84] = (compute_5[84] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[85] = (compute_5[85] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[86] = (compute_5[86] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[87] = (compute_5[87] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[88] = (compute_5[88] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[89] = (compute_5[89] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[90] = (compute_5[90] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[91] = (compute_5[91] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[92] = (compute_5[92] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[93] = (compute_5[93] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[94] = (compute_5[94] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[95] = (compute_5[95] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[96] = (compute_5[96] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[97] = (compute_5[97] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[98] = (compute_5[98] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[99] = (compute_5[99] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[100] = (compute_5[100] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[101] = (compute_5[101] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[102] = (compute_5[102] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[103] = (compute_5[103] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[104] = (compute_5[104] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[105] = (compute_5[105] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[106] = (compute_5[106] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[107] = (compute_5[107] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[108] = (compute_5[108] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[109] = (compute_5[109] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[110] = (compute_5[110] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[111] = (compute_5[111] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[112] = (compute_5[112] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[113] = (compute_5[113] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[114] = (compute_5[114] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[115] = (compute_5[115] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[116] = (compute_5[116] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[117] = (compute_5[117] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[118] = (compute_5[118] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[119] = (compute_5[119] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[120] = (compute_5[120] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[121] = (compute_5[121] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[122] = (compute_5[122] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[123] = (compute_5[123] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[124] = (compute_5[124] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[125] = (compute_5[125] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[126] = (compute_5[126] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[127] = (compute_5[127] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
}
}
- for (i0.inner: int32, 0, 32) {
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 8) {
+ let cse_var_1: int32 = (((i0.outer*4096) + (i0.inner*512)) + (i1.outer*16))
+ compute[ramp(cse_var_1, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_1, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -513,7 +962,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 2.150 ms
+ Execution time of this operator: 2.699 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 68a3831c8c..9e0951e2f9 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**00:46.539** total execution time for **how_to_tune_with_autotvm** files:
+**00:34.526** 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``) | 00:46.503 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:34.489 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.007 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 5e24449533..0f0553f711 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
@@ -265,7 +265,8 @@ for this template
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ No: 1 GFLOPS: 52.03/52.03 result: MeasureResult(costs=(0.00444939392,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1304433345794678, timestamp=1667601805.408173) [('tile_f', [-1, 4, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,652190
+ No: 2 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -387,8 +388,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8867353
- No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7734574
+ No: 3 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -510,8 +511,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3861445
- No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7832639
+ No: 4 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -633,8 +634,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2667763
- 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, 64, 1, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7281042
+ No: 5 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -756,8 +757,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5933042
- 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, 1, 64, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6032563
+ No: 6 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -879,8 +880,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3974552
- No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4588891
+ No: 7 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1002,27 +1003,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3460448
- No: 7 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
- res = future.result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
- return self.__get_result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
- raise self._exception
- File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
- result = self.fn(*self.args, **self.kwargs)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
- worker = lambda *args: self._worker_run(*args)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
- return proc.recv()
- File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
- raise TimeoutError()
- TimeoutError
-
- [('tile_f', [-1, 8, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10078971
- No: 8 GFLOPS: 95.85/95.85 result: MeasureResult(costs=(0.0024152576521739126,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.324777364730835, timestamp=1667594985.9287496) [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2135492
- No: 9 GFLOPS: 0.00/95.85 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10015472
+ No: 8 GFLOPS: 41.42/52.03 result: MeasureResult(costs=(0.005589530499999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.621019124984741, timestamp=1667601811.0111692) [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4850626
+ No: 9 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1144,9 +1127,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8378868
- No: 10 GFLOPS: 183.75/183.75 result: MeasureResult(costs=(0.0012598921894736842,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.1338655948638916, timestamp=1667594989.324478) [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7123640
- No: 11 GFLOPS: 0.00/183.75 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8572150
+ No: 10 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1268,8 +1250,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10395604
- No: 12 GFLOPS: 0.00/183.75 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10334589
+ No: 11 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1391,11 +1373,13 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5547316
- No: 13 GFLOPS: 91.25/183.75 result: MeasureResult(costs=(0.002536974911111111,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3203299045562744, timestamp=1667594992.4279962) [('tile_f', [-1, 2, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,239011
- No: 14 GFLOPS: 120.98/183.75 result: MeasureResult(costs=(0.0019135878333333331,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0510101318359375, timestamp=1667594993.4070063) [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9362896
- No: 15 GFLOPS: 226.29/226.29 result: MeasureResult(costs=(0.0010230270188679245,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1771631240844727, timestamp=1667594994.0688612) [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,239890
- No: 16 GFLOPS: 0.00/226.29 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1414509
+ No: 12 GFLOPS: 6.99/52.03 result: MeasureResult(costs=(0.033106311750000006,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4201440811157227, timestamp=1667601813.6674936) [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8875092
+ No: 13 GFLOPS: 3.77/52.03 result: MeasureResult(costs=(0.06132851025,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.819613695144653, timestamp=1667601818.6682076) [('tile_f', [-1, 1, 2, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,6983210
+ No: 14 GFLOPS: 124.47/124.47 result: MeasureResult(costs=(0.0018598417962962961,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4296081066131592, timestamp=1667601819.3106053) [('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2724816
+ No: 15 GFLOPS: 75.91/124.47 result: MeasureResult(costs=(0.003049750333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.5480942726135254, timestamp=1667601819.9488645) [('tile_f', [-1, 4, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9891422
+ No: 16 GFLOPS: 292.09/292.09 result: MeasureResult(costs=(0.0007925611317829458,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8134474754333496, timestamp=1667601820.614421) [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8916687
+ No: 17 GFLOPS: 0.00/292.09 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1517,26 +1501,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5363060
- No: 17 GFLOPS: 0.00/226.29 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
- res = future.result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
- return self.__get_result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
- raise self._exception
- File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
- result = self.fn(*self.args, **self.kwargs)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
- worker = lambda *args: self._worker_run(*args)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
- return proc.recv()
- File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
- raise TimeoutError()
- TimeoutError
-
- [('tile_f', [-1, 8, 8, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8168064
- No: 18 GFLOPS: 0.00/226.29 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9800932
+ No: 18 GFLOPS: 10.11/292.09 result: MeasureResult(costs=(0.022908447166666665,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7610547542572021, timestamp=1667601822.5637784) [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5355174
+ No: 19 GFLOPS: 0.00/292.09 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1658,253 +1625,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9441420
- No: 19 GFLOPS: 0.00/226.29 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 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:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
- Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 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:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4945734
- No: 20 GFLOPS: 0.00/226.29 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 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:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
- Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 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:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4624755
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 1]), ('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, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2966493
+ No: 20 GFLOPS: 30.46/292.09 result: MeasureResult(costs=(0.0075998355,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.213226318359375, timestamp=1667601823.2526355) [('tile_f', [-1, 16, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3484859
@@ -1959,9 +1681,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,239890
+ [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8916687
Finish loading 20 records
- Time cost of this operator: 0.001338
+ Time cost of this operator: 0.001197
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 40808431b9..4ee45bd183 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -327,10 +327,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.7 98.716 (1, 2, 10, 10, 3) 2 1 [310.7]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.062 0.973 (1, 6, 10, 10) 1 1 [3.062]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.978 0.311 (1, 1, 10, 10, 3) 1 1 [0.978]
- Total_time - 314.741 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.0 98.727 (1, 2, 10, 10, 3) 2 1 [310.0]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.022 0.962 (1, 6, 10, 10) 1 1 [3.022]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.976 0.311 (1, 1, 10, 10, 3) 1 1 [0.976]
+ Total_time - 313.997 - - - - -
@@ -394,10 +394,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 174.1 98.262 (1, 1, 10, 10, 6) 2 1 [174.1]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.233 1.261 (1, 6, 10, 10) 1 1 [2.233]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.845 0.477 (1, 3, 10, 10, 1) 1 1 [0.845]
- Total_time - 177.179 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.2 97.318 (1, 6, 10, 10, 1) 2 1 [100.2]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.77 1.719 (1, 6, 10, 10) 1 1 [1.77]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.991 0.963 (1, 1, 10, 10, 3) 1 1 [0.991]
+ Total_time - 102.961 - - - - -
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 ddffb623ec..7ef38e8a57 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -225,7 +225,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmp4gz4usf4/images/random'
+ '/tmp/tmpgluqejqp/images/random'
@@ -316,7 +316,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
+ :alt: [1.0, 0.0], [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], [1.0, 0.0], [0.0, 1.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp4gz4usf4/images/target contains 8144 images
- /tmp/tmp4gz4usf4/images/random contains 5000 images
+ /tmp/tmpgluqejqp/images/target contains 8144 images
+ /tmp/tmpgluqejqp/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 46s - loss: 0.2163 - accuracy: 0.9276 - val_loss: 0.1432 - val_accuracy: 0.9532 - 46s/epoch - 141ms/step
+ 328/328 - 47s - loss: 0.2240 - accuracy: 0.9252 - val_loss: 0.2493 - val_accuracy: 0.9173 - 47s/epoch - 143ms/step
Epoch 2/3
- 328/328 - 44s - loss: 0.0952 - accuracy: 0.9652 - val_loss: 0.1278 - val_accuracy: 0.9585 - 44s/epoch - 133ms/step
+ 328/328 - 43s - loss: 0.0901 - accuracy: 0.9658 - val_loss: 0.1571 - val_accuracy: 0.9532 - 43s/epoch - 132ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0709 - accuracy: 0.9754 - val_loss: 0.1108 - val_accuracy: 0.9630 - 43s/epoch - 131ms/step
+ 328/328 - 43s - loss: 0.0640 - accuracy: 0.9754 - val_loss: 0.1400 - val_accuracy: 0.9535 - 43s/epoch - 132ms/step
- <keras.callbacks.History object at 0x7fe2d4297190>
+ <keras.callbacks.History object at 0x7f76be7e4590>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 42.250 seconds)
+ **Total running time of the script:** ( 4 minutes 38.646 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 8d9951ac64..73c6aee316 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**05:44.133** total execution time for **how_to_work_with_microtvm** files:
+**05:39.446** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:42.250 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:38.646 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:49.972 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:49.358 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.224 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.718 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.686 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.722 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 0b064e71c2..adba94052c 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
=================
-**00:44.013** total execution time for **how_to_work_with_relay** files:
+**00:43.480** 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``) | 00:31.883 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.638 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.333 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.128 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.790 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.707 | 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 b8edaba802..67a102faf3 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -261,7 +261,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7fe2f6607950>
+ <function my_cuda_math_rule at 0x7f770e8c5320>
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 14b09b3244..41626ef759 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
=================
-**00:06.318** total execution time for **how_to_work_with_schedules** files:
+**00:06.008** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:03.915 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:03.693 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.087 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.007 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.557 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.548 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.539 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.114 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.116 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.049 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.028 | 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``) | 00:00.020 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.019 | 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 d9b2a33499..55be8928ec 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp1pmklucr/input0.cc'\nsource_filename = \"/tmp/tmp1pmklucr/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/tmp2l4a8w3x/input0.cc'\nsource_filename = \"/tmp/tmp2l4a8w3x/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 ad34812c96..2856016e8a 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:26.720** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:26.196** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.713 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.190 | 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 c00f372112..fdd43242df 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -289,7 +289,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 29.24s!
+ resnet18_v1 inference graph built in 28.99s!
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 bb4f36a79f..775c421dad 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -333,7 +333,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 19.28s!
+ yolov3-tiny inference graph built in 19.58s!
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 39be379cd6..cee700ea9f 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
=================
-**01:40.688** total execution time for **topic_vta_tutorials_frontend** files:
+**01:40.948** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.637 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.872 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:49.050 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:49.076 | 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 4b245601e4..baf5ffa606 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
=================
-**00:03.101** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.100** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.652 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.662 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.448 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.438 | 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 3d9693b462..036830bcae 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
=================
-**00:00.791** total execution time for **topic_vta_tutorials** files:
+**00:00.781** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.431 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.416 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.360 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.365 | 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 992e56f7e6..326c9e12fb 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -203,6 +203,13 @@ trials, we can load the best schedule from the log file and apply it.
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+ *E
+
+
@@ -326,7 +333,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 94.078 ms
+ Execution time of this operator: 93.653 ms
@@ -426,7 +433,7 @@ 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
@@ -444,7 +451,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 40.168 seconds)
+ **Total running time of the script:** ( 1 minutes 34.020 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 9014a495f3..6dc3f29e56 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -450,16 +450,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 0.87/0.87 result: MeasureResult(costs=(0.30763721039999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.060778856277466, timestamp=1667593583.5547442) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 2 GFLOPS: 9.66/9.66 result: MeasureResult(costs=(0.027783903800000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6733083724975586, timestamp=1667593584.2113993) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
- No: 3 GFLOPS: 3.11/9.66 result: MeasureResult(costs=(0.08638878959999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5278198719024658, timestamp=1667593586.5010383) [('tile_y', [-1, 128]), ('tile_x', [-1, 8])],None,37
- No: 4 GFLOPS: 9.06/9.66 result: MeasureResult(costs=(0.029624541799999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6877274513244629, timestamp=1667593587.878154) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
- No: 5 GFLOPS: 9.54/9.66 result: MeasureResult(costs=(0.0281495106,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6045265197753906, timestamp=1667593588.603293) [('tile_y', [-1, 4]), ('tile_x', [-1, 32])],None,52
- No: 6 GFLOPS: 3.68/9.66 result: MeasureResult(costs=(0.07299436620000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.327251672744751, timestamp=1667593589.9378283) [('tile_y', [-1, 128]), ('tile_x', [-1, 16])],None,47
- No: 7 GFLOPS: 2.78/9.66 result: MeasureResult(costs=(0.0964121712,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6885387897491455, timestamp=1667593592.3896403) [('tile_y', [-1, 16]), ('tile_x', [-1, 4])],None,24
- No: 8 GFLOPS: 1.57/9.66 result: MeasureResult(costs=(0.1714148756,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9228270053863525, timestamp=1667593595.337938) [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
- No: 9 GFLOPS: 3.92/9.66 result: MeasureResult(costs=(0.0684951524,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.240407943725586, timestamp=1667593596.6913493) [('tile_y', [-1, 64]), ('tile_x', [-1, 16])],None,46
- No: 10 GFLOPS: 12.53/12.53 result: MeasureResult(costs=(0.0214292146,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4738461971282959, timestamp=1667593597.2032459) [('tile_y', [-1, 32]), ('tile_x', [-1, 128])],None,75
+ No: 1 GFLOPS: 9.11/9.11 result: MeasureResult(costs=(0.0294639272,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.704277515411377, timestamp=1667600439.8011644) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
+ No: 2 GFLOPS: 12.36/12.36 result: MeasureResult(costs=(0.0217097956,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5637028217315674, timestamp=1667600440.3613122) [('tile_y', [-1, 64]), ('tile_x', [-1, 256])],None,86
+ No: 3 GFLOPS: 11.60/12.36 result: MeasureResult(costs=(0.0231313244,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5525696277618408, timestamp=1667600441.6351473) [('tile_y', [-1, 32]), ('tile_x', [-1, 32])],None,55
+ No: 4 GFLOPS: 1.47/12.36 result: MeasureResult(costs=(0.1826311896,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.058821201324463, timestamp=1667600445.453223) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.93/12.36 result: MeasureResult(costs=(0.0683016298,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.27158522605896, timestamp=1667600446.8736937) [('tile_y', [-1, 64]), ('tile_x', [-1, 16])],None,46
+ No: 6 GFLOPS: 14.41/14.41 result: MeasureResult(costs=(0.0186263354,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5002939701080322, timestamp=1667600447.3361092) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
+ No: 7 GFLOPS: 3.38/14.41 result: MeasureResult(costs=(0.0793295266,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4188477993011475, timestamp=1667600449.5113862) [('tile_y', [-1, 8]), ('tile_x', [-1, 8])],None,33
+ No: 8 GFLOPS: 1.55/14.41 result: MeasureResult(costs=(0.1729946346,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9581708908081055, timestamp=1667600452.491676) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 9 GFLOPS: 12.10/14.41 result: MeasureResult(costs=(0.022181018,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.48445558547973633, timestamp=1667600453.0983562) [('tile_y', [-1, 256]), ('tile_x', [-1, 256])],None,88
+ No: 10 GFLOPS: 4.09/14.41 result: MeasureResult(costs=(0.065693861,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.17677903175354, timestamp=1667600454.3130083) [('tile_y', [-1, 8]), ('tile_x', [-1, 16])],None,43
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 4945dadf25..32f79745f5 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -320,7 +320,7 @@ standard deviation.
.. code-block:: none
- {'mean': 510.44585038999804, 'median': 510.26684924999586, 'std': 2.741325791063284}
+ {'mean': 513.8701477699988, 'median': 513.6327808999965, 'std': 1.3264686737052278}
@@ -554,30 +554,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 10.97/ 15.56 GFLOPS | Progress: (4/20) | 7.20 s
[Task 1/25] Current/Best: 15.42/ 17.50 GFLOPS | Progress: (8/20) | 9.66 s
[Task 1/25] Current/Best: 7.64/ 17.50 GFLOPS | Progress: (12/20) | 12.37 s
[Task 1/25] Current/Best: 8.41/ 22.79 GFLOPS | Progress: (16/20) | 15.80 s
[Task 1/25] Current/Best: 10.72/ 23.50 GFLOPS | Progress: (20/20) | 17.55 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 18.41/ 18.41 GFLOPS | Progress: (4/20) | 2.78 s
[Task 2/25] Current/Best: 6.38/ 18.41 GFLOPS | Progress: (8/20) | 4.44 s
[Task 2/25] Current/Best: 11.63/ 19.11 GFLOPS | Progress: (12/20) | 6.11 s
[Task 2/25] Current/Best: 8.92/ 19.11 GFLOPS | Progress: (16/20) | 7.44 s
[Task 2/25] Current/Best: 7.13/ 19.11 GFLOPS | Progress: (20/20) | 8.78 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 9.50/ 15.56 GFLOPS | Progress: (4/20) | 4.34 s
[Task 3/25] Current/Best: 10.01/ 17.03 GFLOPS | Progress: (8/20) | 6.48 s
[Task 3/25] Current/Best: 11.91/ 19.02 GFLOPS | Progress: (12/20) | 9.16 s
[Task 3/25] Current/Best: 22.81/ 22.81 GFLOPS | Progress: (16/20) | 12.45 s
[Task 3/25] Current/Best: 18.50/ 23.12 GFLOPS | Progress: (20/20) | 14.36 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 11.17/ 11.73 GFLOPS | Progress: (4/20) | 3.81 s
[Task 4/25] Current/Best: 13.71/ 16.42 GFLOPS | Progress: (8/20) | 5.27 s
[Task 4/25] Current/Best: 9.45/ 17.70 GFLOPS | Progress: (12/20) | 7.48 s
[Task 4/25] Current/Best: 9.58/ 17.70 GFLOPS | Progress: (16/20) | 10.22 s
[Task 4/25] Current/Best: 10.66/ 17.70 GFLOPS | Progress: (20/20) | 13.10 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 13.90/ 18.06 GFLOPS | Progress: (4/20) | 3.10 s
[Task 5/25] Current/Best: 14.39/ 18.06 GFLOPS | Progress: (8/20) | 5.13 s
[Task 5/25] Current/Best: 11.56/ 18.06 GFLOPS | Progress: (12/20) | 7.49 s
[Task 5/25] Current/Best: 5.01/ 18.06 GFLOPS | Progress: (16/20) | 9.42 s
[Task 5/25] Current/Best: 6.77/ 18.06 GFLOPS | Progress: (20/20) | 11.21 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 11.44/ 11.44 GFLOPS | Progress: (4/20) | 4.20 s
[Task 6/25] Current/Best: 10.94/ 11.63 GFLOPS | Progress: (8/20) | 7.04 s
[Task 6/25] Current/Best: 14.72/ 21.96 GFLOPS | Progress: (12/20) | 9.12 s
[Task 6/25] Current/Best: 2.83/ 21.96 GFLOPS | Progress: (16/20) | 13.03 s
[Task 6/25] Current/Best: 15.52/ 21.96 GFLOPS | Progress: (20/20) | 15.15 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 21.84/ 21.84 GFLOPS | Progress: (4/20) | 4.90 s
[Task 7/25] Current/Best: 8.42/ 21.84 GFLOPS | Progress: (8/20) | 7.77 s
[Task 7/25] Current/Best: 14.78/ 21.84 GFLOPS | Progress: (12/20) | 10.63 s
[Task 7/25] Current/Best: 14.84/ 21.84 GFLOPS | Progress: (16/20) | 14.11 s
[Task 7/25] Current/Best: 21.95/ 21.95 GFLOPS | Progress: (20/20) | 16.14 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 6.39/ 19.98 GFLOPS | Progress: (4/20) | 3.42 s
[Task 8/25] Current/Best: 9.56/ 20.86 GFLOPS | Progress: (8/20) | 5.43 s
[Task 8/25] Current/Best: 3.07/ 20.86 GFLOPS | Progress: (12/20) | 9.88 s
[Task 8/25] Current/Best: 4.98/ 20.86 GFLOPS | Progress: (16/20) | 16.01 s
[Task 8/25] Current/Best: 20.22/ 20.86 GFLOPS | Progress: (20/20) | 24.32 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 18.57/ 18.57 GFLOPS | Progress: (4/20) | 5.16 s
[Task 9/25] Current/Best: 6.53/ 18.57 GFLOPS | Progress: (8/20) | 7.47 s
[Task 9/25] Current/Best: 16.47/ 18.57 GFLOPS | Progress: (12/20) | 17.67 s
[Task 9/25] Current/Best: 5.63/ 21.56 GFLOPS | Progress: (16/20) | 19.11 s
[Task 9/25] Current/Best: 17.92/ 21.56 GFLOPS | Progress: (20/20) | 21.84 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 15.45/ 17.93 GFLOPS | Progress: (4/20) | 3.00 s
[Task 10/25] Current/Best: 12.28/ 17.93 GFLOPS | Progress: (8/20) | 4.78 s
[Task 10/25] Current/Best: 3.65/ 17.93 GFLOPS | Progress: (12/20) | 6.65 s
[Task 10/25] Current/Best: 14.69/ 18.57 GFLOPS | Progress: (16/20) | 8.50 s
[Task 10/25] Current/Best: 13.81/ 18.57 GFLOPS | Progress: (20/20) | 11.17 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 11.27/ 19.74 GFLOPS | Progress: (4/20) | 4.04 s
[Task 11/25] Current/Best: 18.92/ 19.74 GFLOPS | Progress: (8/20) | 6.25 s
[Task 11/25] Current/Best: 6.16/ 19.74 GFLOPS | Progress: (12/20) | 8.52 s
[Task 11/25] Current/Best: 10.00/ 21.37 GFLOPS | Progress: (16/20) | 10.76 s
[Task 11/25] Current/Best: 13.94/ 21.37 GFLOPS | Progress: (20/20) | 12.61 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 11.70/ 19.53 GFLOPS | Progress: (4/20) | 3.34 s
[Task 12/25] Current/Best: 3.01/ 19.53 GFLOPS | Progress: (8/20) | 7.02 s
[Task 12/25] Current/Best: 16.46/ 20.22 GFLOPS | Progress: (12/20) | 12.26 s
[Task 12/25] Current/Best: 18.39/ 20.22 GFLOPS | Progress: (16/20) | 15.63 s
[Task 12/25] Current/Best: 15.18/ 20.22 GFLOPS | Progress: (20/20) | 19.15 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 9.89/ 15.64 GFLOPS | Progress: (4/20) | 4.51 s
[Task 13/25] Current/Best: 16.72/ 16.72 GFLOPS | Progress: (8/20) | 7.69 s
[Task 13/25] Current/Best: 20.26/ 20.26 GFLOPS | Progress: (12/20) | 11.15 s
[Task 13/25] Current/Best: 9.69/ 20.26 GFLOPS | Progress: (16/20) | 14.20 s
[Task 13/25] Current/Best: 18.05/ 20.26 GFLOPS | Progress: (20/20) | 16.63 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 15.98/ 15.98 GFLOPS | Progress: (4/20) | 3.20 s
[Task 14/25] Current/Best: 15.57/ 15.98 GFLOPS | Progress: (8/20) | 8.91 s
[Task 14/25] Current/Best: 15.76/ 15.98 GFLOPS | Progress: (12/20) | 11.51 s
[Task 14/25] Current/Best: 5.60/ 17.69 GFLOPS | Progress: (16/20) | 13.38 s
[Task 14/25] Current/Best: 4.57/ 19.79 GFLOPS | Progress: (20/20) | 16.56 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 14.85/ 16.73 GFLOPS | Progress: (4/20) | 3.80 s Done.
-
[Task 15/25] Current/Best: 13.97/ 19.97 GFLOPS | Progress: (8/20) | 5.61 s
[Task 15/25] Current/Best: 18.45/ 21.45 GFLOPS | Progress: (12/20) | 7.60 s
[Task 15/25] Current/Best: 11.30/ 21.45 GFLOPS | Progress: (16/20) | 9.75 s
[Task 15/25] Current/Best: 13.86/ 21.45 GFLOPS | Progress: (20/20) | 12.37 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 12.46/ 19.22 GFLOPS | Progress: (4/20) | 3.65 s
[Task 16/25] Current/Best: 14.45/ 19.22 GFLOPS | Progress: (8/20) | 5.81 s
[Task 16/25] Current/Best: 11.44/ 19.22 GFLOPS | Progress: (12/20) | 8.02 s
[Task 16/25] Current/Best: 12.53/ 19.22 GFLOPS | Progress: (16/20) | 11.43 s
[Task 16/25] Current/Best: 13.49/ 19.22 GFLOPS | Progress: (20/20) | 12.84 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 9.63/ 16.43 GFLOPS | Progress: (4/20) | 3.86 s
[Task 17/25] Current/Best: 17.11/ 17.11 GFLOPS | Progress: (8/20) | 6.28 s
[Task 17/25] Current/Best: 22.59/ 22.59 GFLOPS | Progress: (12/20) | 8.67 s
[Task 17/25] Current/Best: 22.05/ 22.59 GFLOPS | Progress: (16/20) | 10.56 s
[Task 17/25] Current/Best: 12.46/ 23.82 GFLOPS | Progress: (20/20) | 12.62 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 12.24/ 16.09 GFLOPS | Progress: (4/20) | 3.71 s
[Task 18/25] Current/Best: 19.24/ 19.24 GFLOPS | Progress: (8/20) | 5.40 s
[Task 18/25] Current/Best: 6.45/ 19.24 GFLOPS | Progress: (12/20) | 8.74 s
[Task 18/25] Current/Best: 16.43/ 19.24 GFLOPS | Progress: (16/20) | 10.58 s
[Task 18/25] Current/Best: 13.47/ 20.75 GFLOPS | Progress: (20/20) | 12.43 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 8.51/ 14.14 GFLOPS | Progress: (4/20) | 6.92 s
[Task 19/25] Current/Best: 9.90/ 17.79 GFLOPS | Progress: (8/20) | 10.90 s
[Task 19/25] Current/Best: 12.94/ 18.01 GFLOPS | Progress: (12/20) | 14.02 s
[Task 19/25] Current/Best: 15.38/ 20.49 GFLOPS | Progress: (16/20) | 17.14 s
[Task 19/25] Current/Best: 18.39/ 20.49 GFLOPS | Progress: (20/20) | 20.24 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 10.79/ 20.77 GFLOPS | Progress: (4/20) | 3.24 s
[Task 20/25] Current/Best: 2.07/ 21.32 GFLOPS | Progress: (8/20) | 6.45 s
[Task 20/25] Current/Best: 14.95/ 21.32 GFLOPS | Progress: (12/20) | 9.32 s
[Task 20/25] Current/Best: 8.92/ 21.32 GFLOPS | Progress: (16/20) | 11.56 s
[Task 20/25] Current/Best: 4.62/ 21.32 GFLOPS | Progress: (20/20) | 14.27 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 21/25] Current/Best: 9.04/ 21.67 GFLOPS | Progress: (4/20) | 3.91 s
[Task 21/25] Current/Best: 6.71/ 21.67 GFLOPS | Progress: (8/20) | 5.42 s
[Task 21/25] Current/Best: 9.01/ 21.67 GFLOPS | Progress: (12/20) | 7.57 s
[Task 21/25] Current/Best: 15.62/ 21.67 GFLOPS | Progress: (16/20) | 9.12 s
[Task 21/25] Current/Best: 10.42/ 21.67 GFLOPS | Progress: (20/20) | 11.16 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 16.63/ 16.63 GFLOPS | Progress: (4/20) | 3.59 s
[Task 22/25] Current/Best: 5.22/ 16.63 GFLOPS | Progress: (8/20) | 5.06 s
[Task 22/25] Current/Best: 15.61/ 16.63 GFLOPS | Progress: (12/20) | 7.02 s
[Task 22/25] Current/Best: 11.46/ 16.63 GFLOPS | Progress: (16/20) | 8.97 s
[Task 22/25] Current/Best: 6.84/ 18.11 GFLOPS | Progress: (20/20) | 11.19 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 19.29/ 19.29 GFLOPS | Progress: (4/20) | 3.32 s
[Task 23/25] Current/Best: 15.12/ 19.29 GFLOPS | Progress: (8/20) | 6.32 s
[Task 23/25] Current/Best: 17.25/ 22.07 GFLOPS | Progress: (12/20) | 9.35 s
[Task 23/25] Current/Best: 17.06/ 22.07 GFLOPS | Progress: (16/20) | 12.14 s
[Task 23/25] Current/Best: 14.24/ 22.07 GFLOPS | Progress: (20/20) | 14.72 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 0.56/ 7.52 GFLOPS | Progress: (4/20) | 12.34 s
[Task 24/25] Current/Best: 0.60/ 7.52 GFLOPS | Progress: (8/20) | 19.66 s
[Task 24/25] Current/Best: 4.69/ 7.52 GFLOPS | Progress: (12/20) | 30.39 s
[Task 24/25] Current/Best: 6.72/ 9.34 GFLOPS | Progress: (16/20) | 40.90 s
[Task 24/25] Current/Best: 1.79/ 9.34 GFLOPS | Progress: (20/20) | 51.43 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 9.96/ 16.73 GFLOPS | Progress: (4/20) | 7.40 s
[Task 1/25] Current/Best: 11.33/ 16.73 GFLOPS | Progress: (8/20) | 11.02 s
[Task 1/25] Current/Best: 16.79/ 19.58 GFLOPS | Progress: (12/20) | 13.33 s
[Task 1/25] Current/Best: 6.67/ 19.58 GFLOPS | Progress: (16/20) | 18.63 s
[Task 1/25] Current/Best: 8.51/ 19.58 GFLOPS | Progress: (20/20) | 21.25 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 13.25/ 18.20 GFLOPS | Progress: (4/20) | 3.00 s
[Task 2/25] Current/Best: 5.95/ 18.20 GFLOPS | Progress: (8/20) | 4.61 s
[Task 2/25] Current/Best: 11.49/ 18.80 GFLOPS | Progress: (12/20) | 6.02 s
[Task 2/25] Current/Best: 13.46/ 18.80 GFLOPS | Progress: (16/20) | 7.03 s
[Task 2/25] Current/Best: 22.05/ 22.05 GFLOPS | Progress: (20/20) | 8.78 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 10.25/ 22.94 GFLOPS | Progress: (4/20) | 4.58 s
[Task 3/25] Current/Best: 11.97/ 22.94 GFLOPS | Progress: (8/20) | 6.62 s
[Task 3/25] Current/Best: 20.15/ 22.94 GFLOPS | Progress: (12/20) | 8.93 s
[Task 3/25] Current/Best: 19.99/ 22.94 GFLOPS | Progress: (16/20) | 10.51 s
[Task 3/25] Current/Best: 17.59/ 22.94 GFLOPS | Progress: (20/20) | 12.14 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 13.81/ 14.47 GFLOPS | Progress: (4/20) | 3.24 s
[Task 4/25] Current/Best: 6.16/ 21.28 GFLOPS | Progress: (8/20) | 9.10 s
[Task 4/25] Current/Best: 7.51/ 21.28 GFLOPS | Progress: (12/20) | 10.80 s
[Task 4/25] Current/Best: 7.94/ 21.28 GFLOPS | Progress: (16/20) | 13.27 s
[Task 4/25] Current/Best: 14.16/ 21.28 GFLOPS | Progress: (20/20) | 16.20 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 11.69/ 11.69 GFLOPS | Progress: (4/20) | 3.33 s
[Task 5/25] Current/Best: 13.64/ 13.64 GFLOPS | Progress: (8/20) | 5.85 s
[Task 5/25] Current/Best: 15.47/ 15.47 GFLOPS | Progress: (12/20) | 7.71 s
[Task 5/25] Current/Best: 18.38/ 18.38 GFLOPS | Progress: (16/20) | 9.12 s
[Task 5/25] Current/Best: 5.28/ 18.38 GFLOPS | Progress: (20/20) | 10.87 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 10.65/ 13.49 GFLOPS | Progress: (4/20) | 7.55 s
[Task 6/25] Current/Best: 13.88/ 17.20 GFLOPS | Progress: (8/20) | 9.27 s
[Task 6/25] Current/Best: 7.84/ 18.15 GFLOPS | Progress: (12/20) | 12.56 s
[Task 6/25] Current/Best: 3.76/ 18.15 GFLOPS | Progress: (16/20) | 16.07 s
[Task 6/25] Current/Best: 7.38/ 18.15 GFLOPS | Progress: (20/20) | 18.38 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 9.46/ 18.88 GFLOPS | Progress: (4/20) | 3.78 s
[Task 7/25] Current/Best: 17.03/ 18.88 GFLOPS | Progress: (8/20) | 6.21 s
[Task 7/25] Current/Best: 6.26/ 22.77 GFLOPS | Progress: (12/20) | 8.19 s
[Task 7/25] Current/Best: 12.70/ 22.77 GFLOPS | Progress: (16/20) | 10.44 s
[Task 7/25] Current/Best: 11.26/ 22.77 GFLOPS | Progress: (20/20) | 13.24 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 2.74/ 14.22 GFLOPS | Progress: (4/20) | 3.91 s
[Task 8/25] Current/Best: 13.03/ 14.22 GFLOPS | Progress: (8/20) | 14.63 s
[Task 8/25] Current/Best: 10.31/ 19.82 GFLOPS | Progress: (12/20) | 17.21 s
[Task 8/25] Current/Best: 10.18/ 19.82 GFLOPS | Progress: (16/20) | 22.30 s
[Task 8/25] Current/Best: 12.54/ 19.82 GFLOPS | Progress: (20/20) | 28.31 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 6.57/ 16.17 GFLOPS | Progress: (4/20) | 3.30 s
[Task 9/25] Current/Best: 11.91/ 16.46 GFLOPS | Progress: (8/20) | 9.99 s
[Task 9/25] Current/Best: 11.94/ 16.51 GFLOPS | Progress: (12/20) | 14.73 s
[Task 9/25] Current/Best: 14.62/ 16.51 GFLOPS | Progress: (16/20) | 16.95 s
[Task 9/25] Current/Best: 11.01/ 16.51 GFLOPS | Progress: (20/20) | 21.30 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 3.04/ 13.12 GFLOPS | Progress: (4/20) | 3.50 s
[Task 10/25] Current/Best: 20.53/ 20.53 GFLOPS | Progress: (8/20) | 5.21 s
[Task 10/25] Current/Best: 9.44/ 20.53 GFLOPS | Progress: (12/20) | 6.79 s
[Task 10/25] Current/Best: 10.75/ 20.53 GFLOPS | Progress: (16/20) | 8.89 s
[Task 10/25] Current/Best: 11.07/ 22.53 GFLOPS | Progress: (20/20) | 11.75 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 5.53/ 16.38 GFLOPS | Progress: (4/20) | 3.92 s
[Task 11/25] Current/Best: 7.67/ 16.38 GFLOPS | Progress: (8/20) | 8.71 s
[Task 11/25] Current/Best: 12.71/ 22.48 GFLOPS | Progress: (12/20) | 11.07 s
[Task 11/25] Current/Best: 6.19/ 23.39 GFLOPS | Progress: (16/20) | 13.21 s
[Task 11/25] Current/Best: 12.35/ 23.57 GFLOPS | Progress: (20/20) | 15.26 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 13.15/ 14.23 GFLOPS | Progress: (4/20) | 4.37 s
[Task 12/25] Current/Best: 14.60/ 14.86 GFLOPS | Progress: (8/20) | 6.42 s
[Task 12/25] Current/Best: 14.31/ 17.83 GFLOPS | Progress: (12/20) | 8.72 s
[Task 12/25] Current/Best: 3.14/ 17.85 GFLOPS | Progress: (16/20) | 12.32 s
[Task 12/25] Current/Best: 11.78/ 17.85 GFLOPS | Progress: (20/20) | 15.21 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 13.81/ 16.10 GFLOPS | Progress: (4/20) | 4.79 s
[Task 13/25] Current/Best: 5.88/ 17.03 GFLOPS | Progress: (8/20) | 7.68 s
[Task 13/25] Current/Best: 18.90/ 19.86 GFLOPS | Progress: (12/20) | 10.41 s
[Task 13/25] Current/Best: 17.16/ 19.86 GFLOPS | Progress: (16/20) | 12.81 s
[Task 13/25] Current/Best: 11.78/ 22.02 GFLOPS | Progress: (20/20) | 14.46 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 6.67/ 16.46 GFLOPS | Progress: (4/20) | 3.76 s
[Task 14/25] Current/Best: 3.46/ 16.92 GFLOPS | Progress: (8/20) | 6.39 s
[Task 14/25] Current/Best: 13.43/ 18.46 GFLOPS | Progress: (12/20) | 8.86 s
[Task 14/25] Current/Best: 9.27/ 21.30 GFLOPS | Progress: (16/20) | 12.71 s
[Task 14/25] Current/Best: 14.08/ 21.30 GFLOPS | Progress: (20/20) | 14.86 s Done.
+
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 15.12/ 18.05 GFLOPS | Progress: (4/20) | 4.98 s
[Task 15/25] Current/Best: 16.09/ 22.87 GFLOPS | Progress: (8/20) | 6.18 s
[Task 15/25] Current/Best: 23.14/ 23.14 GFLOPS | Progress: (12/20) | 7.35 s
[Task 15/25] Current/Best: 10.22/ 23.14 GFLOPS | Progress: (16/20) | 9.74 s
[Task 15/25] Current/Best: 18.31/ 23.14 GFLOPS | Progress: (20/20) | 12.04 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 9.82/ 20.07 GFLOPS | Progress: (4/20) | 4.56 s
[Task 16/25] Current/Best: 14.09/ 20.65 GFLOPS | Progress: (8/20) | 6.24 s
[Task 16/25] Current/Best: 16.00/ 20.65 GFLOPS | Progress: (12/20) | 8.14 s
[Task 16/25] Current/Best: 9.71/ 20.65 GFLOPS | Progress: (16/20) | 9.67 s
[Task 16/25] Current/Best: 1.56/ 20.65 GFLOPS | Progress: (20/20) |
11.67 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 10.30/ 22.80 GFLOPS | Progress: (4/20) | 3.59 s
[Task 17/25] Current/Best: 12.12/ 22.80 GFLOPS | Progress: (8/20) | 6.22 s
[Task 17/25] Current/Best: 19.29/ 22.80 GFLOPS | Progress: (12/20) | 8.00 s
[Task 17/25] Current/Best: 12.95/ 23.98 GFLOPS | Progress: (16/20) | 10.21 s
[Task 17/25] Current/Best: 4.31/ 23.98 GFLOPS | Progress: (20/20) | 13.92 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 3.01/ 18.11 GFLOPS | Progress: (4/20) | 4.25 s
[Task 18/25] Current/Best: 13.36/ 18.42 GFLOPS | Progress: (8/20) | 6.55 s
[Task 18/25] Current/Best: 16.09/ 18.42 GFLOPS | Progress: (12/20) | 8.70 s
[Task 18/25] Current/Best: 15.68/ 18.42 GFLOPS | Progress: (16/20) | 14.50 s
[Task 18/25] Current/Best: 11.91/ 21.22 GFLOPS | Progress: (20/20) | 16.91 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 9.94/ 21.33 GFLOPS | Progress: (4/20) | 4.67 s
[Task 19/25] Current/Best: 4.54/ 21.33 GFLOPS | Progress: (8/20) | 7.72 s
[Task 19/25] Current/Best: 8.71/ 21.33 GFLOPS | Progress: (12/20) | 10.63 s
[Task 19/25] Current/Best: 7.50/ 21.33 GFLOPS | Progress: (16/20) | 14.04 s
[Task 19/25] Current/Best: 8.63/ 22.33 GFLOPS | Progress: (20/20) | 16.92 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.44/ 19.28 GFLOPS | Progress: (4/20) | 4.16 s Done.
+
[Task 20/25] Current/Best: 10.13/ 19.28 GFLOPS | Progress: (8/20) | 8.31 s
[Task 20/25] Current/Best: 7.45/ 19.28 GFLOPS | Progress: (12/20) | 11.42 s
[Task 20/25] Current/Best: 11.99/ 19.28 GFLOPS | Progress: (16/20) | 14.00 s
[Task 20/25] Current/Best: 10.01/ 19.28 GFLOPS | Progress: (20/20) | 16.65 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 12.95/ 13.28 GFLOPS | Progress: (4/20) | 3.17 s
[Task 21/25] Current/Best: 9.26/ 13.28 GFLOPS | Progress: (8/20) | 6.63 s
[Task 21/25] Current/Best: 8.09/ 14.85 GFLOPS | Progress: (12/20) | 9.02 s
[Task 21/25] Current/Best: 20.63/ 20.63 GFLOPS | Progress: (16/20) | 10.98 s
[Task 21/25] Current/Best: 9.05/ 20.63 GFLOPS | Progress: (20/20) | 13.95 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 18.94/ 18.94 GFLOPS | Progress: (4/20
) | 4.40 s Done.
Done.
-
[Task 25/25] Current/Best: 3.90/ 9.24 GFLOPS | Progress: (4/20) | 3.72 s
[Task 25/25] Current/Best: 9.99/ 10.00 GFLOPS | Progress: (8/20) | 14.38 s
[Task 25/25] Current/Best: 9.11/ 10.00 GFLOPS | Progress: (12/20) | 26.11 s
[Task 25/25] Current/Best: 5.28/ 10.00 GFLOPS | Progress: (16/20) | 36.61 s
[Task 25/25] Current/Best: 5.83/ 10.00 GFLOPS | Progress: (20/20) | 41.78 s
+
[Task 22/25] Current/Best: 12.76/ 18.94 GFLOPS | Progress: (8/20) | 7.07 s
[Task 22/25] Current/Best: 14.40/ 18.94 GFLOPS | Progress: (12/20) | 8.32 s
[Task 22/25] Current/Best: 13.13/ 18.94 GFLOPS | Progress: (16/20) | 10.25 s
[Task 22/25] Current/Best: 17.79/ 18.94 GFLOPS | Progress: (20/20) | 14.02 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 10.79/ 20.38 GFLOPS | Progress: (4/20) | 3.69 s
[Task 23/25] Current/Best: 19.95/ 20.38 GFLOPS | Progress: (8/20) | 7.42 s
[Task 23/25] Current/Best: 9.95/ 20.38 GFLOPS | Progress: (12/20) | 10.94 s
[Task 23/25] Current/Best: 9.07/ 20.38 GFLOPS | Progress: (16/20) | 14.10 s
[Task 23/25] Current/Best: 11.54/ 20.38 GFLOPS | Progress: (20/20) | 16.86 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 9.98/ 9.98 GFLOPS | Progress: (4/20) | 12.21 s
[Task 24/25] Current/Best: 6.01/ 9.98 GFLOPS | Progress: (8/20) | 22.92 s
[Task 24/25] Current/Best: 5.54/ 9.98 GFLOPS | Progress: (12/20) | 34.54 s
[Task 24/25] Current/Best: 3.26/ 9.98 GFLOPS | Progress: (16/20) | 46.01 s
[Task 24/25] Current/Best: 8.05/ 9.98 GFLOPS | Progress: (20/20) | 57.51 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 25/25] Current/Best: 2.79/ 8.54 GFLOPS | Progress: (4/20) | 4.55 s
[Task 25/25] Current/Best: 5.71/ 9.35 GFLOPS | Progress: (8/20) | 9.37 s
[Task 25/25] Current/Best: 1.55/ 9.46 GFLOPS | Progress: (12/20) | 10.77 s
[Task 25/25] Current/Best: 8.71/ 9.46 GFLOPS | Progress: (16/20) | 21.06 s
[Task 25/25] Current/Best: 5.79/ 9.46 GFLOPS | Progress: (20/20) | 32.71 s
@@ -673,7 +674,7 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621103
+ class='n02123045 tabby, tabby cat' with probability=0.621102
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
@@ -731,8 +732,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 407.0469524100031, 'median': 406.3028129000031, 'std': 4.243191979160079}
- unoptimized: {'mean': 510.44585038999804, 'median': 510.26684924999586, 'std': 2.741325791063284}
+ optimized: {'mean': 406.0337182000035, 'median': 406.1050522000073, 'std': 1.1477014024438263}
+ unoptimized: {'mean': 513.8701477699988, 'median': 513.6327808999965, 'std': 1.3264686737052278}
@@ -755,7 +756,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 42.119 seconds)
+ **Total running time of the script:** ( 10 minutes 52.900 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 4dfd1fecfb..6c689a7e6f 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -270,7 +270,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.295e-07 secs/op
+ 1.506e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 0c1f94458e..d3eb9dbca2 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x20e6f3b0)), stage(b, placeholder(b, 0x1608b990)), 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 [...]
+ [stage(a, placeholder(a, 0x5610c10)), stage(b, placeholder(b, 0x22961a50)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index f6e880930c..894d32b518 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
=================
-**14:24.922** total execution time for **tutorial** files:
+**14:24.924** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:42.119 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:52.900 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:40.168 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:34.020 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.874 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.016 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:35.789 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:35.795 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:22.637 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:19.028 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.391 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.230 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.780 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.757 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.154 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.169 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 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_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.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 754a0a69aa..741fd2e2fa 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -294,7 +294,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000007
+ Numpy running time: 0.000008
naive: 0.000007
@@ -501,10 +501,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.191330000750895e-06 1.0
- naive 6.6464e-06 0.9242240307851266
- parallel 6.9099e-06 0.9608653752892011
- vector 2.47405e-05 3.4403232778104575
+ numpy 7.90564999988419e-06 1.0
+ naive 6.6824e-06 0.8452688899834789
+ parallel 6.9530999999999995e-06 0.879510223713655
+ vector 2.4559499999999998e-05 3.1065756769348214
@@ -925,7 +925,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018959
+ Numpy running time: 0.017863
@@ -983,7 +983,7 @@ optimizations.
.. code-block:: none
- none: 3.451261
+ none: 3.421262
@@ -1086,7 +1086,7 @@ schedule.
.. code-block:: none
- blocking: 0.310756
+ blocking: 0.303684
@@ -1182,7 +1182,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.349269
+ vectorization: 0.335182
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1256,7 +1256,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.115520
+ loop permutation: 0.115062
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1355,7 +1355,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.107311
+ array packing: 0.108361
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1448,7 +1448,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110916
+ block caching: 0.110699
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1534,7 +1534,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.145802
+ parallelization: 0.146580
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1615,13 +1615,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4512608985 1.0
- blocking 0.3107555954 0.09004117756935204
- vectorization 0.34926922140000005 0.10120046895086973
- loop permutation 0.1155204428 0.03347195306220052
- array packing 0.10731132800000001 0.03109336881678231
- block caching 0.1109157913 0.03213775908631151
- parallelization 0.145802374 0.04224611766191573
+ none 3.421261704 1.0
+ blocking 0.30368355 0.08876361303929062
+ vectorization 0.33518173139999996 0.097970211108995
+ loop permutation 0.11506181280000001 0.03363139764066409
+ array packing 0.10836136290000001 0.031672924282088184
+ block caching 0.11069907539999999 0.03235621387003956
+ parallelization 0.1465796965 0.04284375449227546
@@ -1663,7 +1663,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.874 seconds)
+ **Total running time of the script:** ( 1 minutes 1.016 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 599293b2dc..c2de33fcef 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-6da298b3a07ce33eca390c6e5afd029d8c388f3d
+dec74cb93d3460d686f1935f933dc24404c5e995
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 721558fbdc..13c6b68ecf 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 14.397 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.861 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 2f9aaefe14..82ef37cd45 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ pip install -U tensorflow --user
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 971ms/step
+1/1 [==============================] - 1s 950ms/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 79fec850dc..28ee8e754a 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -440,7 +440,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip3c1a07bd-ecb3-405d-9697-c477b98d1dd0 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.zipe232925d-da3c-4a18-bed2-a6d0928c330f 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 fbde8938d5..7655e7bf0f 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,14 +448,13 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 15%|#5 | 6.33M/41.5M [00:00<00:01, 27.7MB/s]
- 22%|##1 | 8.98M/41.5M [00:00<00:01, 25.2MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:00, 30.7MB/s]
- 42%|####1 | 17.3M/41.5M [00:00<00:00, 28.6MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 33.8MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 39.0MB/s]
- 92%|#########2| 38.3M/41.5M [00:01<00:00, 33.2MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 33.4MB/s]
+ 16%|#5 | 6.57M/41.5M [00:00<00:00, 68.8MB/s]
+ 32%|###1 | 13.1M/41.5M [00:00<00:00, 66.9MB/s]
+ 47%|####7 | 19.5M/41.5M [00:00<00:00, 51.7MB/s]
+ 60%|#####9 | 24.8M/41.5M [00:00<00:00, 24.1MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 32.5MB/s]
+ 92%|#########2| 38.3M/41.5M [00:01<00:00, 37.1MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 34.9MB/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 b1d8c92911..71b4b9245c 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,13 +431,11 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 5%|4 | 2.05M/44.7M [00:00<00:02, 21.2MB/s]
- 24%|##3 | 10.6M/44.7M [00:00<00:00, 61.2MB/s]
- 40%|#### | 18.0M/44.7M [00:00<00:00, 68.5MB/s]
- 55%|#####5 | 24.7M/44.7M [00:00<00:00, 69.3MB/s]
- 72%|#######1 | 32.0M/44.7M [00:00<00:00, 70.5MB/s]
- 90%|########9 | 40.0M/44.7M [00:00<00:00, 66.3MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 69.3MB/s]
+ 19%|#8 | 8.41M/44.7M [00:00<00:00, 88.1MB/s]
+ 48%|####8 | 21.6M/44.7M [00:00<00:00, 118MB/s]
+ 74%|#######3 | 32.8M/44.7M [00:00<00:00, 88.5MB/s]
+ 99%|#########8| 44.2M/44.7M [00:00<00:00, 94.1MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 95.7MB/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 14380a6a00..f49c74b66e 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -645,7 +645,7 @@ 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 12.873 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.844 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 6cce270a45..d2770eda6f 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>05:53.485</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:45.577</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_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>01:14.397</p></td>
+<td><p>01:11.861</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>01:12.873</p></td>
+<td><p>01:10.844</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>00:47.391</p></td>
+<td><p>00:45.874</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>00:33.138</p></td>
+<td><p>00:32.532</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>00:31.165</p></td>
+<td><p>00:30.407</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:26.774</p></td>
+<td><p>00:26.987</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>00:25.760</p></td>
+<td><p>00:24.445</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:22.667</p></td>
+<td><p>00:22.190</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>00:16.891</p></td>
+<td><p>00:18.043</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>00:02.428</p></td>
+<td><p>00:02.394</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index a8b9b30b36..a6588eae65 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)
- 15.7961 15.7501 16.1495 15.6478 0.1481
+ 16.3996 16.5399 16.8385 15.7575 0.3918
</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 bdf14b421e..b9bf0bfde6 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,31 +453,19 @@ 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]
- 4%|3 | 6.30M/170M [00:00<00:08, 20.7MB/s]
- 5%|5 | 8.94M/170M [00:00<00:07, 22.8MB/s]
- 9%|9 | 16.0M/170M [00:00<00:04, 34.6MB/s]
- 14%|#4 | 24.0M/170M [00:00<00:03, 43.6MB/s]
- 19%|#8 | 32.0M/170M [00:00<00:02, 52.0MB/s]
- 24%|##3 | 40.0M/170M [00:00<00:02, 60.4MB/s]
- 29%|##8 | 49.2M/170M [00:01<00:01, 70.5MB/s]
- 33%|###3 | 56.5M/170M [00:01<00:01, 61.4MB/s]
- 38%|###7 | 64.0M/170M [00:01<00:01, 57.0MB/s]
- 44%|####3 | 74.1M/170M [00:01<00:01, 56.7MB/s]
- 47%|####7 | 80.5M/170M [00:01<00:01, 59.0MB/s]
- 52%|#####1 | 88.0M/170M [00:01<00:01, 57.2MB/s]
- 56%|#####5 | 94.3M/170M [00:01<00:01, 52.3MB/s]
- 59%|#####8 | 99.5M/170M [00:02<00:01, 46.3MB/s]
- 61%|######1 | 104M/170M [00:02<00:01, 41.7MB/s]
- 66%|######5 | 112M/170M [00:02<00:01, 45.1MB/s]
- 71%|####### | 120M/170M [00:02<00:01, 51.4MB/s]
- 75%|#######5 | 128M/170M [00:02<00:00, 56.4MB/s]
- 79%|#######9 | 134M/170M [00:02<00:00, 57.3MB/s]
- 83%|########3 | 141M/170M [00:02<00:00, 61.1MB/s]
- 87%|########6 | 147M/170M [00:02<00:00, 57.6MB/s]
- 90%|########9 | 153M/170M [00:03<00:00, 54.1MB/s]
- 94%|#########4| 160M/170M [00:03<00:00, 56.0MB/s]
- 98%|#########7| 166M/170M [00:03<00:00, 53.5MB/s]
-100%|##########| 170M/170M [00:03<00:00, 51.8MB/s]
+ 9%|8 | 15.0M/170M [00:00<00:01, 157MB/s]
+ 18%|#7 | 30.0M/170M [00:00<00:01, 108MB/s]
+ 24%|##4 | 41.1M/170M [00:00<00:01, 108MB/s]
+ 31%|### | 51.9M/170M [00:00<00:01, 94.9MB/s]
+ 36%|###6 | 61.4M/170M [00:00<00:01, 66.6MB/s]
+ 45%|####4 | 76.2M/170M [00:00<00:01, 86.7MB/s]
+ 56%|#####5 | 94.7M/170M [00:00<00:00, 113MB/s]
+ 64%|######4 | 109M/170M [00:01<00:00, 121MB/s]
+ 72%|#######1 | 122M/170M [00:01<00:00, 97.5MB/s]
+ 79%|#######9 | 134M/170M [00:01<00:00, 98.5MB/s]
+ 87%|########7 | 148M/170M [00:01<00:00, 91.9MB/s]
+ 99%|#########8| 168M/170M [00:01<00:00, 117MB/s]
+100%|##########| 170M/170M [00:01<00:00, 103MB/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=& [...]
@@ -575,7 +563,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 17.732 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 14.701 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 239648c8d8..ee2e07070a 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -497,9 +497,8 @@ 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, 45.3MB/s]
- 91%|######### | 12.3M/13.6M [00:00<00:00, 41.8MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 45.2MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 66.5MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 80.5MB/s]
</pre></div>
</div>
</div>
@@ -590,7 +589,7 @@ 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)
- 90.5724 90.5451 95.0568 90.1166 0.5352
+ 90.5992 90.5281 95.1870 90.2380 0.4903
</pre></div>
</div>
<div class="admonition note">
@@ -629,7 +628,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.280 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.201 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 fdafe08dc5..6d375decc3 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -582,7 +582,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.2797 120.2911 122.2328 117.7436 0.4171
+ 120.1178 119.9952 125.3989 119.3251 0.6637
</pre></div>
</div>
<div class="admonition note">
@@ -610,7 +610,7 @@ 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 23.376 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 22.886 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 f973afeed5..fcb62e54f4 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -520,7 +520,7 @@ 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 38.363 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 35.136 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 3c4657d34b..cec617f552 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -462,23 +462,23 @@ 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 | 4889/132723 [00:00<00:02, 48884.69KB/s]
- 9%|8 | 11927/132723 [00:00<00:01, 61522.68KB/s]
- 16%|#5 | 20597/132723 [00:00<00:01, 73015.88KB/s]
- 22%|##2 | 29298/132723 [00:00<00:01, 78538.42KB/s]
- 28%|##7 | 37152/132723 [00:00<00:01, 51508.86KB/s]
- 34%|###4 | 45789/132723 [00:00<00:01, 60311.25KB/s]
- 40%|###9 | 52802/132723 [00:00<00:01, 60264.44KB/s]
- 46%|####6 | 61565/132723 [00:00<00:01, 67545.57KB/s]
- 53%|#####2 | 70178/132723 [00:01<00:00, 72663.19KB/s]
- 59%|#####9 | 78924/132723 [00:01<00:00, 76839.67KB/s]
- 66%|######5 | 86976/132723 [00:01<00:00, 69110.32KB/s]
- 72%|#######2 | 95685/132723 [00:01<00:00, 73909.34KB/s]
- 78%|#######7 | 103411/132723 [00:01<00:00, 65338.15KB/s]
- 84%|########4 | 112111/132723 [00:01<00:00, 70886.39KB/s]
- 90%|######### | 119568/132723 [00:01<00:00, 69278.44KB/s]
- 97%|#########6| 128191/132723 [00:01<00:00, 73845.31KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 68686.19KB/s]
+ 5%|4 | 6073/132723 [00:00<00:02, 60726.00KB/s]
+ 11%|# | 14266/132723 [00:00<00:01, 73191.15KB/s]
+ 16%|#6 | 21586/132723 [00:00<00:01, 63785.78KB/s]
+ 22%|##2 | 29818/132723 [00:00<00:01, 70500.02KB/s]
+ 28%|##7 | 37004/132723 [00:00<00:01, 69388.81KB/s]
+ 34%|###4 | 45227/132723 [00:00<00:01, 73532.01KB/s]
+ 40%|###9 | 52659/132723 [00:00<00:01, 68612.56KB/s]
+ 46%|####5 | 60890/132723 [00:00<00:00, 72652.91KB/s]
+ 52%|#####2 | 69047/132723 [00:00<00:00, 75294.74KB/s]
+ 58%|#####8 | 77304/132723 [00:01<00:00, 77455.29KB/s]
+ 64%|######4 | 85116/132723 [00:01<00:00, 74894.97KB/s]
+ 70%|####### | 93223/132723 [00:01<00:00, 76692.38KB/s]
+ 76%|#######6 | 101429/132723 [00:01<00:00, 78267.18KB/s]
+ 83%|########2 | 109560/132723 [00:01<00:00, 79164.39KB/s]
+ 89%|########8 | 117769/132723 [00:01<00:00, 80031.60KB/s]
+ 95%|#########4| 126032/132723 [00:01<00:00, 80794.05KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 74773.55KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -517,7 +517,7 @@ 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 1.135 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 59.158 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 ea575a1ed7..e6d3f3b998 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>12:53.187</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>12:43.650</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,39 +349,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:17.732</p></td>
+<td><p>03:14.701</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>03:01.135</p></td>
+<td><p>02:59.158</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>02:23.376</p></td>
+<td><p>02:22.886</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>01:38.363</p></td>
+<td><p>01:35.136</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:06.280</p></td>
+<td><p>01:06.201</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:36.584</p></td>
+<td><p>00:35.965</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:25.163</p></td>
+<td><p>00:24.957</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:24.547</p></td>
+<td><p>00:24.640</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index cb01f2d686..b743c7d659 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -621,7 +621,7 @@ 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.zipa01ac5e8-0e00-4793-8d4f-7a3a0f0bdd52 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.zipd5949416-3aab-4080-b5de-b79dd81af330 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 dcacf6a741..12b2a757aa 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>00:47.708</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:47.430</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>00:44.242</p></td>
+<td><p>00:43.996</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>00:02.425</p></td>
+<td><p>00:02.405</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>00:01.034</p></td>
+<td><p>00:01.022</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 107d52adc6..7bd8a5cd56 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -525,10 +525,10 @@ 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: 6939us [6939us] (46.29%; 46.29%)
-FoldScaleAxis: 8050us [7us] (53.71%; 53.71%)
- FoldConstant: 8043us [1588us] (53.66%; 99.91%)
- InferType: 6455us [6455us] (43.06%; 80.26%)
+InferType: 6658us [6658us] (46.18%; 46.18%)
+FoldScaleAxis: 7759us [5us] (53.82%; 53.82%)
+ FoldConstant: 7753us [1594us] (53.78%; 99.93%)
+ InferType: 6159us [6159us] (42.72%; 79.44%)
</pre></div>
</div>
</div>
@@ -550,10 +550,10 @@ 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: 6542us [6542us] (45.46%; 45.46%)
-FoldScaleAxis: 7849us [6us] (54.54%; 54.54%)
- FoldConstant: 7843us [1611us] (54.50%; 99.92%)
- InferType: 6232us [6232us] (43.31%; 79.46%)
+InferType: 6256us [6256us] (44.66%; 44.66%)
+FoldScaleAxis: 7752us [5us] (55.34%; 55.34%)
+ FoldConstant: 7747us [1624us] (55.31%; 99.94%)
+ InferType: 6123us [6123us] (43.71%; 79.03%)
</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 57b0364afb..71c1606c6a 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -577,7 +577,7 @@ 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: 41.513088 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 35.942497 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 cc7e4ecdfa..ffc21e5b51 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -916,7 +916,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.325258 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.026060 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 a9822f4391..6fce7a2688 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -474,8 +474,8 @@ 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: 0.018412
-Baseline: 3.447995
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018568
+Baseline: 3.441783
</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: 0.298499
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.296655
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -602,7 +602,7 @@ 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: 0.340025
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.331357
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -663,7 +663,7 @@ 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: 0.119436
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.115943
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -746,7 +746,7 @@ 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: 0.109824
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109887
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -832,7 +832,7 @@ 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: 0.111595
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.112823
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -922,7 +922,7 @@ 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: 0.147733
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147258
</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 825a158015..a0dc35136e 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.163</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.862</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.519</p></td>
+<td><p>00:32.351</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>00:01.555</p></td>
+<td><p>00:01.458</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>00:01.088</p></td>
+<td><p>00:01.054</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 06171a184d..61cd86aeb1 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>09:16.328</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>08:59.762</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>05:49.520</p></td>
+<td><p>05:32.526</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:32.538</p></td>
+<td><p>01:32.468</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>01:03.512</p></td>
+<td><p>01:03.203</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>00:27.714</p></td>
+<td><p>00:28.524</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>00:11.838</p></td>
+<td><p>00:11.928</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>00:11.206</p></td>
+<td><p>00:11.112</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 2d0ea7f1d0..e7610cce76 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
@@ -504,11 +504,11 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [1152]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), 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" = 64 {
conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
@@ -524,422 +524,462 @@ cooperative fetching, unrolling and operator fusion.</p>
conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
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" = 56;
- 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[(((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" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 56), 81)) && (floormod((threadIdx.x_1 + 56), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 56), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 31), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 6), 81)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 6), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 62), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 37), 81)) && (floormod((threadIdx.x_1 + 37), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 37), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- 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[((((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" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 43), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else((((threadIdx.x_1 < 54) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 504), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 2)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 74), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 74), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else((((threadIdx.x_1 < 23) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 616), 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_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 56), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 112), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 168), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 224), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 280), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 336), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 448), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 560), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 616), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 672), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 728), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 784), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 840), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 896), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 952), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1064), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_2 < 32), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1120), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- }
- for (ry.outer.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 327)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 408)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 489)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 570)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 328)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 409)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 490)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 571)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 410)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 491)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 572)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 330)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 411)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 492)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 573)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 327)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 408)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 489)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 570)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 328)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 409)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 490)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 571)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 410)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 491)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 572)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 330)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 411)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 492)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 573)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 327)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 408)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 489)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 570)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 328)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 409)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 490)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 571)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 410)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 491)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 572)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 330)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 411)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 492)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 573)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 331)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 412)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 493)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 327)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 408)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 489)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 570)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 328)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 409)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 490)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 571)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 410)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 491)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 572)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 330)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 411)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 492)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 573)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 331)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 412)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 493)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 327)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 408)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 489)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 570)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 328)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 409)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 490)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 571)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 410)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 491)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 572)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 330)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 411)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 492)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 573)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 331)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 412)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 493)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 89)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 170)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 251)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 332)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 413)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 494)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 575)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 327)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 408)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 489)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 570)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 328)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 409)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 490)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 571)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 410)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 491)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 572)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 330)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 411)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 492)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 573)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 331)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 412)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 493)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 89)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 170)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 251)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 332)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 413)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 494)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + 575)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*72)
+ let cse_var_1: int32 = (ry.outer.outer*3)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0 [...]
+ }
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
for (i1.inner: int32, 0, 2) {
for (i3.inner: int32, 0, 7) {
- compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
}
}
}
@@ -977,7 +1017,7 @@ 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: 0.256 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.367 ms
</pre></div>
</div>
</div>
@@ -1008,20 +1048,20 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-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_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=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 [...]
@@ -1029,10 +1069,10 @@ compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
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)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
@@ -1055,12 +1095,12 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+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=64)
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)
+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=4)
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=56)
+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=64)
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, "unroll_explicit", True)
@@ -1080,10 +1120,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[1152];
+ __shared__ float pad_temp_shared[72];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -1099,387 +1139,410 @@ extern "C" __global__ void __launch_bounds__(56) default_function_kern
conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
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) + 56)] = (((((9 <= ((((int)threadIdx.x) + 56) % 81)) && (((((int)threadIdx.x) + 56) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 81) * 49)) + ((((((int)threadIdx.x) + 56) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 81) * 49)) + (((((int)threadIdx.x) + 6) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((9 <= ((((int)threadIdx.x) + 37) % 81)) && (((((int)threadIdx.x) + 37) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 81) * 49)) + ((((((int)threadIdx.x) + 37) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 81) * 49)) + (((((int)threadIdx.x) + 12) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 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) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 504)] = ((((((int)threadIdx.x) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 504) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[(((int)threadIdx.x) + 616)] = ((((((int)threadIdx.x) < 23) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 616) / 81) * 49)) + (((((int)threadIdx.x) + 49) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 73728) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 616)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 616) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 728)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 728) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 840)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 840) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 952)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 952) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1064) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 32) {
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- }
- __syncthreads();
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 327)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 408)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 489)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 328)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 409)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 490)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 410)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 491)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 330)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 411)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 492)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 327)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 408)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 489)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 328)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 409)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 490)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 410)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 491)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 330)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 411)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 492)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 327)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 408)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 489)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 328)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 409)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 490)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 410)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 491)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 330)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 411)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 492)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 331)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 412)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 493)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 327)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 408)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 489)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 328)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 409)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 490)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 410)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 491)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 330)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 411)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 492)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 331)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 412)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 493)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 327)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 408)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 489)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 328)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 409)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 490)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 410)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 491)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 330)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 411)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 492)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 331)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 412)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 493)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 89)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 170)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 251)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 332)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 413)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 494)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 575)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 327)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 408)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 489)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 328)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 409)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 490)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 410)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 491)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 330)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 411)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 492)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 331)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 412)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 493)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 89)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 170)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 251)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 332)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 413)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 494)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + 575)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
}
@@ -1517,7 +1580,7 @@ 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 49.520 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 32.526 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 827c76c74f..733420e052 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -915,7 +915,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.2173 8.2218 8.2245 8.2056 0.0084
+ 8.1633 8.1624 8.1698 8.1577 0.0050
</pre></div>
</div>
</div>
@@ -937,7 +937,7 @@ 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 3.512 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.203 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 71009ba70b..ff72abbd53 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -934,7 +934,7 @@ 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)
- 757.1168 757.0810 757.9855 756.2840 0.6951
+ 762.6226 762.3649 764.3096 761.1933 1.2852
</pre></div>
</div>
</div>
@@ -956,7 +956,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 32.538 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 32.468 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 aeae846276..4e896bf144 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,78 +632,527 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
- for (i.outer.inner: int32, 0, 8) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 4) {
- let cse_var_1: int32 = (((i.outer.inner*128) + (i.inner.init*32)) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [1024], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
- }
- }
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 4) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_19: int32 = (((i.outer.inner*128) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_18: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.outer.inner*1024)) + (i.inner*256))
- let cse_var_17: int32 = (cse_var_19 + 9)
- let cse_var_16: int32 = (cse_var_19 + 8)
- let cse_var_15: int32 = (cse_var_19 + 7)
- let cse_var_14: int32 = (cse_var_19 + 6)
- let cse_var_13: int32 = (cse_var_19 + 5)
- let cse_var_12: int32 = (cse_var_19 + 4)
- let cse_var_11: int32 = (cse_var_19 + 3)
- let cse_var_10: int32 = (cse_var_19 + 2)
- let cse_var_9: int32 = (cse_var_19 + 15)
- let cse_var_8: int32 = (cse_var_19 + 14)
- let cse_var_7: int32 = (cse_var_19 + 13)
- let cse_var_6: int32 = (cse_var_19 + 12)
- let cse_var_5: int32 = (cse_var_19 + 11)
- let cse_var_4: int32 = (cse_var_19 + 10)
- let cse_var_3: int32 = (cse_var_19 + 1)
- {
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- }
- }
- }
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+ for (i0.outer: int32, 0, 16) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global;
+ for (i1.outer: int32, 0, 32) {
+ compute_5: Buffer(compute_4, float32, [128], [])[0] = 0f32
+ compute_5[1] = 0f32
+ compute_5[2] = 0f32
+ compute_5[3] = 0f32
+ compute_5[4] = 0f32
+ compute_5[5] = 0f32
+ compute_5[6] = 0f32
+ compute_5[7] = 0f32
+ compute_5[8] = 0f32
+ compute_5[9] = 0f32
+ compute_5[10] = 0f32
+ compute_5[11] = 0f32
+ compute_5[12] = 0f32
+ compute_5[13] = 0f32
+ compute_5[14] = 0f32
+ compute_5[15] = 0f32
+ compute_5[16] = 0f32
+ compute_5[17] = 0f32
+ compute_5[18] = 0f32
+ compute_5[19] = 0f32
+ compute_5[20] = 0f32
+ compute_5[21] = 0f32
+ compute_5[22] = 0f32
+ compute_5[23] = 0f32
+ compute_5[24] = 0f32
+ compute_5[25] = 0f32
+ compute_5[26] = 0f32
+ compute_5[27] = 0f32
+ compute_5[28] = 0f32
+ compute_5[29] = 0f32
+ compute_5[30] = 0f32
+ compute_5[31] = 0f32
+ compute_5[32] = 0f32
+ compute_5[33] = 0f32
+ compute_5[34] = 0f32
+ compute_5[35] = 0f32
+ compute_5[36] = 0f32
+ compute_5[37] = 0f32
+ compute_5[38] = 0f32
+ compute_5[39] = 0f32
+ compute_5[40] = 0f32
+ compute_5[41] = 0f32
+ compute_5[42] = 0f32
+ compute_5[43] = 0f32
+ compute_5[44] = 0f32
+ compute_5[45] = 0f32
+ compute_5[46] = 0f32
+ compute_5[47] = 0f32
+ compute_5[48] = 0f32
+ compute_5[49] = 0f32
+ compute_5[50] = 0f32
+ compute_5[51] = 0f32
+ compute_5[52] = 0f32
+ compute_5[53] = 0f32
+ compute_5[54] = 0f32
+ compute_5[55] = 0f32
+ compute_5[56] = 0f32
+ compute_5[57] = 0f32
+ compute_5[58] = 0f32
+ compute_5[59] = 0f32
+ compute_5[60] = 0f32
+ compute_5[61] = 0f32
+ compute_5[62] = 0f32
+ compute_5[63] = 0f32
+ compute_5[64] = 0f32
+ compute_5[65] = 0f32
+ compute_5[66] = 0f32
+ compute_5[67] = 0f32
+ compute_5[68] = 0f32
+ compute_5[69] = 0f32
+ compute_5[70] = 0f32
+ compute_5[71] = 0f32
+ compute_5[72] = 0f32
+ compute_5[73] = 0f32
+ compute_5[74] = 0f32
+ compute_5[75] = 0f32
+ compute_5[76] = 0f32
+ compute_5[77] = 0f32
+ compute_5[78] = 0f32
+ compute_5[79] = 0f32
+ compute_5[80] = 0f32
+ compute_5[81] = 0f32
+ compute_5[82] = 0f32
+ compute_5[83] = 0f32
+ compute_5[84] = 0f32
+ compute_5[85] = 0f32
+ compute_5[86] = 0f32
+ compute_5[87] = 0f32
+ compute_5[88] = 0f32
+ compute_5[89] = 0f32
+ compute_5[90] = 0f32
+ compute_5[91] = 0f32
+ compute_5[92] = 0f32
+ compute_5[93] = 0f32
+ compute_5[94] = 0f32
+ compute_5[95] = 0f32
+ compute_5[96] = 0f32
+ compute_5[97] = 0f32
+ compute_5[98] = 0f32
+ compute_5[99] = 0f32
+ compute_5[100] = 0f32
+ compute_5[101] = 0f32
+ compute_5[102] = 0f32
+ compute_5[103] = 0f32
+ compute_5[104] = 0f32
+ compute_5[105] = 0f32
+ compute_5[106] = 0f32
+ compute_5[107] = 0f32
+ compute_5[108] = 0f32
+ compute_5[109] = 0f32
+ compute_5[110] = 0f32
+ compute_5[111] = 0f32
+ compute_5[112] = 0f32
+ compute_5[113] = 0f32
+ compute_5[114] = 0f32
+ compute_5[115] = 0f32
+ compute_5[116] = 0f32
+ compute_5[117] = 0f32
+ compute_5[118] = 0f32
+ compute_5[119] = 0f32
+ compute_5[120] = 0f32
+ compute_5[121] = 0f32
+ compute_5[122] = 0f32
+ compute_5[123] = 0f32
+ compute_5[124] = 0f32
+ compute_5[125] = 0f32
+ compute_5[126] = 0f32
+ compute_5[127] = 0f32
+ for (elem_idx: int32, 0, (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])) {
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[0] = (compute_5[0] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[1] = (compute_5[1] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[2] = (compute_5[2] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[3] = (compute_5[3] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[4] = (compute_5[4] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[5] = (compute_5[5] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[6] = (compute_5[6] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[7] = (compute_5[7] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[8] = (compute_5[8] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[9] = (compute_5[9] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[10] = (compute_5[10] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[11] = (compute_5[11] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[12] = (compute_5[12] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[13] = (compute_5[13] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[14] = (compute_5[14] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[15] = (compute_5[15] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[16] = (compute_5[16] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[17] = (compute_5[17] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[18] = (compute_5[18] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[19] = (compute_5[19] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[20] = (compute_5[20] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[21] = (compute_5[21] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[22] = (compute_5[22] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[23] = (compute_5[23] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[24] = (compute_5[24] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[25] = (compute_5[25] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[26] = (compute_5[26] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[27] = (compute_5[27] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[28] = (compute_5[28] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[29] = (compute_5[29] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[30] = (compute_5[30] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[31] = (compute_5[31] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[32] = (compute_5[32] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[33] = (compute_5[33] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[34] = (compute_5[34] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[35] = (compute_5[35] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[36] = (compute_5[36] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[37] = (compute_5[37] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[38] = (compute_5[38] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[39] = (compute_5[39] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[40] = (compute_5[40] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[41] = (compute_5[41] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[42] = (compute_5[42] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[43] = (compute_5[43] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[44] = (compute_5[44] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[45] = (compute_5[45] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[46] = (compute_5[46] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[47] = (compute_5[47] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[48] = (compute_5[48] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[49] = (compute_5[49] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[50] = (compute_5[50] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[51] = (compute_5[51] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[52] = (compute_5[52] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[53] = (compute_5[53] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[54] = (compute_5[54] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[55] = (compute_5[55] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[56] = (compute_5[56] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[57] = (compute_5[57] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[58] = (compute_5[58] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[59] = (compute_5[59] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[60] = (compute_5[60] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[61] = (compute_5[61] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[62] = (compute_5[62] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[63] = (compute_5[63] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[64] = (compute_5[64] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[65] = (compute_5[65] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[66] = (compute_5[66] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[67] = (compute_5[67] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[68] = (compute_5[68] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[69] = (compute_5[69] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[70] = (compute_5[70] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[71] = (compute_5[71] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[72] = (compute_5[72] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[73] = (compute_5[73] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[74] = (compute_5[74] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[75] = (compute_5[75] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[76] = (compute_5[76] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[77] = (compute_5[77] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[78] = (compute_5[78] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[79] = (compute_5[79] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[80] = (compute_5[80] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[81] = (compute_5[81] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[82] = (compute_5[82] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[83] = (compute_5[83] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[84] = (compute_5[84] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[85] = (compute_5[85] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[86] = (compute_5[86] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[87] = (compute_5[87] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[88] = (compute_5[88] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[89] = (compute_5[89] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[90] = (compute_5[90] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[91] = (compute_5[91] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[92] = (compute_5[92] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[93] = (compute_5[93] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[94] = (compute_5[94] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[95] = (compute_5[95] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[96] = (compute_5[96] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[97] = (compute_5[97] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[98] = (compute_5[98] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[99] = (compute_5[99] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[100] = (compute_5[100] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[101] = (compute_5[101] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[102] = (compute_5[102] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[103] = (compute_5[103] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[104] = (compute_5[104] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[105] = (compute_5[105] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[106] = (compute_5[106] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[107] = (compute_5[107] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[108] = (compute_5[108] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[109] = (compute_5[109] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[110] = (compute_5[110] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[111] = (compute_5[111] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[112] = (compute_5[112] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[113] = (compute_5[113] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[114] = (compute_5[114] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[115] = (compute_5[115] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[116] = (compute_5[116] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[117] = (compute_5[117] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[118] = (compute_5[118] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[119] = (compute_5[119] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[120] = (compute_5[120] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[121] = (compute_5[121] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[122] = (compute_5[122] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[123] = (compute_5[123] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[124] = (compute_5[124] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[125] = (compute_5[125] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[126] = (compute_5[126] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ compute_5[127] = (compute_5[127] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
}
}
- for (i0.inner: int32, 0, 32) {
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 8) {
+ let cse_var_1: int32 = (((i0.outer*4096) + (i0.inner*512)) + (i1.outer*16))
+ compute[ramp(cse_var_1, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_1, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -741,7 +1190,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.150 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.699 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 85f4a0773f..abe2b2f38e 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>00:46.539</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:34.526</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,18 +349,18 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:46.503</p></td>
+<td><p>00:34.489</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
<td><p>00:00.021</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
-<td><p>00:00.005</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index 73a4bd7359..71dffaec42 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -567,7 +567,8 @@ for this template</p>
waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+No: 1 GFLOPS: 52.03/52.03 result: MeasureResult(costs=(0.00444939392,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1304433345794678, timestamp=1667601805.408173) [('tile_f', [-1, 4, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,652190
+No: 2 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -689,8 +690,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8867353
-No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7734574
+No: 3 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -812,8 +813,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3861445
-No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7832639
+No: 4 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -935,8 +936,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2667763
-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, 64, 1, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7281042
+No: 5 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1058,8 +1059,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5933042
-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, 1, 64, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6032563
+No: 6 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1181,8 +1182,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3974552
-No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4588891
+No: 7 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1304,27 +1305,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3460448
-No: 7 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
- res = future.result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
- return self.__get_result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
- raise self._exception
- File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
- result = self.fn(*self.args, **self.kwargs)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
- worker = lambda *args: self._worker_run(*args)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
- return proc.recv()
- File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
- raise TimeoutError()
-TimeoutError
-
- [('tile_f', [-1, 8, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10078971
-No: 8 GFLOPS: 95.85/95.85 result: MeasureResult(costs=(0.0024152576521739126,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.324777364730835, timestamp=1667594985.9287496) [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2135492
-No: 9 GFLOPS: 0.00/95.85 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10015472
+No: 8 GFLOPS: 41.42/52.03 result: MeasureResult(costs=(0.005589530499999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.621019124984741, timestamp=1667601811.0111692) [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4850626
+No: 9 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1446,9 +1429,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8378868
-No: 10 GFLOPS: 183.75/183.75 result: MeasureResult(costs=(0.0012598921894736842,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.1338655948638916, timestamp=1667594989.324478) [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7123640
-No: 11 GFLOPS: 0.00/183.75 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8572150
+No: 10 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1570,8 +1552,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10395604
-No: 12 GFLOPS: 0.00/183.75 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10334589
+No: 11 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1693,11 +1675,13 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5547316
-No: 13 GFLOPS: 91.25/183.75 result: MeasureResult(costs=(0.002536974911111111,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3203299045562744, timestamp=1667594992.4279962) [('tile_f', [-1, 2, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,239011
-No: 14 GFLOPS: 120.98/183.75 result: MeasureResult(costs=(0.0019135878333333331,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0510101318359375, timestamp=1667594993.4070063) [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9362896
-No: 15 GFLOPS: 226.29/226.29 result: MeasureResult(costs=(0.0010230270188679245,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1771631240844727, timestamp=1667594994.0688612) [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,239890
-No: 16 GFLOPS: 0.00/226.29 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1414509
+No: 12 GFLOPS: 6.99/52.03 result: MeasureResult(costs=(0.033106311750000006,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4201440811157227, timestamp=1667601813.6674936) [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8875092
+No: 13 GFLOPS: 3.77/52.03 result: MeasureResult(costs=(0.06132851025,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.819613695144653, timestamp=1667601818.6682076) [('tile_f', [-1, 1, 2, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,6983210
+No: 14 GFLOPS: 124.47/124.47 result: MeasureResult(costs=(0.0018598417962962961,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4296081066131592, timestamp=1667601819.3106053) [('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2724816
+No: 15 GFLOPS: 75.91/124.47 result: MeasureResult(costs=(0.003049750333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.5480942726135254, timestamp=1667601819.9488645) [('tile_f', [-1, 4, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9891422
+No: 16 GFLOPS: 292.09/292.09 result: MeasureResult(costs=(0.0007925611317829458,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8134474754333496, timestamp=1667601820.614421) [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8916687
+No: 17 GFLOPS: 0.00/292.09 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1819,26 +1803,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5363060
-No: 17 GFLOPS: 0.00/226.29 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
- res = future.result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
- return self.__get_result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
- raise self._exception
- File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
- result = self.fn(*self.args, **self.kwargs)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
- worker = lambda *args: self._worker_run(*args)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
- return proc.recv()
- File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
- raise TimeoutError()
-TimeoutError
-
- [('tile_f', [-1, 8, 8, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8168064
-No: 18 GFLOPS: 0.00/226.29 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9800932
+No: 18 GFLOPS: 10.11/292.09 result: MeasureResult(costs=(0.022908447166666665,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7610547542572021, timestamp=1667601822.5637784) [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5355174
+No: 19 GFLOPS: 0.00/292.09 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1960,253 +1927,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9441420
-No: 19 GFLOPS: 0.00/226.29 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 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:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
-Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 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:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4945734
-No: 20 GFLOPS: 0.00/226.29 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 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:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
-Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 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:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4624755
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 1]), ('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, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2966493
+No: 20 GFLOPS: 30.46/292.09 result: MeasureResult(costs=(0.0075998355,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.213226318359375, timestamp=1667601823.2526355) [('tile_f', [-1, 16, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3484859
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2245,9 +1967,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,239890
+[('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8916687
Finish loading 20 records
-Time cost of this operator: 0.001338
+Time cost of this operator: 0.001197
</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 103bb3ba7c..6a076bfc33 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -595,10 +595,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.7 98.716 (1, 2, 10, 10, 3) 2 1 [310.7]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.062 0.973 (1, 6, 10, 10) 1 1 [3.062]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.978 0.311 (1, 1, 10, 10, 3) 1 1 [0.978]
-Total_time - 314.741 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.0 98.727 (1, 2, 10, 10, 3) 2 1 [310.0]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.022 0.962 (1, 6, 10, 10) 1 1 [3.022]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.976 0.311 (1, 1, 10, 10, 3) 1 1 [0.976]
+Total_time - 313.997 - - - - -
</pre></div>
</div>
</div>
@@ -649,10 +649,10 @@ 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 174.1 98.262 (1, 1, 10, 10, 6) 2 1 [174.1]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.233 1.261 (1, 6, 10, 10) 1 1 [2.233]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.845 0.477 (1, 3, 10, 10, 1) 1 1 [0.845]
-Total_time - 177.179 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.2 97.318 (1, 6, 10, 10, 1) 2 1 [100.2]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.77 1.719 (1, 6, 10, 10) 1 1 [1.77]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.991 0.963 (1, 1, 10, 10, 3) 1 1 [0.991]
+Total_time - 102.961 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 0b60e154ac..745d058531 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -529,7 +529,7 @@ 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/tmp4gz4usf4/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpgluqejqp/images/random'
</pre></div>
</div>
</div>
@@ -589,8 +589,8 @@ 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], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp4gz4usf4/images/target contains 8144 images
-/tmp/tmp4gz4usf4/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], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpgluqejqp/images/target contains 8144 images
+/tmp/tmpgluqejqp/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -702,13 +702,13 @@ 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 - 46s - loss: 0.2163 - accuracy: 0.9276 - val_loss: 0.1432 - val_accuracy: 0.9532 - 46s/epoch - 141ms/step
+328/328 - 47s - loss: 0.2240 - accuracy: 0.9252 - val_loss: 0.2493 - val_accuracy: 0.9173 - 47s/epoch - 143ms/step
Epoch 2/3
-328/328 - 44s - loss: 0.0952 - accuracy: 0.9652 - val_loss: 0.1278 - val_accuracy: 0.9585 - 44s/epoch - 133ms/step
+328/328 - 43s - loss: 0.0901 - accuracy: 0.9658 - val_loss: 0.1571 - val_accuracy: 0.9532 - 43s/epoch - 132ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0709 - accuracy: 0.9754 - val_loss: 0.1108 - val_accuracy: 0.9630 - 43s/epoch - 131ms/step
+328/328 - 43s - loss: 0.0640 - accuracy: 0.9754 - val_loss: 0.1400 - val_accuracy: 0.9535 - 43s/epoch - 132ms/step
-<keras.callbacks.History object at 0x7fe2d4297190>
+<keras.callbacks.History object at 0x7f76be7e4590>
</pre></div>
</div>
</div>
@@ -970,7 +970,7 @@ 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 42.250 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 38.646 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 a975589262..0baf71fc7f 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>05:44.133</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:39.446</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,19 +349,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:42.250</p></td>
+<td><p>04:38.646</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:49.972</p></td>
+<td><p>00:49.358</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:08.224</p></td>
+<td><p>00:07.718</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.686</p></td>
+<td><p>00:03.722</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index ce34d41747..e30003a41b 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>00:44.013</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:43.480</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>00:31.883</p></td>
+<td><p>00:31.638</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>00:10.333</p></td>
+<td><p>00:10.128</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>00:01.790</p></td>
+<td><p>00:01.707</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 e74caab4b9..7b3eb0914a 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -535,7 +535,7 @@ 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 0x7fe2f6607950>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f770e8c5320>
</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 b158b98912..2d7e9689cb 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>00:06.318</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:06.008</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,11 +349,11 @@
</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>00:03.915</p></td>
+<td><p>00:03.693</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>00:01.087</p></td>
+<td><p>00:01.007</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>
@@ -361,11 +361,11 @@
<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>00:00.548</p></td>
+<td><p>00:00.539</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>00:00.114</p></td>
+<td><p>00:00.116</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>
@@ -373,11 +373,11 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.028</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>
-<td><p>00:00.020</p></td>
+<td><p>00:00.019</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 24f1bdb064..44c222e640 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -590,7 +590,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp1pmklucr/input0.cc'\nsource_filename = \"/tmp/tmp1pmklucr/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/tmp2l4a8w3x/input0.cc'\nsource_filename = \"/tmp/tmp2l4a8w3x/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/reference/api/doxygen/classtvm_1_1tir_1_1DataTypeLegalizer-members.html b/docs/reference/api/doxygen/classtvm_1_1tir_1_1DataTypeLegalizer-members.html
index 29e6de6843..e8056dffef 100644
--- a/docs/reference/api/doxygen/classtvm_1_1tir_1_1DataTypeLegalizer-members.html
+++ b/docs/reference/api/doxygen/classtvm_1_1tir_1_1DataTypeLegalizer-members.html
@@ -74,24 +74,24 @@ $(function() {
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a4b60203572648ecb12a2aa72a552318d">ivmap_</a></td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1StmtMutator.html#a18e378023df3122893ffaf50bb89464e">operator()</a>(Stmt stmt)</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1StmtMutator.html">tvm::tir::StmtMutator</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1StmtExprMutator.html#afc4dedb17cb5f2057fc8200e6c298fab">VisitExpr</a>(const PrimExpr &e) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1StmtExprMutator.html">tvm::tir::StmtExprMutator</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">protected</span><span class="mlabel">virtual</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a3c9ea744377f09c9656cc3718eed7bfb">VisitExpr_</a>(const SelectNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#abba02eaed632f7b46d078e087f0b4217">VisitExpr_</a>(const RampNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#ace95c42561653586686d4e810b3f6760">VisitExpr_</a>(const AddNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a7faae5c6746c2911d3c4d82f4b0802cf">VisitExpr_</a>(const SubNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a1f08a5698666b1a98455ef75c1d8a434">VisitExpr_</a>(const MulNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a5bad1d0823b0e51fa7c5dbef34f49833">VisitExpr_</a>(const DivNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#ac1e09304dc701e922244e1a4587be114">VisitExpr_</a>(const ModNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a622799ab2b39ebdb6087534f4aab6d2f">VisitExpr_</a>(const FloorDivNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#ae8bfafc2f1bd2568acefa9b984caeb85">VisitExpr_</a>(const FloorModNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#af2a2d31de7d1325c00f923aff28a5904">VisitExpr_</a>(const MinNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a69fc10196783329cd24628db8d29cab6">VisitExpr_</a>(const MaxNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a1503fb6579a078beadfccbe1eba1b717">VisitExpr_</a>(const EQNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a9a526030daa59f557991710eebbcd713">VisitExpr_</a>(const NENode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#aedf84c8c4df1f4c451d41d9c9b8fa266">VisitExpr_</a>(const LTNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#ad56676b279c7602022e9515564ab746d">VisitExpr_</a>(const LENode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#ad6f857beadbb88b9db1c5bafaac59c8c">VisitExpr_</a>(const GTNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a3bee1a8d9a9fd0ab7336810682919787">VisitExpr_</a>(const GENode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#aa78adca6635007e175e6b17a4a758d40">VisitExpr_</a>(const CallNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a3c9ea744377f09c9656cc3718eed7bfb">VisitExpr_</a>(const SelectNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#abba02eaed632f7b46d078e087f0b4217">VisitExpr_</a>(const RampNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#ace95c42561653586686d4e810b3f6760">VisitExpr_</a>(const AddNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a7faae5c6746c2911d3c4d82f4b0802cf">VisitExpr_</a>(const SubNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a1f08a5698666b1a98455ef75c1d8a434">VisitExpr_</a>(const MulNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a5bad1d0823b0e51fa7c5dbef34f49833">VisitExpr_</a>(const DivNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#ac1e09304dc701e922244e1a4587be114">VisitExpr_</a>(const ModNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a622799ab2b39ebdb6087534f4aab6d2f">VisitExpr_</a>(const FloorDivNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#ae8bfafc2f1bd2568acefa9b984caeb85">VisitExpr_</a>(const FloorModNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#af2a2d31de7d1325c00f923aff28a5904">VisitExpr_</a>(const MinNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a69fc10196783329cd24628db8d29cab6">VisitExpr_</a>(const MaxNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a1503fb6579a078beadfccbe1eba1b717">VisitExpr_</a>(const EQNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a9a526030daa59f557991710eebbcd713">VisitExpr_</a>(const NENode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#aedf84c8c4df1f4c451d41d9c9b8fa266">VisitExpr_</a>(const LTNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#ad56676b279c7602022e9515564ab746d">VisitExpr_</a>(const LENode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#ad6f857beadbb88b9db1c5bafaac59c8c">VisitExpr_</a>(const GTNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a3bee1a8d9a9fd0ab7336810682919787">VisitExpr_</a>(const GENode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#aa78adca6635007e175e6b17a4a758d40">VisitExpr_</a>(const CallNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ExprMutator.html#af6e722273818f70d0894aeecd1b55615">tvm::tir::StmtExprMutator::VisitExpr_</a>(const VarNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ExprMutator.html">tvm::tir::ExprMutator</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ExprMutator.html#ade08e1786bce8d1cb220d3f54f3fbfeb">tvm::tir::StmtExprMutator::VisitExpr_</a>(const SizeVarNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ExprMutator.html">tvm::tir::ExprMutator</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ExprMutator.html#af195e0234cba3ed03d36b04a03d3e0e0">tvm::tir::StmtExprMutator::VisitExpr_</a>(const LoadNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ExprMutator.html">tvm::tir::ExprMutator</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
@@ -111,10 +111,10 @@ $(function() {
<tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ExprMutator.html#afa46554fba071aae744164711b6112ae">tvm::tir::StmtExprMutator::VisitExpr_</a>(const AnyNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ExprMutator.html">tvm::tir::ExprMutator</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1StmtMutator.html#a1e24adea3e49d9381246b376349db51f">VisitSeqStmt_</a>(const SeqStmtNode *op, bool flatten_before_visit, std::function< Stmt(const Stmt &)> fmutate=nullptr)</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1StmtMutator.html">tvm::tir::StmtMutator</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1StmtMutator.html#a4306d1beba05fa1ac582503498a6d7ce">VisitStmt</a>(const Stmt &stmt) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1StmtMutator.html">tvm::tir::StmtMutator</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">protected</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#abd51f9d25b5e2419034f028b17aded2a">VisitStmt_</a>(const ForNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#aca20c14f1f058ffb3ef6c8bba1fda6f1">VisitStmt_</a>(const AttrStmtNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#acab424302ee742c9759da1696519496a">VisitStmt_</a>(const BlockRealizeNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a74a17d6246a62100e699dec154ceef72">VisitStmt_</a>(const BlockNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#abd51f9d25b5e2419034f028b17aded2a">VisitStmt_</a>(const ForNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#aca20c14f1f058ffb3ef6c8bba1fda6f1">VisitStmt_</a>(const AttrStmtNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#acab424302ee742c9759da1696519496a">VisitStmt_</a>(const BlockRealizeNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a74a17d6246a62100e699dec154ceef72">VisitStmt_</a>(const BlockNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html">tvm::tir::DataTypeLegalizer</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1StmtMutator.html#a7bc8fad1381862ce012819bd4762a1b6">tvm::tir::StmtExprMutator::VisitStmt_</a>(const IfThenElseNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1StmtMutator.html">tvm::tir::StmtMutator</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1StmtMutator.html#a51d66e88ec3779c117bab5ba9406091c">tvm::tir::StmtExprMutator::VisitStmt_</a>(const LetStmtNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1StmtMutator.html">tvm::tir::StmtMutator</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1StmtMutator.html#a971adb4c88808a67317da73954e093b5">tvm::tir::StmtExprMutator::VisitStmt_</a>(const WhileNode *op) override</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1StmtMutator.html">tvm::tir::StmtMutator</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
diff --git a/docs/reference/api/doxygen/classtvm_1_1tir_1_1DataTypeLegalizer.html b/docs/reference/api/doxygen/classtvm_1_1tir_1_1DataTypeLegalizer.html
index 86597ac35f..b9a24262cc 100644
--- a/docs/reference/api/doxygen/classtvm_1_1tir_1_1DataTypeLegalizer.html
+++ b/docs/reference/api/doxygen/classtvm_1_1tir_1_1DataTypeLegalizer.html
@@ -63,7 +63,7 @@ $(function() {
</div><!-- top -->
<div class="header">
<div class="summary">
-<a href="#pub-methods">Public Member Functions</a> |
+<a href="#pro-methods">Protected Member Functions</a> |
<a href="#pro-attribs">Protected Attributes</a> |
<a href="classtvm_1_1tir_1_1DataTypeLegalizer-members.html">List of all members</a> </div>
<div class="headertitle">
@@ -88,8 +88,8 @@ Collaboration diagram for tvm::tir::DataTypeLegalizer:</div>
</div>
</div>
<table class="memberdecls">
-<tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="pub-methods"></a>
-Public Member Functions</h2></td></tr>
+<tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="pro-methods"></a>
+Protected Member Functions</h2></td></tr>
<tr class="memitem:abd51f9d25b5e2419034f028b17aded2a"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1tir_1_1Stmt.html">Stmt</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#abd51f9d25b5e2419034f028b17aded2a">VisitStmt_</a> (const <a class="el" href="classtvm_1_1tir_1_1ForNode.html">ForNode</a> *op) override</td></tr>
<tr class="separator:abd51f9d25b5e2419034f028b17aded2a"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:aca20c14f1f058ffb3ef6c8bba1fda6f1"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1tir_1_1Stmt.html">Stmt</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#aca20c14f1f058ffb3ef6c8bba1fda6f1">VisitStmt_</a> (const <a class="el" href="classtvm_1_1tir_1_1AttrStmtNode.html">AttrStmtNode</a> *op) override</td></tr>
@@ -134,22 +134,6 @@ Public Member Functions</h2></td></tr>
<tr class="separator:a3bee1a8d9a9fd0ab7336810682919787"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:aa78adca6635007e175e6b17a4a758d40"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1PrimExpr.html">PrimExpr</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#aa78adca6635007e175e6b17a4a758d40">VisitExpr_</a> (const <a class="el" href="classtvm_1_1tir_1_1CallNode.html">CallNode</a> *op) override</td></tr>
<tr class="separator:aa78adca6635007e175e6b17a4a758d40"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="inherit_header pub_methods_classtvm_1_1tir_1_1StmtMutator"><td colspan="2" onclick="javascript:toggleInherit('pub_methods_classtvm_1_1tir_1_1StmtMutator')"><img src="closed.png" alt="-"/> Public Member Functions inherited from <a class="el" href="classtvm_1_1tir_1_1StmtMutator.html">tvm::tir::StmtMutator</a></td></tr>
-<tr class="memitem:a18e378023df3122893ffaf50bb89464e inherit pub_methods_classtvm_1_1tir_1_1StmtMutator"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1tir_1_1Stmt.html">Stmt</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1StmtMutator.html#a18e378023df3122893ffaf50bb89464e">operator()</a> (<a class="el" href="classtvm_1_1tir_1_1Stmt.html">Stmt</a> stmt)</td></tr>
-<tr class="memdesc:a18e378023df3122893ffaf50bb89464e inherit pub_methods_classtvm_1_1tir_1_1StmtMutator"><td class="mdescLeft"> </td><td class="mdescRight">Mutate stmt. <a href="classtvm_1_1tir_1_1StmtMutator.html#a18e378023df3122893ffaf50bb89464e">More...</a><br /></td></tr>
-<tr class="separator:a18e378023df3122893ffaf50bb89464e inherit pub_methods_classtvm_1_1tir_1_1StmtMutator"><td class="memSeparator" colspan="2"> </td></tr>
-</table><table class="memberdecls">
-<tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="pro-attribs"></a>
-Protected Attributes</h2></td></tr>
-<tr class="memitem:a4b60203572648ecb12a2aa72a552318d"><td class="memItemLeft" align="right" valign="top">std::unordered_map< const <a class="el" href="classtvm_1_1tir_1_1IterVarNode.html">IterVarNode</a> *, <a class="el" href="classtvm_1_1tir_1_1IterVar.html">IterVar</a> > </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a4b60203572648ecb12a2aa72a552318d">ivmap_</a></td></tr>
-<tr class="separator:a4b60203572648ecb12a2aa72a552318d"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="inherit_header pro_attribs_classtvm_1_1tir_1_1StmtMutator"><td colspan="2" onclick="javascript:toggleInherit('pro_attribs_classtvm_1_1tir_1_1StmtMutator')"><img src="closed.png" alt="-"/> Protected Attributes inherited from <a class="el" href="classtvm_1_1tir_1_1StmtMutator.html">tvm::tir::StmtMutator</a></td></tr>
-<tr class="memitem:a620e6041832441d25ee4f4d65921231f inherit pro_attribs_classtvm_1_1tir_1_1StmtMutator"><td class="memItemLeft" align="right" valign="top">bool </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1StmtMutator.html#a620e6041832441d25ee4f4d65921231f">allow_copy_on_write_</a> {false}</td></tr>
-<tr class="memdesc:a620e6041832441d25ee4f4d65921231f inherit pro_attribs_classtvm_1_1tir_1_1StmtMutator"><td class="mdescLeft"> </td><td class="mdescRight">Internal state to indicate whether copy on write is enabled. COW is enabled iff all the parents of the node are unique. <a href="classtvm_1_1tir_1_1StmtMutator.html#a620e6041832441d25ee4f4d65921231f">More...</a><br /></td></tr>
-<tr class="separator:a620e6041832441d25ee4f4d65921231f inherit pro_attribs_classtvm_1_1tir_1_1StmtMutator"><td class="memSeparator" colspan="2"> </td></tr>
-</table><table class="memberdecls">
-<tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="inherited"></a>
-Additional Inherited Members</h2></td></tr>
<tr class="inherit_header pro_methods_classtvm_1_1tir_1_1StmtExprMutator"><td colspan="2" onclick="javascript:toggleInherit('pro_methods_classtvm_1_1tir_1_1StmtExprMutator')"><img src="closed.png" alt="-"/> Protected Member Functions inherited from <a class="el" href="classtvm_1_1tir_1_1StmtExprMutator.html">tvm::tir::StmtExprMutator</a></td></tr>
<tr class="memitem:afc4dedb17cb5f2057fc8200e6c298fab inherit pro_methods_classtvm_1_1tir_1_1StmtExprMutator"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1PrimExpr.html">PrimExpr</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1StmtExprMutator.html#afc4dedb17cb5f2057fc8200e6c298fab">VisitExpr</a> (const <a class="el" href="classtvm_1_1PrimExpr.html">PrimExpr</a> &e) override</td></tr>
<tr class="memdesc:afc4dedb17cb5f2057fc8200e6c298fab inherit pro_methods_classtvm_1_1tir_1_1StmtExprMutator"><td class="mdescLeft"> </td><td class="mdescRight">Visitor to Exprs, can be overriden to do recursive changes to Exprs. <a href="classtvm_1_1tir_1_1StmtExprMutator.html#afc4dedb17cb5f2057fc8200e6c298fab">More...</a><br /></td></tr>
@@ -274,6 +258,22 @@ Additional Inherited Members</h2></td></tr>
<tr class="separator:abe827bb16d1930225186627791cea131 inherit pro_methods_classtvm_1_1tir_1_1ExprMutator"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:afa46554fba071aae744164711b6112ae inherit pro_methods_classtvm_1_1tir_1_1ExprMutator"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1PrimExpr.html">PrimExpr</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1ExprMutator.html#afa46554fba071aae744164711b6112ae">VisitExpr_</a> (const <a class="el" href="classtvm_1_1tir_1_1AnyNode.html">AnyNode</a> *op) override</td></tr>
<tr class="separator:afa46554fba071aae744164711b6112ae inherit pro_methods_classtvm_1_1tir_1_1ExprMutator"><td class="memSeparator" colspan="2"> </td></tr>
+</table><table class="memberdecls">
+<tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="pro-attribs"></a>
+Protected Attributes</h2></td></tr>
+<tr class="memitem:a4b60203572648ecb12a2aa72a552318d"><td class="memItemLeft" align="right" valign="top">std::unordered_map< const <a class="el" href="classtvm_1_1tir_1_1IterVarNode.html">IterVarNode</a> *, <a class="el" href="classtvm_1_1tir_1_1IterVar.html">IterVar</a> > </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a4b60203572648ecb12a2aa72a552318d">ivmap_</a></td></tr>
+<tr class="separator:a4b60203572648ecb12a2aa72a552318d"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="inherit_header pro_attribs_classtvm_1_1tir_1_1StmtMutator"><td colspan="2" onclick="javascript:toggleInherit('pro_attribs_classtvm_1_1tir_1_1StmtMutator')"><img src="closed.png" alt="-"/> Protected Attributes inherited from <a class="el" href="classtvm_1_1tir_1_1StmtMutator.html">tvm::tir::StmtMutator</a></td></tr>
+<tr class="memitem:a620e6041832441d25ee4f4d65921231f inherit pro_attribs_classtvm_1_1tir_1_1StmtMutator"><td class="memItemLeft" align="right" valign="top">bool </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1StmtMutator.html#a620e6041832441d25ee4f4d65921231f">allow_copy_on_write_</a> {false}</td></tr>
+<tr class="memdesc:a620e6041832441d25ee4f4d65921231f inherit pro_attribs_classtvm_1_1tir_1_1StmtMutator"><td class="mdescLeft"> </td><td class="mdescRight">Internal state to indicate whether copy on write is enabled. COW is enabled iff all the parents of the node are unique. <a href="classtvm_1_1tir_1_1StmtMutator.html#a620e6041832441d25ee4f4d65921231f">More...</a><br /></td></tr>
+<tr class="separator:a620e6041832441d25ee4f4d65921231f inherit pro_attribs_classtvm_1_1tir_1_1StmtMutator"><td class="memSeparator" colspan="2"> </td></tr>
+</table><table class="memberdecls">
+<tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="inherited"></a>
+Additional Inherited Members</h2></td></tr>
+<tr class="inherit_header pub_methods_classtvm_1_1tir_1_1StmtMutator"><td colspan="2" onclick="javascript:toggleInherit('pub_methods_classtvm_1_1tir_1_1StmtMutator')"><img src="closed.png" alt="-"/> Public Member Functions inherited from <a class="el" href="classtvm_1_1tir_1_1StmtMutator.html">tvm::tir::StmtMutator</a></td></tr>
+<tr class="memitem:a18e378023df3122893ffaf50bb89464e inherit pub_methods_classtvm_1_1tir_1_1StmtMutator"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1tir_1_1Stmt.html">Stmt</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1StmtMutator.html#a18e378023df3122893ffaf50bb89464e">operator()</a> (<a class="el" href="classtvm_1_1tir_1_1Stmt.html">Stmt</a> stmt)</td></tr>
+<tr class="memdesc:a18e378023df3122893ffaf50bb89464e inherit pub_methods_classtvm_1_1tir_1_1StmtMutator"><td class="mdescLeft"> </td><td class="mdescRight">Mutate stmt. <a href="classtvm_1_1tir_1_1StmtMutator.html#a18e378023df3122893ffaf50bb89464e">More...</a><br /></td></tr>
+<tr class="separator:a18e378023df3122893ffaf50bb89464e inherit pub_methods_classtvm_1_1tir_1_1StmtMutator"><td class="memSeparator" colspan="2"> </td></tr>
</table>
<a name="details" id="details"></a><h2 class="groupheader">Detailed Description</h2>
<div class="textblock"><p>Legalize the data types of expressions to make sure they are consistent with other parts of the program. </p>
@@ -303,7 +303,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -329,7 +329,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -355,7 +355,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -381,7 +381,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -407,7 +407,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -433,7 +433,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -459,7 +459,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -485,7 +485,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -511,7 +511,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -537,7 +537,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -563,7 +563,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -589,7 +589,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -615,7 +615,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -641,7 +641,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -667,7 +667,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -693,7 +693,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -719,7 +719,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -745,7 +745,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -771,7 +771,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -797,7 +797,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -823,7 +823,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
@@ -849,7 +849,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</td>
<td class="mlabels-right">
-<span class="mlabels"><span class="mlabel">override</span></span> </td>
+<span class="mlabels"><span class="mlabel">override</span><span class="mlabel">protected</span></span> </td>
</tr>
</table>
</div><div class="memdoc">
diff --git a/docs/reference/api/doxygen/classtvm_1_1tir_1_1DataTypeLegalizer__coll__graph.svg b/docs/reference/api/doxygen/classtvm_1_1tir_1_1DataTypeLegalizer__coll__graph.svg
index d6cdfaf45d..f21b4caf2c 100644
--- a/docs/reference/api/doxygen/classtvm_1_1tir_1_1DataTypeLegalizer__coll__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1tir_1_1DataTypeLegalizer__coll__graph.svg
@@ -17,16 +17,16 @@
<polyline fill="none" stroke="#000000" points="74.5,-148.5 223.5,-148.5 "/>
<text text-anchor="start" x="82.5" y="-136.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ivmap_</text>
<polyline fill="none" stroke="#000000" points="74.5,-129.5 223.5,-129.5 "/>
-<text text-anchor="start" x="82.5" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitStmt_()</text>
-<text text-anchor="start" x="82.5" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitStmt_()</text>
-<text text-anchor="start" x="82.5" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitStmt_()</text>
-<text text-anchor="start" x="82.5" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitStmt_()</text>
-<text text-anchor="start" x="82.5" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="82.5" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="82.5" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="82.5" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="82.5" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="82.5" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
+<text text-anchor="start" x="82.5" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitStmt_()</text>
+<text text-anchor="start" x="82.5" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitStmt_()</text>
+<text text-anchor="start" x="82.5" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitStmt_()</text>
+<text text-anchor="start" x="82.5" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitStmt_()</text>
+<text text-anchor="start" x="82.5" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="82.5" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="82.5" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="82.5" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="82.5" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="82.5" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
<text text-anchor="start" x="82.5" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 12 more...</text>
</g>
<!-- Node7 -->
diff --git a/docs/reference/api/doxygen/classtvm_1_1tir_1_1DataTypeLegalizer__inherit__graph.svg b/docs/reference/api/doxygen/classtvm_1_1tir_1_1DataTypeLegalizer__inherit__graph.svg
index 3ab76939c4..339916e8f2 100644
--- a/docs/reference/api/doxygen/classtvm_1_1tir_1_1DataTypeLegalizer__inherit__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1tir_1_1DataTypeLegalizer__inherit__graph.svg
@@ -17,16 +17,16 @@
<polyline fill="none" stroke="#000000" points="74.5,-148.5 223.5,-148.5 "/>
<text text-anchor="start" x="82.5" y="-136.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ivmap_</text>
<polyline fill="none" stroke="#000000" points="74.5,-129.5 223.5,-129.5 "/>
-<text text-anchor="start" x="82.5" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitStmt_()</text>
-<text text-anchor="start" x="82.5" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitStmt_()</text>
-<text text-anchor="start" x="82.5" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitStmt_()</text>
-<text text-anchor="start" x="82.5" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitStmt_()</text>
-<text text-anchor="start" x="82.5" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="82.5" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="82.5" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="82.5" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="82.5" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="82.5" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
+<text text-anchor="start" x="82.5" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitStmt_()</text>
+<text text-anchor="start" x="82.5" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitStmt_()</text>
+<text text-anchor="start" x="82.5" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitStmt_()</text>
+<text text-anchor="start" x="82.5" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitStmt_()</text>
+<text text-anchor="start" x="82.5" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="82.5" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="82.5" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="82.5" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="82.5" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="82.5" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
<text text-anchor="start" x="82.5" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 12 more...</text>
</g>
<!-- Node1 -->
diff --git a/docs/reference/api/doxygen/classtvm_1_1tir_1_1ExprMutator__inherit__graph.svg b/docs/reference/api/doxygen/classtvm_1_1tir_1_1ExprMutator__inherit__graph.svg
index b3677636ee..95318ea4d1 100644
--- a/docs/reference/api/doxygen/classtvm_1_1tir_1_1ExprMutator__inherit__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1tir_1_1ExprMutator__inherit__graph.svg
@@ -77,16 +77,16 @@
<polyline fill="none" stroke="#000000" points="11.5,-148.5 160.5,-148.5 "/>
<text text-anchor="start" x="19.5" y="-136.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ivmap_</text>
<polyline fill="none" stroke="#000000" points="11.5,-129.5 160.5,-129.5 "/>
-<text text-anchor="start" x="19.5" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitStmt_()</text>
-<text text-anchor="start" x="19.5" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitStmt_()</text>
-<text text-anchor="start" x="19.5" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitStmt_()</text>
-<text text-anchor="start" x="19.5" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitStmt_()</text>
-<text text-anchor="start" x="19.5" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="19.5" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="19.5" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="19.5" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="19.5" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="19.5" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
+<text text-anchor="start" x="19.5" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitStmt_()</text>
+<text text-anchor="start" x="19.5" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitStmt_()</text>
+<text text-anchor="start" x="19.5" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitStmt_()</text>
+<text text-anchor="start" x="19.5" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitStmt_()</text>
+<text text-anchor="start" x="19.5" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="19.5" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="19.5" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="19.5" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="19.5" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="19.5" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
<text text-anchor="start" x="19.5" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 12 more...</text>
</a>
</g>
diff --git a/docs/reference/api/doxygen/classtvm_1_1tir_1_1StmtExprMutator__inherit__graph.svg b/docs/reference/api/doxygen/classtvm_1_1tir_1_1StmtExprMutator__inherit__graph.svg
index 464e67c60a..157fc5675e 100644
--- a/docs/reference/api/doxygen/classtvm_1_1tir_1_1StmtExprMutator__inherit__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1tir_1_1StmtExprMutator__inherit__graph.svg
@@ -28,16 +28,16 @@
<polyline fill="none" stroke="#000000" points="74.5,-148.5 223.5,-148.5 "/>
<text text-anchor="start" x="82.5" y="-136.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ivmap_</text>
<polyline fill="none" stroke="#000000" points="74.5,-129.5 223.5,-129.5 "/>
-<text text-anchor="start" x="82.5" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitStmt_()</text>
-<text text-anchor="start" x="82.5" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitStmt_()</text>
-<text text-anchor="start" x="82.5" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitStmt_()</text>
-<text text-anchor="start" x="82.5" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitStmt_()</text>
-<text text-anchor="start" x="82.5" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="82.5" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="82.5" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="82.5" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="82.5" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="82.5" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
+<text text-anchor="start" x="82.5" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitStmt_()</text>
+<text text-anchor="start" x="82.5" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitStmt_()</text>
+<text text-anchor="start" x="82.5" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitStmt_()</text>
+<text text-anchor="start" x="82.5" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitStmt_()</text>
+<text text-anchor="start" x="82.5" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="82.5" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="82.5" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="82.5" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="82.5" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="82.5" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
<text text-anchor="start" x="82.5" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 12 more...</text>
</a>
</g>
diff --git a/docs/reference/api/doxygen/classtvm_1_1tir_1_1StmtMutator__inherit__graph.svg b/docs/reference/api/doxygen/classtvm_1_1tir_1_1StmtMutator__inherit__graph.svg
index f1e22e6666..51c13c8c1c 100644
--- a/docs/reference/api/doxygen/classtvm_1_1tir_1_1StmtMutator__inherit__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1tir_1_1StmtMutator__inherit__graph.svg
@@ -78,16 +78,16 @@
<polyline fill="none" stroke="#000000" points="0,-148.5 149,-148.5 "/>
<text text-anchor="start" x="8" y="-136.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ivmap_</text>
<polyline fill="none" stroke="#000000" points="0,-129.5 149,-129.5 "/>
-<text text-anchor="start" x="8" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitStmt_()</text>
-<text text-anchor="start" x="8" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitStmt_()</text>
-<text text-anchor="start" x="8" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitStmt_()</text>
-<text text-anchor="start" x="8" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitStmt_()</text>
-<text text-anchor="start" x="8" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="8" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="8" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="8" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="8" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
-<text text-anchor="start" x="8" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitExpr_()</text>
+<text text-anchor="start" x="8" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitStmt_()</text>
+<text text-anchor="start" x="8" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitStmt_()</text>
+<text text-anchor="start" x="8" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitStmt_()</text>
+<text text-anchor="start" x="8" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitStmt_()</text>
+<text text-anchor="start" x="8" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="8" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="8" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="8" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="8" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
+<text text-anchor="start" x="8" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># VisitExpr_()</text>
<text text-anchor="start" x="8" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 12 more...</text>
</a>
</g>
diff --git a/docs/reference/api/doxygen/stmt__functor_8h_source.html b/docs/reference/api/doxygen/stmt__functor_8h_source.html
index edb4653087..85816ea57c 100644
--- a/docs/reference/api/doxygen/stmt__functor_8h_source.html
+++ b/docs/reference/api/doxygen/stmt__functor_8h_source.html
@@ -66,7 +66,7 @@ $(function() {
<div class="title">stmt_functor.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="stmt__functor_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or mo [...]
+<a href="stmt__functor_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or mo [...]
<div class="ttc" id="classtvm_1_1tir_1_1StmtFunctor_3_01R_07const_01Stmt_01_6n_00_01Args_8_8_8_01args_08_4_html_a980c3e5119d1898c9c9a3f5003428aef"><div class="ttname"><a href="classtvm_1_1tir_1_1StmtFunctor_3_01R_07const_01Stmt_01_6n_00_01Args_8_8_8_01args_08_4.html#a980c3e5119d1898c9c9a3f5003428aef">tvm::tir::StmtFunctor< R(const Stmt &n, Args... args)>::VisitStmt_</a></div><div class="ttdeci">virtual R VisitStmt_(const LetStmtNode *op, Args... args)</div><div class="ttdef"><b [...]
<div class="ttc" id="classtvm_1_1NodeFunctor_html"><div class="ttname"><a href="classtvm_1_1NodeFunctor.html">tvm::NodeFunctor</a></div><div class="ttdoc">A dynamically dispatched functor on the type of the first argument. </div><div class="ttdef"><b>Definition:</b> functor.h:64</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1AttrStmtNode_html"><div class="ttname"><a href="classtvm_1_1tir_1_1AttrStmtNode.html">tvm::tir::AttrStmtNode</a></div><div class="ttdoc">Define certain auxiliary attribute for the body to be a symbolic value. This provide auxiliary inform...</div><div class="ttdef"><b>Definition:</b> stmt.h:117</div></div>
@@ -174,7 +174,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1tir_1_1SelectNode_html"><div class="ttname"><a href="classtvm_1_1tir_1_1SelectNode.html">tvm::tir::SelectNode</a></div><div class="ttdoc">return true_value if condition is true, otherwise return false_value. </div><div class="ttdef"><b>Definition:</b> expr.h:552</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1StmtFunctor_3_01R_07const_01Stmt_01_6n_00_01Args_8_8_8_01args_08_4_html_ab3302cd65bf351550e383b0320fdb103"><div class="ttname"><a href="classtvm_1_1tir_1_1StmtFunctor_3_01R_07const_01Stmt_01_6n_00_01Args_8_8_8_01args_08_4.html#ab3302cd65bf351550e383b0320fdb103">tvm::tir::StmtFunctor< R(const Stmt &n, Args... args)>::VisitStmt_</a></div><div class="ttdeci">virtual R VisitStmt_(const BlockNode *op, Args... args)</div><div class="ttdef"><b>D [...]
<div class="ttc" id="classtvm_1_1tir_1_1DivNode_html"><div class="ttname"><a href="classtvm_1_1tir_1_1DivNode.html">tvm::tir::DivNode</a></div><div class="ttdoc">a / b in the C semnatics. </div><div class="ttdef"><b>Definition:</b> expr.h:206</div></div>
-<div class="ttc" id="classtvm_1_1tir_1_1DataTypeLegalizer_html_a4b60203572648ecb12a2aa72a552318d"><div class="ttname"><a href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a4b60203572648ecb12a2aa72a552318d">tvm::tir::DataTypeLegalizer::ivmap_</a></div><div class="ttdeci">std::unordered_map< const IterVarNode *, IterVar > ivmap_</div><div class="ttdef"><b>Definition:</b> stmt_functor.h:536</div></div>
+<div class="ttc" id="classtvm_1_1tir_1_1DataTypeLegalizer_html_a4b60203572648ecb12a2aa72a552318d"><div class="ttname"><a href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a4b60203572648ecb12a2aa72a552318d">tvm::tir::DataTypeLegalizer::ivmap_</a></div><div class="ttdeci">std::unordered_map< const IterVarNode *, IterVar > ivmap_</div><div class="ttdef"><b>Definition:</b> stmt_functor.h:535</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1ExprMutator_html_af6e722273818f70d0894aeecd1b55615"><div class="ttname"><a href="classtvm_1_1tir_1_1ExprMutator.html#af6e722273818f70d0894aeecd1b55615">tvm::tir::ExprMutator::VisitExpr_</a></div><div class="ttdeci">PrimExpr VisitExpr_(const VarNode *op) override</div></div>
<div class="ttc" id="structtvm_1_1tir_1_1LENode_html"><div class="ttname"><a href="structtvm_1_1tir_1_1LENode.html">tvm::tir::LENode</a></div><div class="ttdoc">a <= b </div><div class="ttdef"><b>Definition:</b> expr.h:385</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1StmtFunctor_3_01R_07const_01Stmt_01_6n_00_01Args_8_8_8_01args_08_4_html_a3d1c16d316eac87f2dcaee67152bea84"><div class="ttname"><a href="classtvm_1_1tir_1_1StmtFunctor_3_01R_07const_01Stmt_01_6n_00_01Args_8_8_8_01args_08_4.html#a3d1c16d316eac87f2dcaee67152bea84">tvm::tir::StmtFunctor< R(const Stmt &n, Args... args)>::VisitStmt_</a></div><div class="ttdeci">virtual R VisitStmt_(const AllocateNode *op, Args... args)</div><div class="ttdef">< [...]
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 7a625e5166..3be3c88b46 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 8e4831e48c..04eb5e21ec 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/6da298b3a/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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 5f5459c67a..19a9688ec7 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/6da298b3a/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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 1895b8b9cf..4ef4ffc34d 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/6da298b3a/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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 6c4b5c79af..fad1657030 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/6da298b3a/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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 49585f5abb..65c346e62d 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/6da298b3a/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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 2a77d6abc0..8ac31d7e30 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/6da298b3a/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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 f124bce500..bbbc985ff2 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/6da298b3a/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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 2a47ce356f..acb1e3af56 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/6da298b3a/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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 b05f1da76c..8781a719d0 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/6da298b3a/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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 659aa976ee..91f428cea7 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/6da298b3a/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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 065fd49d6e..7020181fdb 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/6da298b3a/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/dec74cb93/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/6da298b3a/web/src/runtime.ts#L414">runtime.ts:414</a></li>
... 1931 lines suppressed ...