You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/09/07 10:01:59 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@291dd2f06331342f5c89216d5d211cb61fe3d19f)
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 f115ca4ba deploying docs (apache/tvm@291dd2f06331342f5c89216d5d211cb61fe3d19f)
f115ca4ba is described below
commit f115ca4ba469050120419e9558aaed54d51b07f0
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed Sep 7 10:01:53 2022 +0000
deploying docs (apache/tvm@291dd2f06331342f5c89216d5d211cb61fe3d19f)
---
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1223 +++++++-------------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 112 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 26 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 10 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../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 | 2 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 54 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 26 +-
.../tutorial/tensor_expr_get_started.rst.txt | 46 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.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 | 7 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 26 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 18 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 39 +-
docs/how_to/deploy_models/sg_execution_times.html | 22 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1223 +++++++-------------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 112 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 26 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 10 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/install/nnpack.html | 12 +-
docs/reference/api/doxygen/elemwise_8h_source.html | 2 +-
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 | 2 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 258 ++---
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 46 +-
123 files changed, 1730 insertions(+), 2559 deletions(-)
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 3e4c9e04f..29809c73a 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -317,7 +317,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.525 seconds)
+ **Total running time of the script:** ( 1 minutes 4.926 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
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 c69e501bf..3f7d08eeb 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.zip167275a7-b583-4082-8d06-98b5c563db04 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip445e3ca6-aee7-42f7-849a-fc778a269f05 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 71dd6e19f..2fc94ea27 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -113,7 +113,7 @@ 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]
14%|#3 | 5.80M/41.5M [00:00<00:00, 60.6MB/s]
28%|##7 | 11.6M/41.5M [00:00<00:00, 58.5MB/s]
41%|####1 | 17.2M/41.5M [00:00<00:00, 58.3MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 46.3MB/s]
71%|####### | 29.3M/41.5M [00:00<00:00, 49.0MB/s]
83%|########2 | 34.3M/41.5M [00:00<00:00, 46.1MB/s]
96%|#########6| 40.0M/41.5M [00:00<00:00, 43.9MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 48.2MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 58.0MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 53.4MB/s]
47%|####6 | 19.4M/41.5M [00:00<00:00, 53.2MB/s]
59%|#####8 | 24.5M/41.5M [00:00<00:00, 43.4MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 43.0MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 41.5MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 43.8MB/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 a8b5506e0..20943a3aa 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -94,7 +94,7 @@ Load a pretrained PyTorch model
.. code-block:: none
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
7%|6 | 2.99M/44.7M [00:00<00:01, 31.3MB/s]
13%|#3 | 5.98M/44.7M [00:00<00:01, 30.1MB/s]
57%|#####6 | 25.3M/44.7M [00:00<00:00, 107MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 121MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
47%|####7 | 21.0M/44.7M [00:00<00:00, 221MB/s]
94%|#########4| 42.1M/44.7M [00:00<00:00, 214MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 219MB/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 0144d7b08..34d1a4f73 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -423,7 +423,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.490 seconds)
+ **Total running time of the script:** ( 1 minutes 10.886 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 fb1913e3f..ae100677c 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
=================
-**05:18.579** total execution time for **how_to_compile_models** files:
+**05:19.529** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:06.490 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:10.886 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:01.525 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:04.926 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:43.045 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:40.626 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:29.785 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:29.073 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:27.008 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:25.918 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.786 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:25.452 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:24.074 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.338 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:21.043 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:20.021 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.376 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:15.804 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.448 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.485 | 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 fb48d4d90..a08f55cd9 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
@@ -441,7 +441,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.8905 16.6728 17.8270 16.5003 0.4589
+ 16.1371 16.1048 16.3327 16.0200 0.1011
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 6f0317d96..694dbf624 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -123,7 +123,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
11%|# | 18.4M/170M [00:00<00:00, 193MB/s]
25%|##5 | 42.8M/170M [00:00<00:00, 230MB/s]
40%|###9 | 67.5M/170M [00:00<00:00, 243MB/s]
54%|#####4 | 92.1M/170M [00:00<00:00, 249MB/s]
68%|######8 | 116M/170M [00:00<00:00, 200MB/s]
81%|######## | 137M/170M [00:00<00:00, 206MB/s]
94%|#########3| 159M/170M [00:00<00:00, 214MB/s]
100%|##########| 170M/170M [00:00<00:00, 217MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
9%|8 | 15.0M/170M [00:00<00:01, 157MB/s]
23%|##3 | 39.4M/170M [00:00<00:00, 215MB/s]
37%|###6 | 62.7M/170M [00:00<00:00, 228MB/s]
51%|#####1 | 87.3M/170M [00:00<00:00, 240MB/s]
66%|######5 | 112M/170M [00:00<00:00, 247MB/s]
80%|#######9 | 136M/170M [00:00<00:00, 243MB/s]
93%|#########3| 159M/170M [00:00<00:00, 241MB/s]
100%|##########| 170M/170M [00:00<00:00, 235MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -292,7 +292,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 20.881 seconds)
+ **Total running time of the script:** ( 3 minutes 5.180 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 230188a34..5ef8fa431 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -232,7 +232,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
40%|###9 | 5.41M/13.6M [00:00<00:00, 56.6MB/s]
80%|#######9 | 10.8M/13.6M [00:00<00:00, 52.1MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 61.6MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 160MB/s]
@@ -412,7 +412,7 @@ 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)
- 91.0258 90.8413 96.8919 90.6255 0.6976
+ 90.5833 90.2846 105.2855 90.0211 1.6182
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 16.120 seconds)
+ **Total running time of the script:** ( 1 minutes 12.750 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 9d41f7982..f3075636d 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
@@ -439,7 +439,7 @@ 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)
- 124.1265 124.0905 125.6675 123.5366 0.4035
+ 121.5965 121.4984 123.6207 121.0157 0.3948
@@ -476,7 +476,7 @@ 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 3.211 seconds)
+ **Total running time of the script:** ( 1 minutes 58.626 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 52f6d4d6c..29052d9ab 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -255,7 +255,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 13.657 seconds)
+ **Total running time of the script:** ( 1 minutes 32.904 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 95458c2ab..a0cd88370 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -158,7 +158,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
1%|1 | 1601/132723 [00:00<00:08, 16008.72KB/s]
6%|6 | 8469/132723 [00:00<00:02, 46988.85KB/s]
12%|#1 | 15677/132723 [00:00<00:02, 58443.71KB/s]
17%|#7 | 22777/132723 [00:00<00:01, 63394.88KB/s]
22%|##2 | 29506/132723 [00:00<00:01, 64794.26KB/s]
28%|##7 | 36607/132723 [00:00<00:01, 66906.06KB/s]
33%|###3 | 43819/132723 [00:00<00:01, 68607.71KB/s]
38%|###8 | 51026/132723 [00:00<00:01, 69707.27KB/s]
44%|####4 | 58453/132723 [00:00<00:01, 71131.64KB/s]
50%|####9 | 66011/132723 [00:01<00:00, 72503.04KB/s]
56%|#####5 | 73715/132723 [00:01<00:00, 73888.92KB/s]
61%|######1 | 81392/132723 [00:01<00:00, 74763.33KB/s]
67%|######7 | 89024/132723 [00:01<00:00, 75231.90KB/s]
73%|#######2 | 96665/132723 [00:01<00:00, 75585.40KB/s]
79%|#######8 | 104256/132723 [00:01<00:00, 75682.33KB/s]
84%|########4 |
111936/132723 [00:01<00:00, 76016.02KB/s]
90%|######### | 119564/132723 [00:01<00:00, 76093.45KB/s]
96%|#########5| 127176/132723 [00:01<00:00, 76098.73KB/s]
100%|##########| 132723/132723 [00:01<00:00, 70871.84KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6355/132723 [00:00<00:01, 63542.18KB/s]
11%|# | 14091/132723 [00:00<00:01, 71667.43KB/s]
16%|#6 | 21758/132723 [00:00<00:01, 73948.49KB/s]
22%|##2 | 29504/132723 [00:00<00:01, 75332.98KB/s]
28%|##8 | 37275/132723 [00:00<00:01, 76188.10KB/s]
34%|###3 | 45033/132723 [00:00<00:01, 76659.11KB/s]
40%|###9 | 52753/132723 [00:00<00:01, 76834.46KB/s]
46%|####5 | 60489/132723 [00:00<00:00, 76999.33KB/s]
51%|#####1 | 68189/132723 [00:00<00:00, 76939.24KB/s]
57%|#####7 | 75886/132723 [00:01<00:00, 76945.92KB/s]
63%|######3 | 83618/132723 [00:01<00:00, 77057.40KB/s]
69%|######8 | 91339/132723 [00:01<00:00, 77101.71KB/s]
75%|#######4 | 99050/132723 [00:01<00:00, 76768.10KB/s]
80%|######## | 106734/132723 [00:01<00:00, 76786.85KB/s]
86%|########6 | 114413/132723 [00:01<00:00, 76776.09KB/s]
92%|#########
2| 122145/132723 [00:01<00:00, 76936.25KB/s]
98%|#########7| 129842/132723 [00:01<00:00, 76945.41KB/s]
100%|##########| 132723/132723 [00:01<00:00, 75760.24KB/s]
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 49.419 seconds)
+ **Total running time of the script:** ( 2 minutes 43.524 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 032343c68..2eec1f87a 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
=================
-**12:04.950** total execution time for **how_to_deploy_models** files:
+**11:50.862** 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``) | 03:20.881 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:05.180 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:49.419 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:43.524 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:03.211 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:58.626 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:16.120 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:32.904 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:13.657 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:12.750 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:33.012 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:32.114 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:24.655 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:23.012 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:23.989 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.747 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 617de2261..f3dbb76f6 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -476,7 +476,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip1f69daf0-5c8d-4cef-80da-2d76f3870040 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip0a08b11c-cd0e-4332-8020-a2b68519faeb 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 0a97ce6a2..544af19a6 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
=================
-**00:46.209** total execution time for **how_to_extend_tvm** files:
+**00:44.107** 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``) | 00:42.616 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:40.713 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.518 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.378 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.067 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.009 | 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 8efb089eb..92f409596 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: 7700us [7700us] (46.17%; 46.17%)
- FoldScaleAxis: 8976us [9us] (53.83%; 53.83%)
- FoldConstant: 8968us [1876us] (53.77%; 99.90%)
- InferType: 7091us [7091us] (42.52%; 79.08%)
+ InferType: 7253us [7253us] (45.69%; 45.69%)
+ FoldScaleAxis: 8623us [9us] (54.31%; 54.31%)
+ FoldConstant: 8613us [1775us] (54.25%; 99.89%)
+ InferType: 6838us [6838us] (43.07%; 79.39%)
@@ -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: 7559us [7559us] (45.35%; 45.35%)
- FoldScaleAxis: 9110us [8us] (54.65%; 54.65%)
- FoldConstant: 9101us [1821us] (54.60%; 99.91%)
- InferType: 7280us [7280us] (43.67%; 79.99%)
+ InferType: 7000us [7000us] (45.12%; 45.12%)
+ FoldScaleAxis: 8515us [9us] (54.88%; 54.88%)
+ FoldConstant: 8506us [1740us] (54.82%; 99.90%)
+ InferType: 6766us [6766us] (43.61%; 79.54%)
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 17922b805..5d0fc7027 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: 40.744520 ms
+ Convolution: 35.900186 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 54284df3e..726479a8d 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -671,7 +671,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 13.358382 ms
+ conv2d with tensor core: 12.516104 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 9db09e52f..53d1cda0c 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: 0.020113
- Baseline: 3.602078
+ Numpy running time: 0.019695
+ Baseline: 3.467897
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.335986
+ Opt1: 0.330038
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.351040
+ Opt2: 0.358754
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.144266
+ Opt3: 0.122143
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.113638
+ Opt4: 0.111136
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.115786
+ Opt5: 0.111323
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.151466
+ Opt6: 0.148002
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 bdab55656..73cc815f2 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
=================
-**00:36.617** total execution time for **how_to_optimize_operators** files:
+**00:35.648** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:34.285 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:33.346 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.320 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.283 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.012 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.019 | 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 93100eabb..e3e06c938 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**06:44.630** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:15.978** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:36.072 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:25.858 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:27.927 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:24.657 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:49.676 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:48.451 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:31.772 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:18.740 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:09.678 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:09.242 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:09.506 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:09.030 | 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 ffabf3ebc..875aed63d 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
@@ -241,426 +241,272 @@ cooperative fetching, unrolling and operator fusion.
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" = 64;
- allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), 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" = 49 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[4] = 0f32
+ allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [2592]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[7] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- let cse_var_2: int32 = (rc.outer.outer*784)
- let cse_var_1: int32 = (rc.outer.outer*144)
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ for (rc.outer.outer: int32, 0, 16) {
+ let cse_var_2: int32 = (rc.outer.outer*1568)
+ let cse_var_1: int32 = (rc.outer.outer*288)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 49)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 49), 81)) && (floormod((threadIdx.x_1 + 49), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 49), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 49), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 8), 9)) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 147)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 66), 81)) && (floormod((threadIdx.x_1 + 66), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 147), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 66), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 34), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 245)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 2), 81)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 245), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 2), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 51), 81)) && (floormod((threadIdx.x_1 + 51), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 294), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 51), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 343)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 1), 9)) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 343), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 19), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 441)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 4), 9)) && (floormod((threadIdx.x_1 + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 441), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 4), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 490)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 4), 81)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 490), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 4), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 539)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 53), 81)) && (floormod((threadIdx.x_1 + 53), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 539), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 53), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 588), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 21), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 637)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 70), 81)) && (floormod((threadIdx.x_1 + 70), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 637), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 70), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 686)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 38), 81)) && (floormod((threadIdx.x_1 + 38), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 686), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 38), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 735)] = @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 + 735), 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" = 49;
+ 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;
+ pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 49), 81)) && (floormod((threadIdx.x_1 + 49), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((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_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else((((threadIdx.x_1 < 48) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 672), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 24), 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 + 728)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 80), 81)) && (floormod((threadIdx.x_1 + 80), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 728), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 80), 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 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 833)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 5), 9)) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 833), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 23), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 882)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 8), 9)) && (floormod((threadIdx.x_1 + 72), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 882), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 8), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 931)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 40), 81)) && (floormod((threadIdx.x_1 + 40), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 931), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 40), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 8), 81)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 980), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 8), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1029)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 57), 81)) && (floormod((threadIdx.x_1 + 57), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1029), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 57), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1078)] = @tir.if_then_else((((threadIdx.x_1 < 47) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1078), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 25), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1127)] = @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 + 1127), 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" = 49;
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 840)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 30), 81)) && (floormod((threadIdx.x_1 + 30), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 840), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 30), 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 + 896)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 5), 81)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 896), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 5), 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 + 952)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 61), 81)) && (floormod((threadIdx.x_1 + 61), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 952), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 61), 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 + 1008)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 4), 9)) && (floormod((threadIdx.x_1 + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1008), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 4), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1064)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 2), 9)) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1064), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 11), 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 + 1120)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 67), 81)) && (floormod((threadIdx.x_1 + 67), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1120), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 67), 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 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 42), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 42), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1225)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 1), 9)) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1225), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_1 < 22), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 1274)] = @tir.if_then_else((((threadIdx.x_1 < 13) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1274), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 59), 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 + 1232)] = @tir.if_then_else((((threadIdx.x_1 < 55) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1232), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1288)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 73), 81)) && (floormod((threadIdx.x_1 + 73), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1288), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 73), 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 + 1344)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 48), 81)) && (floormod((threadIdx.x_1 + 48), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1344), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 48), 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 + 1400)] = @tir.if_then_else((((threadIdx.x_1 < 49) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1400), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 23), 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 + 1456)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 79), 81)) && (floormod((threadIdx.x_1 + 79), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1456), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 79), 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 + 1512)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 6), 9)) && (floormod((threadIdx.x_1 + 54), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1512), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 6), 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 + 1568)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 29), 81)) && (floormod((threadIdx.x_1 + 29), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1568), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 29), 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 + 1624)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 4), 81)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1624), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 4), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1680)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 60), 81)) && (floormod((threadIdx.x_1 + 60), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1680), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 60), 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 + 1736)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 35), 81)) && (floormod((threadIdx.x_1 + 35), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1736), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 35), 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 + 1792)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 1), 9)) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1792), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 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 + 1848)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 66), 81)) && (floormod((threadIdx.x_1 + 66), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1848), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 66), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1904)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 41), 81)) && (floormod((threadIdx.x_1 + 41), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1904), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 41), 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 + 1960)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 7), 9)) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1960), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 16), 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 + 2016)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 8), 9)) && (floormod((threadIdx.x_1 + 72), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2016), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 8), 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 + 2072)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 47), 81)) && (floormod((threadIdx.x_1 + 47), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2072), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 47), 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 + 2128)] = @tir.if_then_else((((threadIdx.x_1 < 50) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2128), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 22), 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 + 2184)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 78), 81)) && (floormod((threadIdx.x_1 + 78), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2184), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 78), 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 + 2240)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 53), 81)) && (floormod((threadIdx.x_1 + 53), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2240), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 53), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2296)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 28), 81)) && (floormod((threadIdx.x_1 + 28), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2296), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 28), 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 + 2352)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 3), 81)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2352), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 3), 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 + 2408)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 59), 81)) && (floormod((threadIdx.x_1 + 59), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2408), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 59), 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 + 2464)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 34), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2464), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2520)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2520), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 1)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 2576)] = @tir.if_then_else((((threadIdx.x_1 < 7) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2576), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 65), 81), 9)*7)) + (threadIdx.x_1 + 2)) - 8)], 0f32, dtype=float32)
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*36864) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 49)] = kernel[((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 49), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 98), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 147)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 147), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 1)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 196), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 52), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 245)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 245), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 101), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 294)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 294), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 2)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 343)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 343), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 55), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 441)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 441), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 490)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 490), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 58), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 539)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 539), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 107), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 588), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 637)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 637), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 61), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 686)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 686), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 110), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 735)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 735), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 5)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 784), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 833)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 833), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 113), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 882)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 882), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 6)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 931)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 931), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 67), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 980), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 116), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1029)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1029), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 7)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1078)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1078), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 70), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_2 < 25), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 1127)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1127), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 119), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*36864) + 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*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 56), 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*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 112), 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*36864) + cse_var_1) + threadIdx.x_2) + 168)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 224), 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*36864) + (floordiv((threadIdx.x_2 + 280), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 280), 288), 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*36864) + (floordiv((threadIdx.x_2 + 336), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*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*36864) + (floordiv((threadIdx.x_2 + 392), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 288), 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*36864) + (floordiv((threadIdx.x_2 + 448), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 160), 288), 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*36864) + (floordiv((threadIdx.x_2 + 504), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 72)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 560), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 272), 288), 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*36864) + (floordiv((threadIdx.x_2 + 616), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 288), 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*36864) + (floordiv((threadIdx.x_2 + 672), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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*36864) + (floordiv((threadIdx.x_2 + 728), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 152), 288), 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*36864) + (floordiv((threadIdx.x_2 + 784), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 208), 288), 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*36864) + (floordiv((threadIdx.x_2 + 840), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 88), 96)*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*36864) + (floordiv((threadIdx.x_2 + 896), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 288), 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*36864) + (floordiv((threadIdx.x_2 + 952), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 288), 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*36864) + (floordiv((threadIdx.x_2 + 1008), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1064), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 200), 288), 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 + 1120)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1120), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 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 + 1176)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1176), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1232), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 288), 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 + 1288)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1288), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 288), 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 + 1344)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1344), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 64)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1400), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 248), 288), 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 + 1456)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1456), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 288), 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 + 1512)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1512), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 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 + 1568)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1568), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 288), 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 + 1624)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1624), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 184), 288), 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 + 1680)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1680), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 80), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1736)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1736), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 288), 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 + 1792)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1792), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 288), 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 + 1848)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1848), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 40)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1904), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 288), 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 + 1960)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1960), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 232), 288), 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 + 2016)] = kernel[((((blockIdx.x*36864) + 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 + 2072)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 2072), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 288), 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 + 2128)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 2128), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 288), 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 + 2184)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 2184), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 56)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 2240), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 224), 288), 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 < 8), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 2296)] = kernel[(((((blockIdx.x*36864) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 280), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3)) + 32256)]
}
- for (rc.outer.inner: int32, 0, 4) {
- let cse_var_3: int32 = (rc.outer.inner*36)
- {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[cse_var_3]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 576)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 585)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(cse_var_3 + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(cse_var_3 + 594)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(cse_var_3 + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(cse_var_3 + 603)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 144)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 720)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 153)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 729)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(cse_var_3 + 162)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(cse_var_3 + 738)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(cse_var_3 + 171)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(cse_var_3 + 747)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 288)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 864)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 297)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 873)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(cse_var_3 + 306)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(cse_var_3 + 882)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(cse_var_3 + 315)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(cse_var_3 + 891)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 432)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 1008)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 441)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 1017)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(cse_var_3 + 450)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(cse_var_3 + 1026)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(cse_var_3 + 459)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(cse_var_3 + 1035)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 577)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 586)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(cse_var_3 + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(cse_var_3 + 595)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(cse_var_3 + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(cse_var_3 + 604)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 145)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 721)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 154)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 730)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(cse_var_3 + 163)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(cse_var_3 + 739)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(cse_var_3 + 172)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(cse_var_3 + 748)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 289)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 865)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 298)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 874)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(cse_var_3 + 307)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(cse_var_3 + 883)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(cse_var_3 + 316)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(cse_var_3 + 892)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 433)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 1009)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 442)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 1018)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(cse_var_3 + 451)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(cse_var_3 + 1027)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(cse_var_3 + 460)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(cse_var_3 + 1036)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 578)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 587)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(cse_var_3 + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(cse_var_3 + 596)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(cse_var_3 + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(cse_var_3 + 605)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 146)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 722)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 155)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 731)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(cse_var_3 + 164)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(cse_var_3 + 740)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(cse_var_3 + 173)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(cse_var_3 + 749)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 290)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 866)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 299)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 875)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(cse_var_3 + 308)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(cse_var_3 + 884)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(cse_var_3 + 317)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(cse_var_3 + 893)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 434)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 1010)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 443)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 1019)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(cse_var_3 + 452)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(cse_var_3 + 1028)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(cse_var_3 + 461)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(cse_var_3 + 1037)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 579)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 588)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(cse_var_3 + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(cse_var_3 + 597)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_3 + 30)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_3 + 606)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 147)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 723)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 156)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 732)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(cse_var_3 + 165)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(cse_var_3 + 741)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_3 + 174)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_3 + 750)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 291)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 867)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 300)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 876)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(cse_var_3 + 309)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(cse_var_3 + 885)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_3 + 318)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_3 + 894)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 435)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 1011)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 444)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 1020)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(cse_var_3 + 453)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(cse_var_3 + 1029)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_3 + 462)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_3 + 1038)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 580)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 589)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(cse_var_3 + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(cse_var_3 + 598)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_3 + 31)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_3 + 607)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 148)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 724)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 157)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 733)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(cse_var_3 + 166)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(cse_var_3 + 742)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_3 + 175)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_3 + 751)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 292)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 868)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 301)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 877)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(cse_var_3 + 310)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(cse_var_3 + 886)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_3 + 319)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_3 + 895)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 436)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 1012)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 445)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 1021)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(cse_var_3 + 454)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(cse_var_3 + 1030)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_3 + 463)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_3 + 1039)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 581)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 590)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(cse_var_3 + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(cse_var_3 + 599)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_3 + 32)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_3 + 608)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 149)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 725)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 158)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 734)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(cse_var_3 + 167)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(cse_var_3 + 743)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_3 + 176)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_3 + 752)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 293)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 869)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 302)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 878)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(cse_var_3 + 311)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(cse_var_3 + 887)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_3 + 320)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_3 + 896)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 437)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 1013)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 446)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 1022)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(cse_var_3 + 455)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(cse_var_3 + 1031)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_3 + 464)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_3 + 1040)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 582)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 591)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(cse_var_3 + 24)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(cse_var_3 + 600)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(cse_var_3 + 33)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(cse_var_3 + 609)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 150)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 726)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 159)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 735)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(cse_var_3 + 168)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(cse_var_3 + 744)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(cse_var_3 + 177)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(cse_var_3 + 753)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 294)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 870)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 303)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 879)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(cse_var_3 + 312)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(cse_var_3 + 888)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(cse_var_3 + 321)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(cse_var_3 + 897)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 438)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 1014)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 447)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 1023)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(cse_var_3 + 456)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(cse_var_3 + 1032)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(cse_var_3 + 465)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(cse_var_3 + 1041)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 583)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 592)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(cse_var_3 + 25)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(cse_var_3 + 601)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(cse_var_3 + 34)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(cse_var_3 + 610)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 151)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 727)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 160)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 736)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(cse_var_3 + 169)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(cse_var_3 + 745)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(cse_var_3 + 178)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(cse_var_3 + 754)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 295)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 871)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 304)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 880)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(cse_var_3 + 313)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(cse_var_3 + 889)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(cse_var_3 + 322)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(cse_var_3 + 898)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 439)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 1015)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 448)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 1024)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(cse_var_3 + 457)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(cse_var_3 + 1033)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(cse_var_3 + 466)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(cse_var_3 + 1042)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 584)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 593)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(cse_var_3 + 26)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(cse_var_3 + 602)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(cse_var_3 + 35)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(cse_var_3 + 611)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 152)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 728)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 161)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 737)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(cse_var_3 + 170)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(cse_var_3 + 746)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(cse_var_3 + 179)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(cse_var_3 + 755)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 296)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 872)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 305)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 881)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(cse_var_3 + 314)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(cse_var_3 + 890)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(cse_var_3 + 323)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(cse_var_3 + 899)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 440)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 1016)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 449)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 1025)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(cse_var_3 + 458)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(cse_var_3 + 1034)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(cse_var_3 + 467)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(cse_var_3 + 1043)]))
- }
+ for (rc.inner: int32, 0, 32) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.inner*81) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (rc.inner*9))]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (rc.inner*9))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (rc.inner*9))]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (rc.inner*9))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (rc.inner*9))]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (rc.inner*9))]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (rc.inner*9))]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 8)]))
}
}
}
- for (i1.inner: int32, 0, 4) {
- compute[(((blockIdx.x*392) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*8) + i1.inner)]), 0f32)
- compute[((((blockIdx.x*392) + (i1.inner*49)) + threadIdx.x) + 196)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*8) + i1.inner) + 4)]), 0f32)
+ for (i2.inner: int32, 0, 7) {
+ compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
}
}
}
@@ -715,7 +561,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.247 ms
+ Execution time of this operator: 0.231 ms
@@ -764,32 +610,32 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=4)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
- conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+ 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=7)
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=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=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_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=32)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, 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=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
- compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
@@ -812,14 +658,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -837,370 +683,181 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[8];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[1152];
+ extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[7];
+ __shared__ float pad_temp_shared[2592];
+ __shared__ float kernel_shared[2304];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++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 * 784) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 49) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 98)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 98) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((9 <= ((((int)threadIdx.x) + 66) % 81)) && (((((int)threadIdx.x) + 66) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 147) / 81) * 49)) + ((((((int)threadIdx.x) + 66) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 245)] = ((((7 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 245) / 81) * 49)) + (((((int)threadIdx.x) + 2) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((9 <= ((((int)threadIdx.x) + 51) % 81)) && (((((int)threadIdx.x) + 51) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 294) / 81) * 49)) + ((((((int)threadIdx.x) + 51) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 343)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 343) / 81) * 49)) + (((((int)threadIdx.x) + 19) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 441)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 441) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 490)] = ((((5 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 490) / 81) * 49)) + (((((int)threadIdx.x) + 4) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 539)] = (((((9 <= ((((int)threadIdx.x) + 53) % 81)) && (((((int)threadIdx.x) + 53) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 539) / 81) * 49)) + ((((((int)threadIdx.x) + 53) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 588)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 588) / 81) * 49)) + (((((int)threadIdx.x) + 21) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 637)] = (((((9 <= ((((int)threadIdx.x) + 70) % 81)) && (((((int)threadIdx.x) + 70) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 637) / 81) * 49)) + ((((((int)threadIdx.x) + 70) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((9 <= ((((int)threadIdx.x) + 38) % 81)) && (((((int)threadIdx.x) + 38) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 686) / 81) * 49)) + ((((((int)threadIdx.x) + 38) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 735)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 735) / 81) * 49)) + (((((int)threadIdx.x) + 6) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 833)] = (((1 <= ((((int)threadIdx.x) + 5) % 9)) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 833) / 81) * 49)) + (((((int)threadIdx.x) + 23) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 882)] = (((((1 <= (((((int)threadIdx.x) / 9) + 8) % 9)) && (((((int)threadIdx.x) + 72) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 882) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 8) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 931)] = (((((9 <= ((((int)threadIdx.x) + 40) % 81)) && (((((int)threadIdx.x) + 40) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 931) / 81) * 49)) + ((((((int)threadIdx.x) + 40) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 980)] = ((((1 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 980) / 81) * 49)) + (((((int)threadIdx.x) + 8) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1029)] = (((((9 <= ((((int)threadIdx.x) + 57) % 81)) && (((((int)threadIdx.x) + 57) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1029) / 81) * 49)) + ((((((int)threadIdx.x) + 57) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1078)] = ((((((int)threadIdx.x) < 47) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1078) / 81) * 49)) + (((((int)threadIdx.x) + 25) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1127)] = (((((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 * 784) + (((((int)threadIdx.x) + 1127) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1225)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1225) / 81) * 49)) + (((((int)threadIdx.x) + 10) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 22) {
- pad_temp_shared[(((int)threadIdx.x) + 1274)] = ((((((int)threadIdx.x) < 13) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1274) / 81) * 49)) + (((((int)threadIdx.x) + 59) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((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 * 1568) + (((((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 * 1568) + (((((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 * 1568) + (((((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 * 1568) + (((((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 * 1568) + (((((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 * 1568) + (((((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 * 1568) + (((((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 * 1568) + (((((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 * 1568) + (((((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 * 1568) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 616) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 672)] = ((((((int)threadIdx.x) < 48) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 672) / 81) * 49)) + (((((int)threadIdx.x) + 24) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 728)] = (((((9 <= ((((int)threadIdx.x) + 80) % 81)) && (((((int)threadIdx.x) + 80) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 728) / 81) * 49)) + ((((((int)threadIdx.x) + 80) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 840)] = (((((9 <= ((((int)threadIdx.x) + 30) % 81)) && (((((int)threadIdx.x) + 30) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 840) / 81) * 49)) + ((((((int)threadIdx.x) + 30) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 896)] = ((((4 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 896) / 81) * 49)) + (((((int)threadIdx.x) + 5) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 952)] = (((((9 <= ((((int)threadIdx.x) + 61) % 81)) && (((((int)threadIdx.x) + 61) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 952) / 81) * 49)) + ((((((int)threadIdx.x) + 61) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1008) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1064)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1064) / 81) * 49)) + (((((int)threadIdx.x) + 11) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1120) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1232)] = ((((((int)threadIdx.x) < 55) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1232) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1288)] = (((((9 <= ((((int)threadIdx.x) + 73) % 81)) && (((((int)threadIdx.x) + 73) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1288) / 81) * 49)) + ((((((int)threadIdx.x) + 73) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((9 <= ((((int)threadIdx.x) + 48) % 81)) && (((((int)threadIdx.x) + 48) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1344) / 81) * 49)) + ((((((int)threadIdx.x) + 48) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1400)] = ((((((int)threadIdx.x) < 49) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1400) / 81) * 49)) + (((((int)threadIdx.x) + 23) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1456)] = (((((9 <= ((((int)threadIdx.x) + 79) % 81)) && (((((int)threadIdx.x) + 79) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1456) / 81) * 49)) + ((((((int)threadIdx.x) + 79) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1512)] = (((((1 <= (((((int)threadIdx.x) / 9) + 6) % 9)) && (((((int)threadIdx.x) + 54) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1512) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 6) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((9 <= ((((int)threadIdx.x) + 29) % 81)) && (((((int)threadIdx.x) + 29) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 81) * 49)) + ((((((int)threadIdx.x) + 29) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1624)] = ((((5 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1624) / 81) * 49)) + (((((int)threadIdx.x) + 4) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1680)] = (((((9 <= ((((int)threadIdx.x) + 60) % 81)) && (((((int)threadIdx.x) + 60) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1680) / 81) * 49)) + ((((((int)threadIdx.x) + 60) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1736)] = (((((9 <= ((((int)threadIdx.x) + 35) % 81)) && (((((int)threadIdx.x) + 35) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1736) / 81) * 49)) + ((((((int)threadIdx.x) + 35) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1792) / 81) * 49)) + (((((int)threadIdx.x) + 10) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1848)] = (((((9 <= ((((int)threadIdx.x) + 66) % 81)) && (((((int)threadIdx.x) + 66) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1848) / 81) * 49)) + ((((((int)threadIdx.x) + 66) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1904)] = (((((9 <= ((((int)threadIdx.x) + 41) % 81)) && (((((int)threadIdx.x) + 41) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1904) / 81) * 49)) + ((((((int)threadIdx.x) + 41) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((1 <= ((((int)threadIdx.x) + 7) % 9)) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 81) * 49)) + (((((int)threadIdx.x) + 16) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2016)] = (((((1 <= (((((int)threadIdx.x) / 9) + 8) % 9)) && (((((int)threadIdx.x) + 72) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2016) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 8) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2072)] = (((((9 <= ((((int)threadIdx.x) + 47) % 81)) && (((((int)threadIdx.x) + 47) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2072) / 81) * 49)) + ((((((int)threadIdx.x) + 47) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2128)] = ((((((int)threadIdx.x) < 50) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2128) / 81) * 49)) + (((((int)threadIdx.x) + 22) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2184)] = (((((9 <= ((((int)threadIdx.x) + 78) % 81)) && (((((int)threadIdx.x) + 78) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2184) / 81) * 49)) + ((((((int)threadIdx.x) + 78) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2240)] = (((((9 <= ((((int)threadIdx.x) + 53) % 81)) && (((((int)threadIdx.x) + 53) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2240) / 81) * 49)) + ((((((int)threadIdx.x) + 53) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2296)] = (((((9 <= ((((int)threadIdx.x) + 28) % 81)) && (((((int)threadIdx.x) + 28) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2296) / 81) * 49)) + ((((((int)threadIdx.x) + 28) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = ((((6 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2352) / 81) * 49)) + (((((int)threadIdx.x) + 3) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2408)] = (((((9 <= ((((int)threadIdx.x) + 59) % 81)) && (((((int)threadIdx.x) + 59) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2408) / 81) * 49)) + ((((((int)threadIdx.x) + 59) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2464)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2464) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2520)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2520) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 1)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 16) {
+ pad_temp_shared[(((int)threadIdx.x) + 2576)] = ((((((int)threadIdx.x) < 7) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2576) / 81) * 49)) + (((((int)threadIdx.x) + 65) / 9) * 7)) + ((int)threadIdx.x)) - 6)] : 0.000000e+00f);
}
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 36864) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 49) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 98) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 147)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 147) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 3)];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 196) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 52) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 245)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 245) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 101) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 294)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 294) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 6)];
- kernel_shared[(((int)threadIdx.x) + 343)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 343) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 55) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 441)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 441) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 9)];
- kernel_shared[(((int)threadIdx.x) + 490)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 490) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 58) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 539)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 539) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 107) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 588)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 588) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 12)];
- kernel_shared[(((int)threadIdx.x) + 637)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 637) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 61) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 686)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 686) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 110) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 735)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 735) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 15)];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 833)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 833) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 113) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 882)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 882) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 18)];
- kernel_shared[(((int)threadIdx.x) + 931)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 931) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 67) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 980)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 980) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 116) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1029)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1029) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 21)];
- kernel_shared[(((int)threadIdx.x) + 1078)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1078) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 70) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 25) {
- kernel_shared[(((int)threadIdx.x) + 1127)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1127) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 119) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 168)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 224) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 280) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 280) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 336) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 104) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 448) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 160) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 504) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 216)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 560) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 272) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 616) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 672) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 728) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 152) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 784) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 208) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 840) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 88) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 896) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 952) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1008) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 144)];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1064) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 200) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1120) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1176) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1232) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1288) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 136) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1344) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 192)];
+ kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1400) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 248) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1456) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1512) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1568) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1624)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1624) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 184) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1680) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 80) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1736)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1736) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1792) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1848)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1848) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 120)];
+ kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1904) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 176) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1960) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 232) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 2072)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 2072) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 2128) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2184)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 2184) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 168)];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 2240) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 224) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 8) {
+ kernel_shared[(((int)threadIdx.x) + 2296)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 280) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 32256)];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(rc_outer_inner * 36)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 36) + 576)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 36) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 36) + 585)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((rc_outer_inner * 36) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((rc_outer_inner * 36) + 594)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((rc_outer_inner * 36) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((rc_outer_inner * 36) + 603)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 36) + 144)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 36) + 720)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 36) + 153)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 36) + 729)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((rc_outer_inner * 36) + 162)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((rc_outer_inner * 36) + 738)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((rc_outer_inner * 36) + 171)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((rc_outer_inner * 36) + 747)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 36) + 288)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 36) + 864)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 36) + 297)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 36) + 873)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((rc_outer_inner * 36) + 306)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((rc_outer_inner * 36) + 882)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((rc_outer_inner * 36) + 315)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((rc_outer_inner * 36) + 891)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 36) + 432)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 36) + 1008)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 36) + 441)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 36) + 1017)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((rc_outer_inner * 36) + 450)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((rc_outer_inner * 36) + 1026)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((rc_outer_inner * 36) + 459)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((rc_outer_inner * 36) + 1035)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 36) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 36) + 577)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 36) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 36) + 586)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((rc_outer_inner * 36) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((rc_outer_inner * 36) + 595)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((rc_outer_inner * 36) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((rc_outer_inner * 36) + 604)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 36) + 145)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 36) + 721)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 36) + 154)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 36) + 730)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((rc_outer_inner * 36) + 163)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((rc_outer_inner * 36) + 739)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((rc_outer_inner * 36) + 172)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((rc_outer_inner * 36) + 748)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 36) + 289)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 36) + 865)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 36) + 298)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 36) + 874)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((rc_outer_inner * 36) + 307)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((rc_outer_inner * 36) + 883)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((rc_outer_inner * 36) + 316)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((rc_outer_inner * 36) + 892)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 36) + 433)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 36) + 1009)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 36) + 442)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 36) + 1018)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((rc_outer_inner * 36) + 451)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((rc_outer_inner * 36) + 1027)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((rc_outer_inner * 36) + 460)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((rc_outer_inner * 36) + 1036)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 36) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 36) + 578)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 36) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 36) + 587)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((rc_outer_inner * 36) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((rc_outer_inner * 36) + 596)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((rc_outer_inner * 36) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((rc_outer_inner * 36) + 605)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 36) + 146)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 36) + 722)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 36) + 155)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 36) + 731)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((rc_outer_inner * 36) + 164)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((rc_outer_inner * 36) + 740)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((rc_outer_inner * 36) + 173)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((rc_outer_inner * 36) + 749)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 36) + 290)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 36) + 866)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 36) + 299)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 36) + 875)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((rc_outer_inner * 36) + 308)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((rc_outer_inner * 36) + 884)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((rc_outer_inner * 36) + 317)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((rc_outer_inner * 36) + 893)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 36) + 434)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 36) + 1010)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 36) + 443)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 36) + 1019)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((rc_outer_inner * 36) + 452)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((rc_outer_inner * 36) + 1028)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((rc_outer_inner * 36) + 461)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((rc_outer_inner * 36) + 1037)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 36) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 36) + 579)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 36) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 36) + 588)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((rc_outer_inner * 36) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((rc_outer_inner * 36) + 597)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 36) + 30)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 36) + 606)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 36) + 147)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 36) + 723)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 36) + 156)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 36) + 732)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((rc_outer_inner * 36) + 165)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((rc_outer_inner * 36) + 741)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 36) + 174)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 36) + 750)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 36) + 291)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 36) + 867)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 36) + 300)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 36) + 876)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((rc_outer_inner * 36) + 309)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((rc_outer_inner * 36) + 885)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 36) + 318)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 36) + 894)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 36) + 435)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 36) + 1011)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 36) + 444)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 36) + 1020)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((rc_outer_inner * 36) + 453)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((rc_outer_inner * 36) + 1029)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 36) + 462)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 36) + 1038)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 36) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 36) + 580)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 36) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 36) + 589)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((rc_outer_inner * 36) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((rc_outer_inner * 36) + 598)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 36) + 31)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 36) + 607)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 36) + 148)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 36) + 724)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 36) + 157)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 36) + 733)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((rc_outer_inner * 36) + 166)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((rc_outer_inner * 36) + 742)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 36) + 175)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 36) + 751)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 36) + 292)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 36) + 868)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 36) + 301)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 36) + 877)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((rc_outer_inner * 36) + 310)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((rc_outer_inner * 36) + 886)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 36) + 319)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 36) + 895)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 36) + 436)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 36) + 1012)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 36) + 445)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 36) + 1021)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((rc_outer_inner * 36) + 454)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((rc_outer_inner * 36) + 1030)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 36) + 463)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 36) + 1039)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 36) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 36) + 581)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 36) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 36) + 590)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((rc_outer_inner * 36) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((rc_outer_inner * 36) + 599)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 36) + 32)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 36) + 608)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 36) + 149)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 36) + 725)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 36) + 158)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 36) + 734)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((rc_outer_inner * 36) + 167)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((rc_outer_inner * 36) + 743)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 36) + 176)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 36) + 752)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 36) + 293)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 36) + 869)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 36) + 302)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 36) + 878)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((rc_outer_inner * 36) + 311)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((rc_outer_inner * 36) + 887)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 36) + 320)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 36) + 896)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 36) + 437)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 36) + 1013)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 36) + 446)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 36) + 1022)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((rc_outer_inner * 36) + 455)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((rc_outer_inner * 36) + 1031)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 36) + 464)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 36) + 1040)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 36) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 36) + 582)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 36) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 36) + 591)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((rc_outer_inner * 36) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((rc_outer_inner * 36) + 600)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((rc_outer_inner * 36) + 33)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((rc_outer_inner * 36) + 609)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 36) + 150)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 36) + 726)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 36) + 159)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 36) + 735)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((rc_outer_inner * 36) + 168)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((rc_outer_inner * 36) + 744)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((rc_outer_inner * 36) + 177)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((rc_outer_inner * 36) + 753)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 36) + 294)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 36) + 870)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 36) + 303)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 36) + 879)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((rc_outer_inner * 36) + 312)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((rc_outer_inner * 36) + 888)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((rc_outer_inner * 36) + 321)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((rc_outer_inner * 36) + 897)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 36) + 438)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 36) + 1014)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 36) + 447)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 36) + 1023)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((rc_outer_inner * 36) + 456)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((rc_outer_inner * 36) + 1032)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((rc_outer_inner * 36) + 465)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((rc_outer_inner * 36) + 1041)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 36) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 36) + 583)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 36) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 36) + 592)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((rc_outer_inner * 36) + 25)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((rc_outer_inner * 36) + 601)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((rc_outer_inner * 36) + 34)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((rc_outer_inner * 36) + 610)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 36) + 151)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 36) + 727)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 36) + 160)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 36) + 736)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((rc_outer_inner * 36) + 169)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((rc_outer_inner * 36) + 745)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((rc_outer_inner * 36) + 178)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((rc_outer_inner * 36) + 754)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 36) + 295)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 36) + 871)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 36) + 304)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 36) + 880)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((rc_outer_inner * 36) + 313)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((rc_outer_inner * 36) + 889)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((rc_outer_inner * 36) + 322)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((rc_outer_inner * 36) + 898)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 36) + 439)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 36) + 1015)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 36) + 448)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 36) + 1024)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((rc_outer_inner * 36) + 457)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((rc_outer_inner * 36) + 1033)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((rc_outer_inner * 36) + 466)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((rc_outer_inner * 36) + 1042)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 36) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 36) + 584)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 36) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 36) + 593)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((rc_outer_inner * 36) + 26)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((rc_outer_inner * 36) + 602)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((rc_outer_inner * 36) + 35)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((rc_outer_inner * 36) + 611)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 36) + 152)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 36) + 728)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 36) + 161)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 36) + 737)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((rc_outer_inner * 36) + 170)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((rc_outer_inner * 36) + 746)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((rc_outer_inner * 36) + 179)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((rc_outer_inner * 36) + 755)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 36) + 296)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 36) + 872)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 36) + 305)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 36) + 881)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((rc_outer_inner * 36) + 314)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((rc_outer_inner * 36) + 890)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((rc_outer_inner * 36) + 323)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((rc_outer_inner * 36) + 899)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 36) + 440)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 36) + 1016)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 36) + 449)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 36) + 1025)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((rc_outer_inner * 36) + 458)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((rc_outer_inner * 36) + 1034)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((rc_outer_inner * 36) + 467)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((rc_outer_inner * 36) + 1043)]));
+ for (int rc_inner = 0; rc_inner < 32; ++rc_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_inner * 81) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
}
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[(((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 8) + i1_inner)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x)) + 196)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 8) + i1_inner) + 4)]), 0.000000e+00f);
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
}
}
@@ -1262,7 +919,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 36.072 seconds)
+ **Total running time of the script:** ( 3 minutes 25.858 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 3791966e0..667c5df01 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.8313 9.8337 9.8863 9.7740 0.0459
+ 9.8596 9.8597 9.8747 9.8443 0.0124
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 2b3c0bddb..2972cb11a 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -666,7 +666,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 773.9615 774.3938 776.3110 771.1796 2.1171
+ 754.3905 753.7758 757.3666 752.0289 2.2220
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 27.927 seconds)
+ **Total running time of the script:** ( 1 minutes 24.657 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 dc3ac98bb..6cc13aaa2 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -397,102 +397,28 @@ 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_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer: int32, 0, 16) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global;
- for (i1.outer: int32, 0, 32) {
- for (i.inner.init: int32, 0, 8) {
- let cse_var_1: int32 = (i.inner.init*16)
- {
- compute_5: Buffer(compute_4, float32, [128], [])[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, (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])) {
- for (i.inner: int32, 0, 8) {
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- let cse_var_2: int32 = (i.inner*16)
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_3: int32 = ((i.inner*16) + 1)
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_4: int32 = ((i.inner*16) + 2)
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_5: int32 = ((i.inner*16) + 3)
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_6: int32 = ((i.inner*16) + 4)
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_7: int32 = ((i.inner*16) + 5)
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_8: int32 = ((i.inner*16) + 6)
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_9: int32 = ((i.inner*16) + 7)
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 32) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [1024], [])[(((i.inner.init*32) + (nb_j.inner*16)) + j.init)] = 0f32
}
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- let cse_var_10: int32 = ((i.inner*16) + 8)
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_11: int32 = ((i.inner*16) + 9)
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_12: int32 = ((i.inner*16) + 10)
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_13: int32 = ((i.inner*16) + 11)
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_14: int32 = ((i.inner*16) + 12)
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_15: int32 = ((i.inner*16) + 13)
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_16: int32 = ((i.inner*16) + 14)
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_17: int32 = ((i.inner*16) + 15)
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 32) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_2: int32 = (((i.inner*32) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
}
}
}
- for (i0.inner: int32, 0, 8) {
- let cse_var_18: int32 = (((i0.outer*4096) + (i0.inner*512)) + (i1.outer*16))
- compute[ramp(cse_var_18, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_18, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 32) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ compute[ramp(cse_var_4, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -548,7 +474,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.840 ms
+ Execution time of this operator: 1.655 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 0a6bb33bc..c657440c7 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:47.017** total execution time for **how_to_tune_with_autotvm** files:
+**00:45.693** 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``) | 00:46.981 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:45.656 | 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_cuda.py` (``tune_relay_cuda.py``) | 00:00.006 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 2f83eff12..7630995f9 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
@@ -1156,8 +1156,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
- No: 9 GFLOPS: 214.47/214.47 result: MeasureResult(costs=(0.0010794016068965517,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.261305332183838, timestamp=1662538808.5707426) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
- No: 10 GFLOPS: 0.00/214.47 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 80.86/80.86 result: MeasureResult(costs=(0.0028629368857142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9043185710906982, timestamp=1662538783.2651484) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+ No: 10 GFLOPS: 0.00/80.86 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
@@ -1280,8 +1280,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
- No: 11 GFLOPS: 260.97/260.97 result: MeasureResult(costs=(0.0008870867790055248,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8471014499664307, timestamp=1662538809.500747) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
- No: 12 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 259.11/259.11 result: MeasureResult(costs=(0.0008934569642857143,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6702837944030762, timestamp=1662538784.0759976) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+ No: 12 GFLOPS: 0.00/259.11 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
@@ -1404,7 +1404,7 @@ for this template
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, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
- No: 13 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/259.11 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
@@ -1527,7 +1527,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
- No: 14 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/259.11 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
@@ -1650,9 +1650,9 @@ for this template
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, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
- No: 15 GFLOPS: 5.33/260.97 result: MeasureResult(costs=(0.04344341825,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9088964462280273, timestamp=1662538814.2537436) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
- No: 16 GFLOPS: 3.34/260.97 result: MeasureResult(costs=(0.06939141925,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.742975473403931, timestamp=1662538815.5034032) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
- No: 17 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 5.47/259.11 result: MeasureResult(costs=(0.04230818525,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8662571907043457, timestamp=1662538788.7046597) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+ No: 16 GFLOPS: 3.34/259.11 result: MeasureResult(costs=(0.0693959645,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.610472679138184, timestamp=1662538789.9481373) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+ No: 17 GFLOPS: 0.00/259.11 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
@@ -1670,8 +1670,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
- No: 18 GFLOPS: 27.14/260.97 result: MeasureResult(costs=(0.008530872562500002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3425092697143555, timestamp=1662538826.5791588) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
- No: 19 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 27.90/259.11 result: MeasureResult(costs=(0.00829776292857143,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3258106708526611, timestamp=1662538801.0125623) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+ No: 19 GFLOPS: 0.00/259.11 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
@@ -1794,7 +1794,7 @@ for this template
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, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
- No: 20 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+ No: 20 GFLOPS: 0.00/259.11 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
@@ -1973,7 +1973,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
- Time cost of this operator: 0.001253
+ Time cost of this operator: 0.001264
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 596071ad2..60ffbd336 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
@@ -329,10 +329,10 @@ 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 313.7 98.707 (1, 2, 10, 10, 3) 2 1 [313.7]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.117 0.981 (1, 6, 10, 10) 1 1 [3.117]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.992 0.312 (1, 1, 10, 10, 3) 1 1 [0.992]
- Total_time - 317.809 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.0 98.726 (1, 2, 10, 10, 3) 2 1 [309.0]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.018 0.964 (1, 6, 10, 10) 1 1 [3.018]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.309 (1, 1, 10, 10, 3) 1 1 [0.969]
+ Total_time - 312.986 - - - - -
@@ -398,10 +398,10 @@ 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 216.6 98.597 (1, 1, 10, 10, 6) 2 1 [216.6]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.198 1.001 (1, 6, 10, 10) 1 1 [2.198]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.883 0.402 (1, 3, 10, 10, 1) 1 1 [0.883]
- Total_time - 219.681 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 220.5 98.62 (1, 1, 10, 10, 6) 2 1 [220.5]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.24 1.002 (1, 6, 10, 10) 1 1 [2.24]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.845 0.378 (1, 3, 10, 10, 1) 1 1 [0.845]
+ Total_time - 223.585 - - - - -
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 17353ada6..a7461195e 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/tmpqxrrffw5/images/random'
+ '/tmp/tmp77owt4nb/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpqxrrffw5/images/target contains 8144 images
- /tmp/tmpqxrrffw5/images/random contains 5000 images
+ /tmp/tmp77owt4nb/images/target contains 8144 images
+ /tmp/tmp77owt4nb/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 57s - loss: 0.2220 - accuracy: 0.9241 - val_loss: 0.1741 - val_accuracy: 0.9517
+ 328/328 - 57s - loss: 0.2266 - accuracy: 0.9204 - val_loss: 0.1380 - val_accuracy: 0.9532
Epoch 2/3
- 328/328 - 58s - loss: 0.0987 - accuracy: 0.9621 - val_loss: 0.1086 - val_accuracy: 0.9664
+ 328/328 - 53s - loss: 0.0999 - accuracy: 0.9626 - val_loss: 0.1135 - val_accuracy: 0.9645
Epoch 3/3
- 328/328 - 61s - loss: 0.0683 - accuracy: 0.9748 - val_loss: 0.1066 - val_accuracy: 0.9675
+ 328/328 - 53s - loss: 0.0648 - accuracy: 0.9760 - val_loss: 0.1153 - val_accuracy: 0.9619
- <keras.callbacks.History object at 0x7fc571c977d0>
+ <keras.callbacks.History object at 0x7f3c71a73e10>
@@ -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 52.566 seconds)
+ **Total running time of the script:** ( 5 minutes 7.448 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 c89eeb8f1..c79492163 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
=================
-**05:51.379** total execution time for **how_to_work_with_microtvm** files:
+**06:02.454** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:52.566 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:07.448 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:46.390 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:43.777 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.816 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.810 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.605 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.417 | 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 fe28c26a6..f00008dd5 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
=================
-**00:48.320** total execution time for **how_to_work_with_relay** files:
+**00:44.205** 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``) | 00:36.579 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.466 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.171 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.217 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.563 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.515 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.008 | 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 c374396cf..05524364f 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 0x7fc4f6412680>
+ <function my_cuda_math_rule at 0x7f3bd6615560>
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 40a54ef52..eaf0e0cc2 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
=================
-**00:04.366** total execution time for **how_to_work_with_schedules** files:
+**00:04.253** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:02.019 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.967 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.024 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.999 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.569 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.555 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.550 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.540 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.108 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.104 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.049 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.044 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.031 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.028 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.017 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.016 | 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 d901ba5fb..41e892c7a 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/tmpdxsk3kes/input0.cc'\nsource_filename = \"/tmp/tmpdxsk3kes/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/tmpsvrfghet/input0.cc'\nsource_filename = \"/tmp/tmpsvrfghet/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 bec2e92a7..fd2a969b3 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
=================
-**00:23.251** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:23.010** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:23.244 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:23.003 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index f204d143e..0e3b55675 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ 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 26.12s!
+ resnet18_v1 inference graph built in 25.05s!
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
index e95c9b46b..c99a1f700 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/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 17.52s!
+ yolov3-tiny inference graph built in 17.37s!
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 4d7ac31f2..736a1714b 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
=================
-**01:35.359** total execution time for **topic_vta_tutorials_frontend** files:
+**01:35.870** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.156 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:50.386 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:46.203 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:45.484 | 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 72f8be749..3ddb96ceb 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
=================
-**00:03.304** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.278** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.893 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.861 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.410 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.417 | 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 b15dc2447..9634a32e7 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
=================
-**00:00.765** total execution time for **topic_vta_tutorials** files:
+**00:00.750** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.412 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.404 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.352 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.345 | 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 c364bacbe..fe5fddcb3 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -326,7 +326,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 95.308 ms
+ Execution time of this operator: 94.049 ms
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index c2f6213d7..c08db58aa 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 9.37/9.37 result: MeasureResult(costs=(0.028644973599999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6037588119506836, timestamp=1662537521.942411) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.51/9.37 result: MeasureResult(costs=(0.10708118039999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8712053298950195, timestamp=1662537523.8243418) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 10.89/10.89 result: MeasureResult(costs=(0.0246387222,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5891413688659668, timestamp=1662537524.991608) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.69/10.89 result: MeasureResult(costs=(0.1584580492,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6713852882385254, timestamp=1662537528.2955613) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.55/10.89 result: MeasureResult(costs=(0.0757060276,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3639497756958008, timestamp=1662537529.7837975) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.84/10.89 result: MeasureResult(costs=(0.1461511332,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4779767990112305, timestamp=1662537532.8961031) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.87/10.89 result: MeasureResult(costs=(0.3088538152,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.078850746154785, timestamp=1662537538.0101764) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.14/10.89 result: MeasureResult(costs=(0.0264776046,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.578754186630249, timestamp=1662537538.604207) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.66/10.89 result: MeasureResult(costs=(0.1619709292,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6991984844207764, timestamp=1662537541.4238858) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.77/10.89 result: MeasureResult(costs=(0.0968786178,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.665210247039795, timestamp=1662537543.1423182) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 9.12/9.12 result: MeasureResult(costs=(0.029440913000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6066429615020752, timestamp=1662537520.205738) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.59/9.12 result: MeasureResult(costs=(0.10350975679999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.791125774383545, timestamp=1662537522.5778143) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.64/11.64 result: MeasureResult(costs=(0.0230526156,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5854988098144531, timestamp=1662537523.1529157) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.64/11.64 result: MeasureResult(costs=(0.1636105772,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7520909309387207, timestamp=1662537526.5029535) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.55/11.64 result: MeasureResult(costs=(0.0756971984,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3548974990844727, timestamp=1662537527.9882061) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.69/11.64 result: MeasureResult(costs=(0.159028207,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7103192806243896, timestamp=1662537530.7405684) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.87/11.64 result: MeasureResult(costs=(0.30897949739999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.073216676712036, timestamp=1662537536.4244936) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 9.88/11.64 result: MeasureResult(costs=(0.0271777442,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5799770355224609, timestamp=1662537537.0253024) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.89/11.64 result: MeasureResult(costs=(0.1420222946,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.37844181060791, timestamp=1662537539.5241234) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.49/11.64 result: MeasureResult(costs=(0.10785104279999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.834287405014038, timestamp=1662537541.4143353) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index cd83dc50c..c571cbd55 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -327,7 +327,7 @@ standard deviation.
.. code-block:: none
- {'mean': 504.8379361799995, 'median': 504.92999955000073, 'std': 0.4890225566327642}
+ {'mean': 501.0427243799995, 'median': 500.7832751500018, 'std': 1.0385531205208194}
@@ -563,30 +563,30 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.15/ 17.15 GFLOPS | Progress: (4/20) | 6.91 s
[Task 1/25] Current/Best: 6.12/ 17.15 GFLOPS | Progress: (8/20) | 10.08 s
[Task 1/25] Current/Best: 11.44/ 22.19 GFLOPS | Progress: (12/20) | 12.67 s
[Task 1/25] Current/Best: 16.30/ 22.55 GFLOPS | Progress: (16/20) | 14.41 s
[Task 1/25] Current/Best: 11.49/ 23.60 GFLOPS | Progress: (20/20) | 16.20 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 11.75/ 13.20 GFLOPS | Progress: (4/20) | 4.17 s
[Task 2/25] Current/Best: 13.80/ 18.00 GFLOPS | Progress: (8/20) | 5.52 s
[Task 2/25] Current/Best: 20.01/ 20.01 GFLOPS | Progress: (12/20) | 6.89 s
[Task 2/25] Current/Best: 12.63/ 20.01 GFLOPS | Progress: (16/20) | 8.21 s
[Task 2/25] Current/Best: 19.58/ 20.01 GFLOPS | Progress: (20/20) | 9.89 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.62/ 10.76 GFLOPS | Progress: (4/20) | 6.07 s
[Task 3/25] Current/Best: 15.13/ 16.67 GFLOPS | Progress: (8/20) | 8.08 s
[Task 3/25] Current/Best: 14.74/ 16.67 GFLOPS | Progress: (12/20) | 9.85 s
[Task 3/25] Current/Best: 7.16/ 23.49 GFLOPS | Progress: (16/20) | 11.82 s
[Task 3/25] Current/Best: 12.45/ 23.49 GFLOPS | Progress: (20/20) | 16.52 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.37/ 19.82 GFLOPS | Progress: (4/20) | 2.60 s
[Task 4/25] Current/Best: 6.71/ 19.82 GFLOPS | Progress: (8/20) | 7.51 s
[Task 4/25] Current/Best: 20.69/ 20.69 GFLOPS | Progress: (12/20) | 12.65 s
[Task 4/25] Current/Best: 16.73/ 20.69 GFLOPS | Progress: (16/20) | 15.11 s
[Task 4/25] Current/Best: 12.90/ 20.69 GFLOPS | Progress: (20/20) | 17.26 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.49/ 10.02 GFLOPS | Progress: (4/20) | 2.79 s
[Task 5/25] Current/Best: 11.26/ 13.00 GFLOPS | Progress: (8/20) | 4.92 s
[Task 5/25] Current/Best: 9.54/ 17.23 GFLOPS | Progress: (12/20) | 8.12 s
[Task 5/25] Current/Best: 11.17/ 22.13 GFLOPS | Progress: (16/20) | 9.59 s
[Task 5/25] Current/Best: 10.76/ 22.13 GFLOPS | Progress: (20/20) | 11.63 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.02/ 19.83 GFLOPS | Progress: (4/20) | 4.35 s
[Task 6/25] Current/Best: 18.20/ 19.83 GFLOPS | Progress: (8/20) | 6.25 s
[Task 6/25] Current/Best: 12.28/ 19.83 GFLOPS | Progress: (12/20) | 8.26 s
[Task 6/25] Current/Best: 19.50/ 19.83 GFLOPS | Progress: (16/20) | 10.61 s
[Task 6/25] Current/Best: 3.70/ 19.83 GFLOPS | Progress: (20/20) | 13.21 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 10.76/ 12.21 GFLOPS | Progress: (4/20) | 3.81 s
[Task 7/25] Current/Best: 19.25/ 20.73 GFLOPS | Progress: (8/20) | 5.39 s
[Task 7/25] Current/Best: 15.19/ 20.73 GFLOPS | Progress: (12/20) | 7.42 s
[Task 7/25] Current/Best: 12.12/ 20.73 GFLOPS | Progress: (16/20) | 9.52 s
[Task 7/25] Current/Best: 6.34/ 21.16 GFLOPS | Progress: (20/20) | 12.05 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.22/ 14.06 GFLOPS | Progress: (4/20) | 3.13 s
[Task 8/25] Current/Best: 9.76/ 14.06 GFLOPS | Progress: (8/20) | 8.39 s
[Task 8/25] Current/Best: 13.71/ 14.06 GFLOPS | Progress: (12/20) | 15.19 s
[Task 8/25] Current/Best: 18.95/ 18.95 GFLOPS | Progress: (16/20) | 17.31 s
[Task 8/25] Current/Best: 19.81/ 19.81 GFLOPS | Progress: (20/20) | 24.53 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.07/ 15.61 GFLOPS | Progress: (4/20) | 12.13 s
[Task 9/25] Current/Best: 22.22/ 22.22 GFLOPS | Progress: (8/20) | 14.03 s
[Task 9/25] Current/Best: 8.16/ 22.22 GFLOPS | Progress: (12/20) | 16.67 s
[Task 9/25] Current/Best: 17.58/ 22.22 GFLOPS | Progress: (16/20) | 19.65 s
[Task 9/25] Current/Best: 8.80/ 22.22 GFLOPS | Progress: (20/20) | 28.57 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.20/ 18.20 GFLOPS | Progress: (4/20) | 2.74 s
[Task 10/25] Current/Best: 15.44/ 18.20 GFLOPS | Progress: (8/20) | 4.45 s
[Task 10/25] Current/Best: 12.91/ 19.02 GFLOPS | Progress: (12/20) | 6.06 s
[Task 10/25] Current/Best: 18.87/ 20.32 GFLOPS | Progress: (16/20) | 7.21 s
[Task 10/25] Current/Best: 8.92/ 20.32 GFLOPS | Progress: (20/20
) | 8.79 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 11.47/ 18.01 GFLOPS | Progress: (4/20) | 3.62 s
[Task 11/25] Current/Best: 16.84/ 18.01 GFLOPS | Progress: (8/20) | 6.50 s
[Task 11/25] Current/Best: 15.82/ 18.01 GFLOPS | Progress: (12/20) | 8.64 s
[Task 11/25] Current/Best: 11.94/ 20.74 GFLOPS | Progress: (16/20) | 11.62 s
[Task 11/25] Current/Best: 19.33/ 21.32 GFLOPS | Progress: (20/20) | 13.78 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.76/ 18.00 GFLOPS | Progress: (4/20) | 5.95 s
[Task 12/25] Current/Best: 5.26/ 18.00 GFLOPS | Progress: (8/20) | 10.01 s
[Task 12/25] Current/Best: 17.72/ 18.82 GFLOPS | Progress: (12/20) | 12.05 s
[Task 12/25] Current/Best: 12.74/ 18.82 GFLOPS | Progress: (16/20) | 15.11 s
[Task 12/25] Current/Best: 14.95/ 18.82 GFLOPS | Progress: (20/20) | 17.05 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.81/ 17.18 GFLOPS | Progress: (4/20) | 3.99 s
[Task 13/25] Current/Best: 15.25/ 20.45 GFLOPS | Progress: (8/20) | 6.66 s
[Task 13/25] Current/Best: 19.22/ 21.08 GFLOPS | Progress: (12/20) | 9.85 s
[Task 13/25] Current/Best: 12.16/ 21.08 GFLOPS | Progress: (16/20) | 13.46 s
[Task 13/25] Current/Best: 18.29/ 21.08 GFLOPS | Progress: (20/20) | 15.81 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 12.36/ 12.99 GFLOPS | Progress: (4/20) | 3.59 s
[Task 14/25] Current/Best: 6.05/ 13.13 GFLOPS | Progress: (8/20) | 5.81 s
[Task 14/25] Current/Best: 20.47/ 20.47 GFLOPS | Progress: (12/20) | 8.55 s
[Task 14/25] Current/Best: 16.95/ 20.47 GFLOPS | Progress: (16/20) | 10.29 s Done.
-
[Task 14/25] Current/Best: 16.93/ 20.47 GFLOPS | Progress: (20/20) | 12.12 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 15.96/ 17.41 GFLOPS | Progress: (4/20) | 3.00 s
[Task 15/25] Current/Best: 14.06/ 17.69 GFLOPS | Progress: (8/20) | 4.35 s
[Task 15/25] Current/Best: 10.30/ 21.79 GFLOPS | Progress: (12/20) | 6.64 s
[Task 15/25] Current/Best: 20.05/ 21.79 GFLOPS | Progress: (16/20) | 10.57 s
[Task 15/25] Current/Best: 9.61/ 21.79 GFLOPS | Progress: (20/20) | 11.63 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 19.89/ 19.89 GFLOPS | Progress: (4/20) | 3.21 s
[Task 16/25] Current/Best: 3.02/ 19.89 GFLOPS | Progress: (8/20) | 4.86 s
[Task 16/25] Current/Best: 19.42/ 19.89 GFLOPS | Progress: (12/20) | 6.12 s
[Task 16/25] Current/Best: 18.05/ 19.89 GFLOPS | Progress: (16/20)
| 7.55 s
[Task 16/25] Current/Best: 9.85/ 21.48 GFLOPS | Progress: (20/20) | 9.81 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 14.09/ 18.08 GFLOPS | Progress: (4/20) | 5.05 s
[Task 17/25] Current/Best: 14.27/ 22.85 GFLOPS | Progress: (8/20) | 8.10 s
[Task 17/25] Current/Best: 16.57/ 22.85 GFLOPS | Progress: (12/20) | 10.23 s
[Task 17/25] Current/Best: 16.31/ 22.85 GFLOPS | Progress: (16/20) | 12.50 s
[Task 17/25] Current/Best: 9.98/ 22.85 GFLOPS | Progress: (20/20) | 14.76 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.48/ 16.58 GFLOPS | Progress: (4/20) | 4.06 s
[Task 18/25] Current/Best: 10.53/ 17.23 GFLOPS | Progress: (8/20) | 7.92 s
[Task 18/25] Current/Best: 18.96/ 18.96 GFLOPS | Progress: (12/20) | 9.91 s
[Task 18/25] Current/Best: 9.71/ 18.96 GFLOPS | Progress: (16/20) | 13.89 s
[Task 18/25] Current/Best: 20.41/ 20.41 GFLOPS | Progress: (20/20) | 15.46 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 4.93/ 20.04 GFLOPS | Progress: (4/20) | 6.85 s
[Task 19/25] Current/Best: 2.68/ 20.04 GFLOPS | Progress: (8/20) | 10.24 s
[Task 19/25] Current/Best: 18.93/ 20.27 GFLOPS | Progress: (12/20) | 13.28 s
[Task 19/25] Current/Best: 14.42/ 21.34 GFLOPS | Progress: (16/20) | 16.36 s
[Task 19/25] Current/Best: 2.68/ 22.20 GFLOPS | Progress: (20/20) | 19.23 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.06/ 14.89 GFLOPS | Progress: (4/20) | 3.59 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.39/ 17.39 GFLOPS | Progress: (4/20) | 6.62 s
[Task 1/25] Current/Best: 6.16/ 17.39 GFLOPS | Progress: (8/20) | 9.60 s
[Task 1/25] Current/Best: 11.46/ 22.50 GFLOPS | Progress: (12/20) | 12.10 s
[Task 1/25] Current/Best: 16.41/ 22.74 GFLOPS | Progress: (16/20) | 13.81 s
[Task 1/25] Current/Best: 11.42/ 23.77 GFLOPS | Progress: (20/20) | 15.58 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.25/ 13.17 GFLOPS | Progress: (4/20) | 3.90 s
[Task 2/25] Current/Best: 13.96/ 18.56 GFLOPS | Progress: (8/20) | 5.22 s
[Task 2/25] Current/Best: 20.93/ 20.93 GFLOPS | Progress: (12/20) | 6.55 s
[Task 2/25] Current/Best: 12.44/ 20.93 GFLOPS | Progress: (16/20) | 7.81 s
[Task 2/25] Current/Best: 19.81/ 20.93 GFLOPS | Progress: (20/20) | 9.44 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.62/ 10.82 GFLOPS | Progress: (4/20) | 5.94 s
[Task 3/25] Current/Best: 15.29/ 16.77 GFLOPS | Progress: (8/20) | 7.90 s
[Task 3/25] Current/Best: 14.78/ 16.77 GFLOPS | Progress: (12/20) | 9.65 s
[Task 3/25] Current/Best: 7.21/ 23.73 GFLOPS | Progress: (16/20) | 11.57 s
[Task 3/25] Current/Best: 12.34/ 23.73 GFLOPS | Progress: (20/20) | 16.13 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.53/ 20.44 GFLOPS | Progress: (4/20) | 2.48 s
[Task 4/25] Current/Best: 6.80/ 20.44 GFLOPS | Progress: (8/20) | 6.93 s
[Task 4/25] Current/Best: 21.78/ 21.78 GFLOPS | Progress: (12/20) | 11.56 s
[Task 4/25] Current/Best: 17.26/ 21.78 GFLOPS | Progress: (16/20) | 13.83 s
[Task 4/25] Current/Best: 13.24/ 21.78 GFLOPS | Progress: (20/20) | 15.83 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.56/ 9.93 GFLOPS | Progress: (4/20) | 2.71 s
[Task 5/25] Current/Best: 11.77/ 13.06 GFLOPS | Progress: (8/20) | 4.81 s
[Task 5/25] Current/Best: 9.73/ 17.92 GFLOPS | Progress: (12/20) | 7.97 s
[Task 5/25] Current/Best: 11.81/ 22.46 GFLOPS | Progress: (16/20) | 9.45 s
[Task 5/25] Current/Best: 11.83/ 22.46 GFLOPS | Progress: (20/20) | 11.32 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.09/ 19.93 GFLOPS | Progress: (4/20) | 4.08 s
[Task 6/25] Current/Best: 18.78/ 19.93 GFLOPS | Progress: (8/20) | 5.86 s
[Task 6/25] Current/Best: 13.19/ 19.93 GFLOPS | Progress: (12/20) | 7.81 s
[Task 6/25] Current/Best: 19.80/ 19.93 GFLOPS | Progress: (16/20) | 10.08 s
[Task 6/25] Current/Best: 3.75/ 19.93 GFLOPS | Progress: (20/20) | 12.63 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 10.98/ 12.61 GFLOPS | Progress: (4/20) | 3.76 s
[Task 7/25] Current/Best: 19.79/ 21.12 GFLOPS | Progress: (8/20) | 5.31 s
[Task 7/25] Current/Best: 14.54/ 21.12 GFLOPS | Progress: (12/20) | 7.25 s
[Task 7/25] Current/Best: 12.11/ 21.12 GFLOPS | Progress: (16/20) | 9.33 s
[Task 7/25] Current/Best: 6.31/ 21.36 GFLOPS | Progress: (20/20) | 11.84 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.13/ 14.21 GFLOPS | Progress: (4/20) | 3.00 s
[Task 8/25] Current/Best: 9.70/ 14.21 GFLOPS | Progress: (8/20) | 7.86 s
[Task 8/25] Current/Best: 13.16/ 14.21 GFLOPS | Progress: (12/20) | 14.16 s
[Task 8/25] Current/Best: 19.03/ 19.03 GFLOPS | Progress: (16/20) | 16.25 s
[Task 8/25] Current/Best: 19.85/ 19.85 GFLOPS | Progress: (20/20) | 22.80 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.24/ 15.43 GFLOPS | Progress: (4/20) | 12.04 s
[Task 9/25] Current/Best: 23.28/ 23.28 GFLOPS | Progress: (8/20) | 13.93 s
[Task 9/25] Current/Best: 8.23/ 23.28 GFLOPS | Progress: (12/20) | 16.31 s
[Task 9/25] Current/Best: 17.68/ 23.28 GFLOPS | Progress: (16/20) | 18.92 s
[Task 9/25] Current/Best: 8.90/ 23.28 GFLOPS | Progress: (20/20) | 26.90 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.04/ 18.04 GFLOPS | Progress: (4/20) | 2.70 s
[Task 10/25] Current/Best: 15.66/ 18.04 GFLOPS | Progress: (8/20) | 4.31 s
[Task 10/25] Current/Best: 12.20/ 19.14 GFLOPS | Progress: (12/20) | 5.87 s
[Task 10/25] Current/Best: 19.09/ 20.48 GFLOPS | Progress: (16/20) | 7.00 s
[Task 10/25] Current/Best: 8.89/ 20.48 GFLOPS | Progress: (20/20
) | 8.57 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.22/ 18.06 GFLOPS | Progress: (4/20) | 3.45 s
[Task 11/25] Current/Best: 16.71/ 18.06 GFLOPS | Progress: (8/20) | 6.22 s
[Task 11/25] Current/Best: 17.47/ 18.06 GFLOPS | Progress: (12/20) | 8.33 s
[Task 11/25] Current/Best: 13.58/ 20.87 GFLOPS | Progress: (16/20) | 11.10 s
[Task 11/25] Current/Best: 19.06/ 21.23 GFLOPS | Progress: (20/20) | 13.18 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.75/ 18.12 GFLOPS | Progress: (4/20) | 5.55 s
[Task 12/25] Current/Best: 5.23/ 18.12 GFLOPS | Progress: (8/20) | 9.33 s
[Task 12/25] Current/Best: 19.26/ 19.26 GFLOPS | Progress: (12/20) | 11.33 s
[Task 12/25] Current/Best: 12.84/ 19.26 GFLOPS | Progress: (16/20) | 14.17 s
[Task 12/25] Current/Best: 15.22/ 19.26 GFLOPS | Progress: (20/20) | 16.10 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.83/ 17.27 GFLOPS | Progress: (4/20) | 3.80 s
[Task 13/25] Current/Best: 15.02/ 20.62 GFLOPS | Progress: (8/20) | 6.27 s
[Task 13/25] Current/Best: 19.44/ 21.05 GFLOPS | Progress: (12/20) | 9.27 s
[Task 13/25] Current/Best: 12.18/ 21.05 GFLOPS | Progress: (16/20) | 12.77 s
[Task 13/25] Current/Best: 18.41/ 21.05 GFLOPS | Progress: (20/20) | 15.04 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.84/ 13.84 GFLOPS | Progress: (4/20) | 3.35 s
[Task 14/25] Current/Best: 6.11/ 13.84 GFLOPS | Progress: (8/20) | 5.54 s
[Task 14/25] Current/Best: 20.26/ 20.26 GFLOPS | Progress: (12/20) | 8.11 s
[Task 14/25] Current/Best: 16.78/ 20.26 GFLOPS | Progress: (16/20) | 9.79 s Done.
+
[Task 14/25] Current/Best: 17.35/ 20.26 GFLOPS | Progress: (20/20) | 11.60 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.15/ 17.50 GFLOPS | Progress: (4/20) | 2.85 s
[Task 15/25] Current/Best: 14.45/ 17.78 GFLOPS | Progress: (8/20) | 4.20 s
[Task 15/25] Current/Best: 10.37/ 22.24 GFLOPS | Progress: (12/20) | 6.33 s
[Task 15/25] Current/Best: 20.27/ 22.24 GFLOPS | Progress: (16/20) | 9.39 s
[Task 15/25] Current/Best: 9.65/ 22.24 GFLOPS | Progress: (20/20) | 10.43 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.48/ 20.48 GFLOPS | Progress: (4/20) | 3.10 s
[Task 16/25] Current/Best: 3.04/ 20.48 GFLOPS | Progress: (8/20) | 4.73 s
[Task 16/25] Current/Best: 19.55/ 20.48 GFLOPS | Progress: (12/20) | 5.96 s
[Task 16/25] Current/Best: 17.98/ 20.48 GFLOPS | Progress: (16/20) |
7.34 s
[Task 16/25] Current/Best: 9.82/ 21.76 GFLOPS | Progress: (20/20) | 9.43 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 14.24/ 18.19 GFLOPS | Progress: (4/20) | 4.84 s
[Task 17/25] Current/Best: 14.35/ 22.93 GFLOPS | Progress: (8/20) | 7.74 s
[Task 17/25] Current/Best: 16.72/ 22.93 GFLOPS | Progress: (12/20) | 9.80 s
[Task 17/25] Current/Best: 16.36/ 22.93 GFLOPS | Progress: (16/20) | 11.95 s
[Task 17/25] Current/Best: 10.00/ 22.93 GFLOPS | Progress: (20/20) | 14.12 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.39/ 17.93 GFLOPS | Progress: (4/20) | 3.81 s
[Task 18/25] Current/Best: 10.59/ 19.29 GFLOPS | Progress: (8/20) | 7.34 s
[Task 18/25] Current/Best: 19.53/ 19.53 GFLOPS | Progress: (12/20) | 9.27 s
[Task 18/25] Current/Best: 9.77/ 19.53 GFLOPS | Progress: (16/20) | 12.93 s
[Task 18/25] Current/Best: 20.56/ 20.56 GFLOPS | Progress: (20/20) | 14.47 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.58/ 20.13 GFLOPS | Progress: (4/20) | 6.28 s
[Task 19/25] Current/Best: 2.69/ 20.13 GFLOPS | Progress: (8/20) | 9.54 s
[Task 19/25] Current/Best: 19.13/ 20.81 GFLOPS | Progress: (12/20) | 12.35 s
[Task 19/25] Current/Best: 15.12/ 21.24 GFLOPS | Progress: (16/20) | 15.18 s
[Task 19/25] Current/Best: 2.69/ 22.59 GFLOPS | Progress: (20/20) | 18.00 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.62/ 15.06 GFLOPS | Progress: (4/20) | 3.41 s Done.
Done.
-
[Task 20/25] Current/Best: 10.00/ 14.89 GFLOPS | Progress: (8/20) | 7.17 s
[Task 20/25] Current/Best: 2.32/ 16.32 GFLOPS | Progress: (12/20) | 11.25 s
[Task 20/25] Current/Best: 12.37/ 16.32 GFLOPS | Progress: (16/20) | 15.23 s
[Task 20/25] Current/Best: 12.94/ 21.50 GFLOPS | Progress: (20/20) | 17.40 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.36/ 17.32 GFLOPS | Progress: (4/20) | 3.52 s
[Task 21/25] Current/Best: 13.71/ 17.32 GFLOPS | Progress: (8/20) | 5.21 s
[Task 21/25] Current/Best: 1.60/ 17.32 GFLOPS | Progress: (12/20) | 7.46 s
[Task 21/25] Current/Best: 17.70/ 17.70 GFLOPS | Progress: (16/20) | 11.19 s
[Task 21/25] Current/Best: 4.44/ 17.70 GFLOPS | Progress: (20/20) | 19.06 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.69/ 16.72 GFLOPS | Progress: (4/20
) | 2.89 s
[Task 22/25] Current/Best: 9.10/ 20.45 GFLOPS | Progress: (8/20) | 4.93 s
[Task 22/25] Current/Best: 19.32/ 20.45 GFLOPS | Progress: (12/20) | 7.42 s
[Task 22/25] Current/Best: 14.97/ 20.45 GFLOPS | Progress: (16/20) | 9.60 s
[Task 22/25] Current/Best: 14.71/ 20.45 GFLOPS | Progress: (20/20) | 11.44 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.18/ 19.81 GFLOPS | Progress: (4/20) | 3.48 s
[Task 23/25] Current/Best: 15.99/ 19.81 GFLOPS | Progress: (8/20) | 7.08 s
[Task 23/25] Current/Best: 20.55/ 20.91 GFLOPS | Progress: (12/20) | 9.00 s
[Task 23/25] Current/Best: 4.84/ 20.91 GFLOPS | Progress: (16/20) | 16.74 s
[Task 23/25] Current/Best: 6.62/ 20.91 GFLOPS | Progress: (20/20) | 21.21 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.43/ 8.43 GFLOPS | Progress: (4/20) | 11.99 s
[Task 24/25] Current/Best: 1.70/ 8.43 GFLOPS | Progress: (8/20) | 23.11 s
[Task 24/25] Current/Best: 2.26/ 8.43 GFLOPS | Progress: (12/20) | 34.82 s Done.
-
[Task 24/25] Current/Best: 6.84/ 8.57 GFLOPS | Progress: (16/20) | 40.82 s
[Task 24/25] Current/Best: 2.81/ 8.68 GFLOPS | Progress: (20/20) | 47.07 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.51/ 2.55 GFLOPS | Progress: (4/20) | 11.78 s
[Task 25/25] Current/Best: 4.55/ 6.86 GFLOPS | Progress: (8/20) | 23.24 s
[Task 25/25] Current/Best: 5.48/ 6.86 GFLOPS | Progress: (12/20) | 34.84 s
[Task 25/25] Current/Best: 5.52/ 8.30 GFLOPS | Progress: (16/20) | 36.82 s
[Task 25/25] Current/Best: 2.53/ 8.30 GFLOPS | Progress: (20/20) | 47.58 s
+
[Task 20/25] Current/Best: 10.26/ 15.06 GFLOPS | Progress: (8/20) | 6.92 s
[Task 20/25] Current/Best: 2.32/ 16.31 GFLOPS | Progress: (12/20) | 10.93 s
[Task 20/25] Current/Best: 12.35/ 16.31 GFLOPS | Progress: (16/20) | 14.79 s
[Task 20/25] Current/Best: 13.25/ 21.69 GFLOPS | Progress: (20/20) | 16.91 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.38/ 17.53 GFLOPS | Progress: (4/20) | 3.35 s
[Task 21/25] Current/Best: 14.56/ 17.53 GFLOPS | Progress: (8/20) | 4.98 s
[Task 21/25] Current/Best: 1.61/ 17.53 GFLOPS | Progress: (12/20) | 7.21 s
[Task 21/25] Current/Best: 18.19/ 18.19 GFLOPS | Progress: (16/20) | 10.75 s
[Task 21/25] Current/Best: 4.45/ 18.19 GFLOPS | Progress: (20/20) | 18.00 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.96 GFLOPS | Progress: (4/20
) | 2.78 s
[Task 22/25] Current/Best: 9.05/ 21.28 GFLOPS | Progress: (8/20) | 4.77 s
[Task 22/25] Current/Best: 19.56/ 21.28 GFLOPS | Progress: (12/20) | 7.15 s
[Task 22/25] Current/Best: 15.03/ 21.28 GFLOPS | Progress: (16/20) | 9.21 s
[Task 22/25] Current/Best: 14.70/ 21.28 GFLOPS | Progress: (20/20) | 10.90 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.28/ 20.07 GFLOPS | Progress: (4/20) | 3.37 s
[Task 23/25] Current/Best: 15.19/ 20.07 GFLOPS | Progress: (8/20) | 6.76 s
[Task 23/25] Current/Best: 20.70/ 21.07 GFLOPS | Progress: (12/20) | 8.61 s
[Task 23/25] Current/Best: 5.77/ 21.07 GFLOPS | Progress: (16/20) | 15.98 s
[Task 23/25] Current/Best: 7.40/ 21.07 GFLOPS | Progress: (20/20) | 20.29 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.58/ 8.58 GFLOPS | Progress: (4/20) | 11.89 s
[Task 24/25] Current/Best: 1.92/ 8.58 GFLOPS | Progress: (8/20) | 23.02 s
[Task 24/25] Current/Best: 4.10/ 8.58 GFLOPS | Progress: (12/20) | 34.61 s Done.
+
[Task 24/25] Current/Best: 7.10/ 8.85 GFLOPS | Progress: (16/20) | 40.09 s
[Task 24/25] Current/Best: 3.21/ 8.85 GFLOPS | Progress: (20/20) | 46.13 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.54/ 2.85 GFLOPS | Progress: (4/20) | 11.69 s
[Task 25/25] Current/Best: 5.50/ 7.39 GFLOPS | Progress: (8/20) | 23.03 s
[Task 25/25] Current/Best: 5.79/ 7.39 GFLOPS | Progress: (12/20) | 34.39 s
[Task 25/25] Current/Best: 5.70/ 9.11 GFLOPS | Progress: (16/20) | 36.18 s
[Task 25/25] Current/Best: 2.83/ 9.11 GFLOPS | Progress: (20/20) | 46.87 s
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 417.65380139999934, 'median': 417.4471308999955, 'std': 0.7647686871230543}
- unoptimized: {'mean': 504.8379361799995, 'median': 504.92999955000073, 'std': 0.4890225566327642}
+ optimized: {'mean': 416.6093637100016, 'median': 415.2053465999984, 'std': 3.2585566053229775}
+ unoptimized: {'mean': 501.0427243799995, 'median': 500.7832751500018, 'std': 1.0385531205208194}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 55.101 seconds)
+ **Total running time of the script:** ( 10 minutes 28.988 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 af451b269..bd21b989e 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -282,7 +282,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.264e-07 secs/op
+ 1.255e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 217c67e09..9475b4589 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, 0x847d4e0)), stage(b, placeholder(b, 0x1a6b7dc0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
+ [stage(a, placeholder(a, 0x15710cc0)), stage(b, placeholder(b, 0x156e8e30)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 1adacf2e9..d3477a97c 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
Computation times
=================
-**13:58.736** total execution time for **tutorial** files:
+**13:24.317** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:55.101 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:28.988 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:04.899 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.955 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:58.655 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:55.559 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:32.816 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:31.846 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:25.088 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.880 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.260 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.182 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.739 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.723 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.170 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.176 | 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``) | 00:00.002 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 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_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index f1a4d54c5..9656f4b21 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -301,7 +301,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000009
+ Numpy running time: 0.000008
naive: 0.000007
@@ -403,7 +403,7 @@ compile and run this new schedule with the parallel operation applied:
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallel: 0.000009
+ parallel: 0.000006
@@ -460,7 +460,7 @@ factor to be the number of threads on your CPU.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vector: 0.000026
+ vector: 0.000025
@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, [(stride: int32*n: int32)], [], type="auto"),
@@ -512,10 +512,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 9.224419998190569e-06 1.0
- naive 6.6517e-06 0.721096827909481
- parallel 9.4665e-06 1.026243384609213
- vector 2.5711e-05 2.787275514888024
+ numpy 8.222219998970103e-06 1.0
+ naive 6.6622e-06 0.8102677866603536
+ parallel 6.0359e-06 0.7340961444422606
+ vector 2.4501300000000002e-05 2.9798886435864014
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.020310
+ Numpy running time: 0.019648
@@ -996,7 +996,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- none: 3.606828
+ none: 3.348520
@@ -1101,7 +1101,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- blocking: 0.337259
+ blocking: 0.328356
@@ -1199,7 +1199,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vectorization: 0.355468
+ vectorization: 0.360574
@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], []),
@@ -1275,7 +1275,7 @@ more cache friendly.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- loop permutation: 0.147487
+ loop permutation: 0.125586
@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], []),
@@ -1376,7 +1376,7 @@ optimized schedule.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- array packing: 0.113672
+ array packing: 0.108727
@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], []),
@@ -1471,7 +1471,7 @@ to `C` when all the block results are ready.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- block caching: 0.115491
+ block caching: 0.110984
@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], []),
@@ -1559,7 +1559,7 @@ of thread-level parallelization.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallelization: 0.150194
+ parallelization: 0.147097
@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], []),
@@ -1640,13 +1640,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.6068279385000004 1.0
- blocking 0.3372588413 0.09350566399356951
- vectorization 0.3554675789 0.09855407160005285
- loop permutation 0.1474866838 0.04089096744141791
- array packing 0.11367241349999999 0.031515895806017796
- block caching 0.11549136509999999 0.032020203644100166
- parallelization 0.150194414 0.041641690859936756
+ none 3.3485195541 1.0
+ blocking 0.3283564355 0.09806018158023096
+ vectorization 0.36057413809999994 0.10768165819981702
+ loop permutation 0.12558638090000002 0.0375050462961249
+ array packing 0.1087265983 0.0324700502844228
+ block caching 0.11098382700000001 0.03314414779633256
+ parallelization 0.147096591 0.043928843365985945
@@ -1688,7 +1688,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.899 seconds)
+ **Total running time of the script:** ( 1 minutes 0.955 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 2d23e4892..824354222 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-6cd31e7bf1d9fed7e2e9f5de1b725d1fdc5a4659
+291dd2f06331342f5c89216d5d211cb61fe3d19f
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 82e64df4f..20753df1b 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -574,7 +574,7 @@ 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 1.525 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.926 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_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 62fba2877..2634c4e28 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -427,7 +427,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip167275a7-b583-4082-8d06-98b5c563db04 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.zip445e3ca6-aee7-42f7-849a-fc778a269f05 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 07d54586b..fa360b874 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -432,14 +432,13 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<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]
- 14%|#3 | 5.80M/41.5M [00:00<00:00, 60.6MB/s]
- 28%|##7 | 11.6M/41.5M [00:00<00:00, 58.5MB/s]
- 41%|####1 | 17.2M/41.5M [00:00<00:00, 58.3MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 46.3MB/s]
- 71%|####### | 29.3M/41.5M [00:00<00:00, 49.0MB/s]
- 83%|########2 | 34.3M/41.5M [00:00<00:00, 46.1MB/s]
- 96%|#########6| 40.0M/41.5M [00:00<00:00, 43.9MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 48.2MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 58.0MB/s]
+ 35%|###4 | 14.3M/41.5M [00:00<00:00, 53.4MB/s]
+ 47%|####6 | 19.4M/41.5M [00:00<00:00, 53.2MB/s]
+ 59%|#####8 | 24.5M/41.5M [00:00<00:00, 43.4MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 43.0MB/s]
+ 92%|#########2| 38.3M/41.5M [00:00<00:00, 41.5MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 43.8MB/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 0994c1e84..a4de8de3f 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,10 +414,9 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 7%|6 | 2.99M/44.7M [00:00<00:01, 31.3MB/s]
- 13%|#3 | 5.98M/44.7M [00:00<00:01, 30.1MB/s]
- 57%|#####6 | 25.3M/44.7M [00:00<00:00, 107MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 121MB/s]
+ 47%|####7 | 21.0M/44.7M [00:00<00:00, 221MB/s]
+ 94%|#########4| 42.1M/44.7M [00:00<00:00, 214MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 219MB/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 aec4e7908..8e6559a4a 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -636,7 +636,7 @@ 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 6.490 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.886 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 7e09d6d42..fa72632d5 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:18.579</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:19.529</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -336,43 +336,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:06.490</p></td>
+<td><p>01:10.886</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:01.525</p></td>
+<td><p>01:04.926</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>00:43.045</p></td>
+<td><p>00:40.626</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>00:29.785</p></td>
+<td><p>00:29.073</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>00:27.008</p></td>
+<td><p>00:25.918</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:25.786</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
+<td><p>00:25.452</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:24.074</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
+<td><p>00:24.338</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:21.043</p></td>
+<td><p>00:20.021</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:17.376</p></td>
+<td><p>00:15.804</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>00:02.448</p></td>
+<td><p>00:02.485</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 f98337ad2..4ccdafa90 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -653,7 +653,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.8905 16.6728 17.8270 16.5003 0.4589
+ 16.1371 16.1048 16.3327 16.0200 0.1011
</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 043da304c..cb3f3c38f 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,14 +436,14 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 11%|# | 18.4M/170M [00:00<00:00, 193MB/s]
- 25%|##5 | 42.8M/170M [00:00<00:00, 230MB/s]
- 40%|###9 | 67.5M/170M [00:00<00:00, 243MB/s]
- 54%|#####4 | 92.1M/170M [00:00<00:00, 249MB/s]
- 68%|######8 | 116M/170M [00:00<00:00, 200MB/s]
- 81%|######## | 137M/170M [00:00<00:00, 206MB/s]
- 94%|#########3| 159M/170M [00:00<00:00, 214MB/s]
-100%|##########| 170M/170M [00:00<00:00, 217MB/s]
+ 9%|8 | 15.0M/170M [00:00<00:01, 157MB/s]
+ 23%|##3 | 39.4M/170M [00:00<00:00, 215MB/s]
+ 37%|###6 | 62.7M/170M [00:00<00:00, 228MB/s]
+ 51%|#####1 | 87.3M/170M [00:00<00:00, 240MB/s]
+ 66%|######5 | 112M/170M [00:00<00:00, 247MB/s]
+ 80%|#######9 | 136M/170M [00:00<00:00, 243MB/s]
+ 93%|#########3| 159M/170M [00:00<00:00, 241MB/s]
+100%|##########| 170M/170M [00:00<00:00, 235MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -538,7 +538,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 20.881 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 5.180 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 3e49fe0fc..375694fa1 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,9 +480,7 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 40%|###9 | 5.41M/13.6M [00:00<00:00, 56.6MB/s]
- 80%|#######9 | 10.8M/13.6M [00:00<00:00, 52.1MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 61.6MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 160MB/s]
</pre></div>
</div>
</div>
@@ -571,7 +569,7 @@ 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)
- 91.0258 90.8413 96.8919 90.6255 0.6976
+ 90.5833 90.2846 105.2855 90.0211 1.6182
</pre></div>
</div>
<div class="admonition note">
@@ -610,7 +608,7 @@ 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 16.120 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 12.750 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 2346e0f03..7558cae54 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -573,7 +573,7 @@ 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)
- 124.1265 124.0905 125.6675 123.5366 0.4035
+ 121.5965 121.4984 123.6207 121.0157 0.3948
</pre></div>
</div>
<div class="admonition note">
@@ -601,7 +601,7 @@ 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 3.211 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 58.626 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 cc96433b9..d7a78f589 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -509,7 +509,7 @@ 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 13.657 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 32.904 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 d2a38857a..2328e3073 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,25 +441,24 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 1%|1 | 1601/132723 [00:00<00:08, 16008.72KB/s]
- 6%|6 | 8469/132723 [00:00<00:02, 46988.85KB/s]
- 12%|#1 | 15677/132723 [00:00<00:02, 58443.71KB/s]
- 17%|#7 | 22777/132723 [00:00<00:01, 63394.88KB/s]
- 22%|##2 | 29506/132723 [00:00<00:01, 64794.26KB/s]
- 28%|##7 | 36607/132723 [00:00<00:01, 66906.06KB/s]
- 33%|###3 | 43819/132723 [00:00<00:01, 68607.71KB/s]
- 38%|###8 | 51026/132723 [00:00<00:01, 69707.27KB/s]
- 44%|####4 | 58453/132723 [00:00<00:01, 71131.64KB/s]
- 50%|####9 | 66011/132723 [00:01<00:00, 72503.04KB/s]
- 56%|#####5 | 73715/132723 [00:01<00:00, 73888.92KB/s]
- 61%|######1 | 81392/132723 [00:01<00:00, 74763.33KB/s]
- 67%|######7 | 89024/132723 [00:01<00:00, 75231.90KB/s]
- 73%|#######2 | 96665/132723 [00:01<00:00, 75585.40KB/s]
- 79%|#######8 | 104256/132723 [00:01<00:00, 75682.33KB/s]
- 84%|########4 | 111936/132723 [00:01<00:00, 76016.02KB/s]
- 90%|######### | 119564/132723 [00:01<00:00, 76093.45KB/s]
- 96%|#########5| 127176/132723 [00:01<00:00, 76098.73KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 70871.84KB/s]
+ 5%|4 | 6355/132723 [00:00<00:01, 63542.18KB/s]
+ 11%|# | 14091/132723 [00:00<00:01, 71667.43KB/s]
+ 16%|#6 | 21758/132723 [00:00<00:01, 73948.49KB/s]
+ 22%|##2 | 29504/132723 [00:00<00:01, 75332.98KB/s]
+ 28%|##8 | 37275/132723 [00:00<00:01, 76188.10KB/s]
+ 34%|###3 | 45033/132723 [00:00<00:01, 76659.11KB/s]
+ 40%|###9 | 52753/132723 [00:00<00:01, 76834.46KB/s]
+ 46%|####5 | 60489/132723 [00:00<00:00, 76999.33KB/s]
+ 51%|#####1 | 68189/132723 [00:00<00:00, 76939.24KB/s]
+ 57%|#####7 | 75886/132723 [00:01<00:00, 76945.92KB/s]
+ 63%|######3 | 83618/132723 [00:01<00:00, 77057.40KB/s]
+ 69%|######8 | 91339/132723 [00:01<00:00, 77101.71KB/s]
+ 75%|#######4 | 99050/132723 [00:01<00:00, 76768.10KB/s]
+ 80%|######## | 106734/132723 [00:01<00:00, 76786.85KB/s]
+ 86%|########6 | 114413/132723 [00:01<00:00, 76776.09KB/s]
+ 92%|#########2| 122145/132723 [00:01<00:00, 76936.25KB/s]
+ 98%|#########7| 129842/132723 [00:01<00:00, 76945.41KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 75760.24KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -502,7 +501,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 49.419 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 43.524 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 4f36416b6..a61473974 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>12:04.950</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:50.862</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -336,35 +336,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:20.881</p></td>
+<td><p>03:05.180</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:49.419</p></td>
+<td><p>02:43.524</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>02:03.211</p></td>
+<td><p>01:58.626</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><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>01:16.120</p></td>
+<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>01:32.904</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><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>01:13.657</p></td>
+<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>01:12.750</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>00:33.012</p></td>
+<td><p>00:32.114</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>00:24.655</p></td>
+<td><p>00:23.012</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>00:23.989</p></td>
+<td><p>00:22.747</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index b773c3b39..c9f54e729 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -612,7 +612,7 @@ 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.zip1f69daf0-5c8d-4cef-80da-2d76f3870040 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.zip0a08b11c-cd0e-4332-8020-a2b68519faeb 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 556650244..6107513bf 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:46.209</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:44.107</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="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>00:42.616</p></td>
+<td><p>00:40.713</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>00:02.518</p></td>
+<td><p>00:02.378</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>00:01.067</p></td>
+<td><p>00:01.009</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index cb20bae67..98545082f 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -512,10 +512,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 7700us [7700us] (46.17%; 46.17%)
-FoldScaleAxis: 8976us [9us] (53.83%; 53.83%)
- FoldConstant: 8968us [1876us] (53.77%; 99.90%)
- InferType: 7091us [7091us] (42.52%; 79.08%)
+InferType: 7253us [7253us] (45.69%; 45.69%)
+FoldScaleAxis: 8623us [9us] (54.31%; 54.31%)
+ FoldConstant: 8613us [1775us] (54.25%; 99.89%)
+ InferType: 6838us [6838us] (43.07%; 79.39%)
</pre></div>
</div>
</div>
@@ -537,10 +537,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 7559us [7559us] (45.35%; 45.35%)
-FoldScaleAxis: 9110us [8us] (54.65%; 54.65%)
- FoldConstant: 9101us [1821us] (54.60%; 99.91%)
- InferType: 7280us [7280us] (43.67%; 79.99%)
+InferType: 7000us [7000us] (45.12%; 45.12%)
+FoldScaleAxis: 8515us [9us] (54.88%; 54.88%)
+ FoldConstant: 8506us [1740us] (54.82%; 99.90%)
+ InferType: 6766us [6766us] (43.61%; 79.54%)
</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 ed92d728f..d50ac4213 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -564,7 +564,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 40.744520 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 35.900186 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 a8d44c370..5390b8ed7 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -906,7 +906,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.358382 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.516104 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 3cdd31716..d832a9ea1 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -461,8 +461,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.020113
-Baseline: 3.602078
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019695
+Baseline: 3.467897
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -522,7 +522,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.335986
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.330038
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -589,7 +589,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.351040
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.358754
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -650,7 +650,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.144266
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.122143
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -733,7 +733,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.113638
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111136
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -819,7 +819,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.115786
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111323
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -909,7 +909,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.151466
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.148002
</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 b6205b5a2..ca07f9a0f 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:36.617</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.648</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:34.285</p></td>
+<td><p>00:33.346</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></td>
-<td><p>00:01.320</p></td>
+<td><p>00:01.283</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>00:01.012</p></td>
+<td><p>00:01.019</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 87f8f5db6..d9a1853b2 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:44.630</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:15.978</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -336,27 +336,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>03:36.072</p></td>
+<td><p>03:25.858</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>01:27.927</p></td>
+<td><p>01:24.657</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>00:49.676</p></td>
+<td><p>00:48.451</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>00:31.772</p></td>
+<td><p>00:18.740</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:09.678</p></td>
+<td><p>00:09.242</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:09.506</p></td>
+<td><p>00:09.030</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 b6e9cbdcf..f590d6f94 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
@@ -492,426 +492,272 @@ cooperative fetching, unrolling and operator fusion.</p>
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" = 64;
- allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), 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" = 49 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[4] = 0f32
+ allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [2592]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[7] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- let cse_var_2: int32 = (rc.outer.outer*784)
- let cse_var_1: int32 = (rc.outer.outer*144)
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ for (rc.outer.outer: int32, 0, 16) {
+ let cse_var_2: int32 = (rc.outer.outer*1568)
+ let cse_var_1: int32 = (rc.outer.outer*288)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 49)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 49), 81)) && (floormod((threadIdx.x_1 + 49), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 49), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 49), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 8), 9)) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 147)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 66), 81)) && (floormod((threadIdx.x_1 + 66), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 147), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 66), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 34), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 245)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 2), 81)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 245), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 2), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 51), 81)) && (floormod((threadIdx.x_1 + 51), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 294), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 51), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 343)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 1), 9)) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 343), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 19), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 441)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 4), 9)) && (floormod((threadIdx.x_1 + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 441), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 4), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 490)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 4), 81)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 490), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 4), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 539)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 53), 81)) && (floormod((threadIdx.x_1 + 53), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 539), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 53), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 588), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 21), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 637)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 70), 81)) && (floormod((threadIdx.x_1 + 70), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 637), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 70), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 686)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 38), 81)) && (floormod((threadIdx.x_1 + 38), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 686), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 38), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 735)] = @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 + 735), 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" = 49;
+ 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;
+ pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 49), 81)) && (floormod((threadIdx.x_1 + 49), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((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_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else((((threadIdx.x_1 < 48) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 672), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 24), 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 + 728)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 80), 81)) && (floormod((threadIdx.x_1 + 80), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 728), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 80), 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 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 833)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 5), 9)) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 833), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 23), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 882)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 8), 9)) && (floormod((threadIdx.x_1 + 72), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 882), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 8), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 931)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 40), 81)) && (floormod((threadIdx.x_1 + 40), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 931), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 40), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 8), 81)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 980), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 8), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1029)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 57), 81)) && (floormod((threadIdx.x_1 + 57), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1029), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 57), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1078)] = @tir.if_then_else((((threadIdx.x_1 < 47) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1078), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 25), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1127)] = @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 + 1127), 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" = 49;
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 840)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 30), 81)) && (floormod((threadIdx.x_1 + 30), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 840), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 30), 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 + 896)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 5), 81)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 896), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 5), 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 + 952)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 61), 81)) && (floormod((threadIdx.x_1 + 61), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 952), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 61), 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 + 1008)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 4), 9)) && (floormod((threadIdx.x_1 + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1008), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 4), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1064)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 2), 9)) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1064), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 11), 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 + 1120)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 67), 81)) && (floormod((threadIdx.x_1 + 67), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1120), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 67), 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 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 42), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 42), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1225)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 1), 9)) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1225), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_1 < 22), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 1274)] = @tir.if_then_else((((threadIdx.x_1 < 13) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1274), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 59), 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 + 1232)] = @tir.if_then_else((((threadIdx.x_1 < 55) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1232), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1288)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 73), 81)) && (floormod((threadIdx.x_1 + 73), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1288), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 73), 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 + 1344)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 48), 81)) && (floormod((threadIdx.x_1 + 48), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1344), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 48), 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 + 1400)] = @tir.if_then_else((((threadIdx.x_1 < 49) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1400), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 23), 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 + 1456)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 79), 81)) && (floormod((threadIdx.x_1 + 79), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1456), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 79), 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 + 1512)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 6), 9)) && (floormod((threadIdx.x_1 + 54), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1512), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 6), 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 + 1568)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 29), 81)) && (floormod((threadIdx.x_1 + 29), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1568), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 29), 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 + 1624)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 4), 81)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1624), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 4), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1680)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 60), 81)) && (floormod((threadIdx.x_1 + 60), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1680), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 60), 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 + 1736)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 35), 81)) && (floormod((threadIdx.x_1 + 35), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1736), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 35), 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 + 1792)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 1), 9)) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1792), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 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 + 1848)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 66), 81)) && (floormod((threadIdx.x_1 + 66), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1848), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 66), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1904)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 41), 81)) && (floormod((threadIdx.x_1 + 41), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1904), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 41), 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 + 1960)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 7), 9)) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1960), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 16), 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 + 2016)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 8), 9)) && (floormod((threadIdx.x_1 + 72), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2016), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 8), 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 + 2072)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 47), 81)) && (floormod((threadIdx.x_1 + 47), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2072), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 47), 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 + 2128)] = @tir.if_then_else((((threadIdx.x_1 < 50) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2128), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 22), 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 + 2184)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 78), 81)) && (floormod((threadIdx.x_1 + 78), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2184), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 78), 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 + 2240)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 53), 81)) && (floormod((threadIdx.x_1 + 53), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2240), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 53), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2296)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 28), 81)) && (floormod((threadIdx.x_1 + 28), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2296), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 28), 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 + 2352)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 3), 81)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2352), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 3), 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 + 2408)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 59), 81)) && (floormod((threadIdx.x_1 + 59), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2408), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 59), 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 + 2464)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 34), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2464), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2520)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2520), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 1)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 2576)] = @tir.if_then_else((((threadIdx.x_1 < 7) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2576), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 65), 81), 9)*7)) + (threadIdx.x_1 + 2)) - 8)], 0f32, dtype=float32)
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*36864) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 49)] = kernel[((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 49), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 98), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 147)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 147), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 1)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 196), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 52), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 245)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 245), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 101), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 294)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 294), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 2)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 343)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 343), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 55), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 441)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 441), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 490)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 490), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 58), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 539)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 539), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 107), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 588), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 637)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 637), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 61), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 686)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 686), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 110), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 735)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 735), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 5)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 784), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 833)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 833), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 113), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 882)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 882), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 6)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 931)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 931), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 67), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 980), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 116), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1029)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1029), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 7)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1078)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1078), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 70), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_2 < 25), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 1127)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1127), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 119), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*36864) + 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*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 56), 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*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 112), 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*36864) + cse_var_1) + threadIdx.x_2) + 168)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 224), 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*36864) + (floordiv((threadIdx.x_2 + 280), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 280), 288), 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*36864) + (floordiv((threadIdx.x_2 + 336), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*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*36864) + (floordiv((threadIdx.x_2 + 392), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 288), 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*36864) + (floordiv((threadIdx.x_2 + 448), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 160), 288), 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*36864) + (floordiv((threadIdx.x_2 + 504), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 72)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 560), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 272), 288), 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*36864) + (floordiv((threadIdx.x_2 + 616), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 288), 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*36864) + (floordiv((threadIdx.x_2 + 672), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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*36864) + (floordiv((threadIdx.x_2 + 728), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 152), 288), 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*36864) + (floordiv((threadIdx.x_2 + 784), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 208), 288), 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*36864) + (floordiv((threadIdx.x_2 + 840), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 88), 96)*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*36864) + (floordiv((threadIdx.x_2 + 896), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 288), 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*36864) + (floordiv((threadIdx.x_2 + 952), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 288), 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*36864) + (floordiv((threadIdx.x_2 + 1008), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1064), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 200), 288), 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 + 1120)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1120), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 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 + 1176)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1176), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1232), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 288), 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 + 1288)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1288), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 288), 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 + 1344)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1344), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 64)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1400), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 248), 288), 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 + 1456)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1456), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 288), 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 + 1512)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1512), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 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 + 1568)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1568), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 288), 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 + 1624)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1624), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 184), 288), 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 + 1680)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1680), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 80), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1736)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1736), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 288), 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 + 1792)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1792), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 288), 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 + 1848)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1848), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 40)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1904), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 288), 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 + 1960)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1960), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 232), 288), 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 + 2016)] = kernel[((((blockIdx.x*36864) + 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 + 2072)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 2072), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 288), 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 + 2128)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 2128), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 288), 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 + 2184)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 2184), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 56)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 2240), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 224), 288), 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 < 8), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 2296)] = kernel[(((((blockIdx.x*36864) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 280), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3)) + 32256)]
}
- for (rc.outer.inner: int32, 0, 4) {
- let cse_var_3: int32 = (rc.outer.inner*36)
- {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[cse_var_3]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 576)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 585)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(cse_var_3 + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(cse_var_3 + 594)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(cse_var_3 + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(cse_var_3 + 603)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 144)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 720)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 153)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 729)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(cse_var_3 + 162)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(cse_var_3 + 738)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(cse_var_3 + 171)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(cse_var_3 + 747)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 288)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 864)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 297)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 873)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(cse_var_3 + 306)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(cse_var_3 + 882)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(cse_var_3 + 315)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(cse_var_3 + 891)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 432)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 1008)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 441)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 1017)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(cse_var_3 + 450)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(cse_var_3 + 1026)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(cse_var_3 + 459)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(cse_var_3 + 1035)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 577)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 586)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(cse_var_3 + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(cse_var_3 + 595)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(cse_var_3 + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(cse_var_3 + 604)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 145)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 721)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 154)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 730)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(cse_var_3 + 163)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(cse_var_3 + 739)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(cse_var_3 + 172)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(cse_var_3 + 748)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 289)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 865)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 298)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 874)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(cse_var_3 + 307)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(cse_var_3 + 883)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(cse_var_3 + 316)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(cse_var_3 + 892)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 433)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 1009)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 442)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 1018)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(cse_var_3 + 451)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(cse_var_3 + 1027)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(cse_var_3 + 460)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(cse_var_3 + 1036)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 578)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 587)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(cse_var_3 + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(cse_var_3 + 596)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(cse_var_3 + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(cse_var_3 + 605)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 146)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 722)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 155)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 731)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(cse_var_3 + 164)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(cse_var_3 + 740)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(cse_var_3 + 173)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(cse_var_3 + 749)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 290)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 866)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 299)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 875)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(cse_var_3 + 308)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(cse_var_3 + 884)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(cse_var_3 + 317)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(cse_var_3 + 893)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 434)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 1010)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 443)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 1019)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(cse_var_3 + 452)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(cse_var_3 + 1028)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(cse_var_3 + 461)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(cse_var_3 + 1037)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 579)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 588)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(cse_var_3 + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(cse_var_3 + 597)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_3 + 30)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_3 + 606)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 147)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 723)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 156)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 732)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(cse_var_3 + 165)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(cse_var_3 + 741)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_3 + 174)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_3 + 750)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 291)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 867)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 300)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 876)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(cse_var_3 + 309)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(cse_var_3 + 885)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_3 + 318)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_3 + 894)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 435)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 1011)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 444)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 1020)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(cse_var_3 + 453)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(cse_var_3 + 1029)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_3 + 462)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_3 + 1038)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 580)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 589)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(cse_var_3 + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(cse_var_3 + 598)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_3 + 31)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_3 + 607)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 148)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 724)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 157)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 733)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(cse_var_3 + 166)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(cse_var_3 + 742)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_3 + 175)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_3 + 751)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 292)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 868)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 301)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 877)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(cse_var_3 + 310)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(cse_var_3 + 886)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_3 + 319)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_3 + 895)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 436)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 1012)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 445)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 1021)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(cse_var_3 + 454)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(cse_var_3 + 1030)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_3 + 463)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_3 + 1039)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 581)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 590)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(cse_var_3 + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(cse_var_3 + 599)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_3 + 32)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_3 + 608)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 149)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 725)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 158)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 734)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(cse_var_3 + 167)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(cse_var_3 + 743)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_3 + 176)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_3 + 752)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 293)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 869)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 302)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 878)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(cse_var_3 + 311)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(cse_var_3 + 887)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_3 + 320)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_3 + 896)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 437)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 1013)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 446)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 1022)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(cse_var_3 + 455)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(cse_var_3 + 1031)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_3 + 464)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_3 + 1040)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 582)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 591)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(cse_var_3 + 24)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(cse_var_3 + 600)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(cse_var_3 + 33)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(cse_var_3 + 609)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 150)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 726)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 159)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 735)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(cse_var_3 + 168)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(cse_var_3 + 744)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(cse_var_3 + 177)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(cse_var_3 + 753)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 294)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 870)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 303)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 879)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(cse_var_3 + 312)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(cse_var_3 + 888)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(cse_var_3 + 321)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(cse_var_3 + 897)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 438)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 1014)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 447)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 1023)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(cse_var_3 + 456)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(cse_var_3 + 1032)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(cse_var_3 + 465)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(cse_var_3 + 1041)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 583)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 592)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(cse_var_3 + 25)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(cse_var_3 + 601)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(cse_var_3 + 34)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(cse_var_3 + 610)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 151)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 727)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 160)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 736)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(cse_var_3 + 169)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(cse_var_3 + 745)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(cse_var_3 + 178)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(cse_var_3 + 754)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 295)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 871)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 304)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 880)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(cse_var_3 + 313)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(cse_var_3 + 889)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(cse_var_3 + 322)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(cse_var_3 + 898)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 439)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 1015)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 448)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 1024)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(cse_var_3 + 457)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(cse_var_3 + 1033)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(cse_var_3 + 466)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(cse_var_3 + 1042)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 584)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 593)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(cse_var_3 + 26)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(cse_var_3 + 602)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(cse_var_3 + 35)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(cse_var_3 + 611)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 152)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 728)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 161)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 737)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(cse_var_3 + 170)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(cse_var_3 + 746)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(cse_var_3 + 179)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(cse_var_3 + 755)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 296)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 872)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 305)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 881)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(cse_var_3 + 314)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(cse_var_3 + 890)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(cse_var_3 + 323)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(cse_var_3 + 899)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 440)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 1016)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 449)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 1025)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(cse_var_3 + 458)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(cse_var_3 + 1034)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(cse_var_3 + 467)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(cse_var_3 + 1043)]))
- }
+ for (rc.inner: int32, 0, 32) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.inner*81) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (rc.inner*9))]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (rc.inner*9))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (rc.inner*9))]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (rc.inner*9))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (rc.inner*9))]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (rc.inner*9))]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (rc.inner*9))]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.inner*81) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.inner*9)) + 8)]))
}
}
}
- for (i1.inner: int32, 0, 4) {
- compute[(((blockIdx.x*392) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*8) + i1.inner)]), 0f32)
- compute[((((blockIdx.x*392) + (i1.inner*49)) + threadIdx.x) + 196)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*8) + i1.inner) + 4)]), 0f32)
+ for (i2.inner: int32, 0, 7) {
+ compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
}
}
}
@@ -948,7 +794,7 @@ 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: 0.247 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.231 ms
</pre></div>
</div>
</div>
@@ -978,32 +824,32 @@ conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=4)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
-conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+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=7)
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=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=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_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=32)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, 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=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
-compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
@@ -1026,14 +872,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1051,370 +897,181 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[8];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[1152];
+extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[7];
+ __shared__ float pad_temp_shared[2592];
+ __shared__ float kernel_shared[2304];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++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 * 784) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 49) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 98)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 98) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((9 <= ((((int)threadIdx.x) + 66) % 81)) && (((((int)threadIdx.x) + 66) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 147) / 81) * 49)) + ((((((int)threadIdx.x) + 66) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 245)] = ((((7 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 245) / 81) * 49)) + (((((int)threadIdx.x) + 2) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((9 <= ((((int)threadIdx.x) + 51) % 81)) && (((((int)threadIdx.x) + 51) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 294) / 81) * 49)) + ((((((int)threadIdx.x) + 51) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 343)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 343) / 81) * 49)) + (((((int)threadIdx.x) + 19) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 441)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 441) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 490)] = ((((5 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 490) / 81) * 49)) + (((((int)threadIdx.x) + 4) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 539)] = (((((9 <= ((((int)threadIdx.x) + 53) % 81)) && (((((int)threadIdx.x) + 53) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 539) / 81) * 49)) + ((((((int)threadIdx.x) + 53) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 588)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 588) / 81) * 49)) + (((((int)threadIdx.x) + 21) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 637)] = (((((9 <= ((((int)threadIdx.x) + 70) % 81)) && (((((int)threadIdx.x) + 70) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 637) / 81) * 49)) + ((((((int)threadIdx.x) + 70) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((9 <= ((((int)threadIdx.x) + 38) % 81)) && (((((int)threadIdx.x) + 38) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 686) / 81) * 49)) + ((((((int)threadIdx.x) + 38) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 735)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 735) / 81) * 49)) + (((((int)threadIdx.x) + 6) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 833)] = (((1 <= ((((int)threadIdx.x) + 5) % 9)) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 833) / 81) * 49)) + (((((int)threadIdx.x) + 23) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 882)] = (((((1 <= (((((int)threadIdx.x) / 9) + 8) % 9)) && (((((int)threadIdx.x) + 72) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 882) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 8) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 931)] = (((((9 <= ((((int)threadIdx.x) + 40) % 81)) && (((((int)threadIdx.x) + 40) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 931) / 81) * 49)) + ((((((int)threadIdx.x) + 40) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 980)] = ((((1 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 980) / 81) * 49)) + (((((int)threadIdx.x) + 8) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1029)] = (((((9 <= ((((int)threadIdx.x) + 57) % 81)) && (((((int)threadIdx.x) + 57) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1029) / 81) * 49)) + ((((((int)threadIdx.x) + 57) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1078)] = ((((((int)threadIdx.x) < 47) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1078) / 81) * 49)) + (((((int)threadIdx.x) + 25) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1127)] = (((((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 * 784) + (((((int)threadIdx.x) + 1127) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1225)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1225) / 81) * 49)) + (((((int)threadIdx.x) + 10) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 22) {
- pad_temp_shared[(((int)threadIdx.x) + 1274)] = ((((((int)threadIdx.x) < 13) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1274) / 81) * 49)) + (((((int)threadIdx.x) + 59) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((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 * 1568) + (((((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 * 1568) + (((((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 * 1568) + (((((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 * 1568) + (((((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 * 1568) + (((((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 * 1568) + (((((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 * 1568) + (((((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 * 1568) + (((((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 * 1568) + (((((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 * 1568) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 616) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 672)] = ((((((int)threadIdx.x) < 48) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 672) / 81) * 49)) + (((((int)threadIdx.x) + 24) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 728)] = (((((9 <= ((((int)threadIdx.x) + 80) % 81)) && (((((int)threadIdx.x) + 80) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 728) / 81) * 49)) + ((((((int)threadIdx.x) + 80) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 840)] = (((((9 <= ((((int)threadIdx.x) + 30) % 81)) && (((((int)threadIdx.x) + 30) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 840) / 81) * 49)) + ((((((int)threadIdx.x) + 30) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 896)] = ((((4 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 896) / 81) * 49)) + (((((int)threadIdx.x) + 5) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 952)] = (((((9 <= ((((int)threadIdx.x) + 61) % 81)) && (((((int)threadIdx.x) + 61) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 952) / 81) * 49)) + ((((((int)threadIdx.x) + 61) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1008) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1064)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1064) / 81) * 49)) + (((((int)threadIdx.x) + 11) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1120) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1232)] = ((((((int)threadIdx.x) < 55) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1232) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1288)] = (((((9 <= ((((int)threadIdx.x) + 73) % 81)) && (((((int)threadIdx.x) + 73) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1288) / 81) * 49)) + ((((((int)threadIdx.x) + 73) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((9 <= ((((int)threadIdx.x) + 48) % 81)) && (((((int)threadIdx.x) + 48) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1344) / 81) * 49)) + ((((((int)threadIdx.x) + 48) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1400)] = ((((((int)threadIdx.x) < 49) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1400) / 81) * 49)) + (((((int)threadIdx.x) + 23) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1456)] = (((((9 <= ((((int)threadIdx.x) + 79) % 81)) && (((((int)threadIdx.x) + 79) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1456) / 81) * 49)) + ((((((int)threadIdx.x) + 79) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1512)] = (((((1 <= (((((int)threadIdx.x) / 9) + 6) % 9)) && (((((int)threadIdx.x) + 54) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1512) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 6) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((9 <= ((((int)threadIdx.x) + 29) % 81)) && (((((int)threadIdx.x) + 29) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 81) * 49)) + ((((((int)threadIdx.x) + 29) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1624)] = ((((5 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1624) / 81) * 49)) + (((((int)threadIdx.x) + 4) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1680)] = (((((9 <= ((((int)threadIdx.x) + 60) % 81)) && (((((int)threadIdx.x) + 60) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1680) / 81) * 49)) + ((((((int)threadIdx.x) + 60) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1736)] = (((((9 <= ((((int)threadIdx.x) + 35) % 81)) && (((((int)threadIdx.x) + 35) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1736) / 81) * 49)) + ((((((int)threadIdx.x) + 35) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1792) / 81) * 49)) + (((((int)threadIdx.x) + 10) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1848)] = (((((9 <= ((((int)threadIdx.x) + 66) % 81)) && (((((int)threadIdx.x) + 66) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1848) / 81) * 49)) + ((((((int)threadIdx.x) + 66) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1904)] = (((((9 <= ((((int)threadIdx.x) + 41) % 81)) && (((((int)threadIdx.x) + 41) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1904) / 81) * 49)) + ((((((int)threadIdx.x) + 41) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((1 <= ((((int)threadIdx.x) + 7) % 9)) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 81) * 49)) + (((((int)threadIdx.x) + 16) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2016)] = (((((1 <= (((((int)threadIdx.x) / 9) + 8) % 9)) && (((((int)threadIdx.x) + 72) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2016) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 8) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2072)] = (((((9 <= ((((int)threadIdx.x) + 47) % 81)) && (((((int)threadIdx.x) + 47) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2072) / 81) * 49)) + ((((((int)threadIdx.x) + 47) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2128)] = ((((((int)threadIdx.x) < 50) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2128) / 81) * 49)) + (((((int)threadIdx.x) + 22) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2184)] = (((((9 <= ((((int)threadIdx.x) + 78) % 81)) && (((((int)threadIdx.x) + 78) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2184) / 81) * 49)) + ((((((int)threadIdx.x) + 78) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2240)] = (((((9 <= ((((int)threadIdx.x) + 53) % 81)) && (((((int)threadIdx.x) + 53) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2240) / 81) * 49)) + ((((((int)threadIdx.x) + 53) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2296)] = (((((9 <= ((((int)threadIdx.x) + 28) % 81)) && (((((int)threadIdx.x) + 28) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2296) / 81) * 49)) + ((((((int)threadIdx.x) + 28) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = ((((6 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2352) / 81) * 49)) + (((((int)threadIdx.x) + 3) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2408)] = (((((9 <= ((((int)threadIdx.x) + 59) % 81)) && (((((int)threadIdx.x) + 59) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2408) / 81) * 49)) + ((((((int)threadIdx.x) + 59) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2464)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2464) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2520)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2520) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 1)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 16) {
+ pad_temp_shared[(((int)threadIdx.x) + 2576)] = ((((((int)threadIdx.x) < 7) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2576) / 81) * 49)) + (((((int)threadIdx.x) + 65) / 9) * 7)) + ((int)threadIdx.x)) - 6)] : 0.000000e+00f);
}
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 36864) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 49) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 98) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 147)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 147) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 3)];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 196) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 52) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 245)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 245) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 101) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 294)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 294) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 6)];
- kernel_shared[(((int)threadIdx.x) + 343)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 343) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 55) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 441)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 441) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 9)];
- kernel_shared[(((int)threadIdx.x) + 490)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 490) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 58) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 539)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 539) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 107) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 588)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 588) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 12)];
- kernel_shared[(((int)threadIdx.x) + 637)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 637) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 61) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 686)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 686) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 110) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 735)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 735) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 15)];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 833)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 833) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 113) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 882)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 882) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 18)];
- kernel_shared[(((int)threadIdx.x) + 931)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 931) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 67) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 980)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 980) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 116) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1029)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1029) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 21)];
- kernel_shared[(((int)threadIdx.x) + 1078)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1078) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 70) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 25) {
- kernel_shared[(((int)threadIdx.x) + 1127)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1127) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 119) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 168)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 224) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 280) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 280) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 336) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 104) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 448) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 160) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 504) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 216)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 560) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 272) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 616) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 672) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 728) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 152) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 784) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 208) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 840) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 88) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 896) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 952) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1008) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 144)];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1064) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 200) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1120) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1176) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1232) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1288) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 136) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1344) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 192)];
+ kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1400) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 248) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1456) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1512) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1568) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1624)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1624) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 184) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1680) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 80) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1736)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1736) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1792) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1848)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1848) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 120)];
+ kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1904) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 176) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1960) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 232) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 2072)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 2072) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 2128) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2184)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 2184) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 168)];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 2240) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 224) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 8) {
+ kernel_shared[(((int)threadIdx.x) + 2296)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 280) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 32256)];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(rc_outer_inner * 36)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 36) + 576)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 36) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 36) + 585)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((rc_outer_inner * 36) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((rc_outer_inner * 36) + 594)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((rc_outer_inner * 36) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((rc_outer_inner * 36) + 603)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 36) + 144)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 36) + 720)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 36) + 153)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 36) + 729)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((rc_outer_inner * 36) + 162)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((rc_outer_inner * 36) + 738)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((rc_outer_inner * 36) + 171)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((rc_outer_inner * 36) + 747)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 36) + 288)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 36) + 864)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 36) + 297)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 36) + 873)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((rc_outer_inner * 36) + 306)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((rc_outer_inner * 36) + 882)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((rc_outer_inner * 36) + 315)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((rc_outer_inner * 36) + 891)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 36) + 432)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 36) + 1008)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 36) + 441)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 36) + 1017)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((rc_outer_inner * 36) + 450)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((rc_outer_inner * 36) + 1026)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((rc_outer_inner * 36) + 459)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((rc_outer_inner * 36) + 1035)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 36) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 36) + 577)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 36) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 36) + 586)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((rc_outer_inner * 36) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((rc_outer_inner * 36) + 595)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((rc_outer_inner * 36) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((rc_outer_inner * 36) + 604)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 36) + 145)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 36) + 721)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 36) + 154)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 36) + 730)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((rc_outer_inner * 36) + 163)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((rc_outer_inner * 36) + 739)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((rc_outer_inner * 36) + 172)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((rc_outer_inner * 36) + 748)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 36) + 289)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 36) + 865)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 36) + 298)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 36) + 874)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((rc_outer_inner * 36) + 307)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((rc_outer_inner * 36) + 883)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((rc_outer_inner * 36) + 316)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((rc_outer_inner * 36) + 892)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 36) + 433)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 36) + 1009)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 36) + 442)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 36) + 1018)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((rc_outer_inner * 36) + 451)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((rc_outer_inner * 36) + 1027)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((rc_outer_inner * 36) + 460)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((rc_outer_inner * 36) + 1036)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 36) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 36) + 578)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 36) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 36) + 587)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((rc_outer_inner * 36) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((rc_outer_inner * 36) + 596)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((rc_outer_inner * 36) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((rc_outer_inner * 36) + 605)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 36) + 146)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 36) + 722)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 36) + 155)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 36) + 731)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((rc_outer_inner * 36) + 164)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((rc_outer_inner * 36) + 740)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((rc_outer_inner * 36) + 173)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((rc_outer_inner * 36) + 749)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 36) + 290)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 36) + 866)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 36) + 299)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 36) + 875)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((rc_outer_inner * 36) + 308)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((rc_outer_inner * 36) + 884)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((rc_outer_inner * 36) + 317)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((rc_outer_inner * 36) + 893)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 36) + 434)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 36) + 1010)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 36) + 443)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 36) + 1019)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((rc_outer_inner * 36) + 452)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((rc_outer_inner * 36) + 1028)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((rc_outer_inner * 36) + 461)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((rc_outer_inner * 36) + 1037)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 36) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 36) + 579)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 36) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 36) + 588)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((rc_outer_inner * 36) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((rc_outer_inner * 36) + 597)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 36) + 30)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 36) + 606)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 36) + 147)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 36) + 723)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 36) + 156)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 36) + 732)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((rc_outer_inner * 36) + 165)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((rc_outer_inner * 36) + 741)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 36) + 174)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 36) + 750)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 36) + 291)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 36) + 867)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 36) + 300)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 36) + 876)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((rc_outer_inner * 36) + 309)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((rc_outer_inner * 36) + 885)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 36) + 318)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 36) + 894)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 36) + 435)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 36) + 1011)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 36) + 444)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 36) + 1020)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((rc_outer_inner * 36) + 453)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((rc_outer_inner * 36) + 1029)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 36) + 462)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 36) + 1038)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 36) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 36) + 580)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 36) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 36) + 589)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((rc_outer_inner * 36) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((rc_outer_inner * 36) + 598)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 36) + 31)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 36) + 607)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 36) + 148)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 36) + 724)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 36) + 157)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 36) + 733)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((rc_outer_inner * 36) + 166)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((rc_outer_inner * 36) + 742)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 36) + 175)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 36) + 751)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 36) + 292)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 36) + 868)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 36) + 301)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 36) + 877)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((rc_outer_inner * 36) + 310)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((rc_outer_inner * 36) + 886)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 36) + 319)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 36) + 895)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 36) + 436)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 36) + 1012)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 36) + 445)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 36) + 1021)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((rc_outer_inner * 36) + 454)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((rc_outer_inner * 36) + 1030)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 36) + 463)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 36) + 1039)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 36) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 36) + 581)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 36) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 36) + 590)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((rc_outer_inner * 36) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((rc_outer_inner * 36) + 599)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 36) + 32)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 36) + 608)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 36) + 149)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 36) + 725)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 36) + 158)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 36) + 734)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((rc_outer_inner * 36) + 167)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((rc_outer_inner * 36) + 743)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 36) + 176)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 36) + 752)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 36) + 293)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 36) + 869)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 36) + 302)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 36) + 878)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((rc_outer_inner * 36) + 311)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((rc_outer_inner * 36) + 887)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 36) + 320)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 36) + 896)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 36) + 437)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 36) + 1013)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 36) + 446)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 36) + 1022)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((rc_outer_inner * 36) + 455)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((rc_outer_inner * 36) + 1031)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 36) + 464)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 36) + 1040)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 36) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 36) + 582)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 36) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 36) + 591)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((rc_outer_inner * 36) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((rc_outer_inner * 36) + 600)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((rc_outer_inner * 36) + 33)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((rc_outer_inner * 36) + 609)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 36) + 150)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 36) + 726)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 36) + 159)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 36) + 735)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((rc_outer_inner * 36) + 168)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((rc_outer_inner * 36) + 744)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((rc_outer_inner * 36) + 177)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((rc_outer_inner * 36) + 753)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 36) + 294)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 36) + 870)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 36) + 303)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 36) + 879)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((rc_outer_inner * 36) + 312)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((rc_outer_inner * 36) + 888)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((rc_outer_inner * 36) + 321)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((rc_outer_inner * 36) + 897)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 36) + 438)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 36) + 1014)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 36) + 447)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 36) + 1023)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((rc_outer_inner * 36) + 456)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((rc_outer_inner * 36) + 1032)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((rc_outer_inner * 36) + 465)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((rc_outer_inner * 36) + 1041)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 36) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 36) + 583)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 36) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 36) + 592)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((rc_outer_inner * 36) + 25)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((rc_outer_inner * 36) + 601)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((rc_outer_inner * 36) + 34)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((rc_outer_inner * 36) + 610)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 36) + 151)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 36) + 727)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 36) + 160)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 36) + 736)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((rc_outer_inner * 36) + 169)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((rc_outer_inner * 36) + 745)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((rc_outer_inner * 36) + 178)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((rc_outer_inner * 36) + 754)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 36) + 295)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 36) + 871)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 36) + 304)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 36) + 880)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((rc_outer_inner * 36) + 313)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((rc_outer_inner * 36) + 889)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((rc_outer_inner * 36) + 322)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((rc_outer_inner * 36) + 898)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 36) + 439)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 36) + 1015)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 36) + 448)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 36) + 1024)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((rc_outer_inner * 36) + 457)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((rc_outer_inner * 36) + 1033)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((rc_outer_inner * 36) + 466)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((rc_outer_inner * 36) + 1042)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 36) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 36) + 584)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 36) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 36) + 593)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((rc_outer_inner * 36) + 26)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((rc_outer_inner * 36) + 602)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((rc_outer_inner * 36) + 35)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((rc_outer_inner * 36) + 611)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 36) + 152)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 36) + 728)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 36) + 161)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 36) + 737)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((rc_outer_inner * 36) + 170)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((rc_outer_inner * 36) + 746)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((rc_outer_inner * 36) + 179)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((rc_outer_inner * 36) + 755)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 36) + 296)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 36) + 872)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 36) + 305)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 36) + 881)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((rc_outer_inner * 36) + 314)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((rc_outer_inner * 36) + 890)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((rc_outer_inner * 36) + 323)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((rc_outer_inner * 36) + 899)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 36) + 440)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 36) + 1016)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 36) + 449)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 36) + 1025)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((rc_outer_inner * 36) + 458)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((rc_outer_inner * 36) + 1034)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((rc_outer_inner * 36) + 467)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 324) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((rc_outer_inner * 36) + 1043)]));
+ for (int rc_inner = 0; rc_inner < 32; ++rc_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_inner * 81) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
}
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[(((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 8) + i1_inner)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x)) + 196)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 8) + i1_inner) + 4)]), 0.000000e+00f);
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
}
}
</pre></div>
@@ -1451,7 +1108,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 36.072 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 25.858 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 4aab974ac..885deb49f 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -906,7 +906,7 @@ 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)
- 9.8313 9.8337 9.8863 9.7740 0.0459
+ 9.8596 9.8597 9.8747 9.8443 0.0124
</pre></div>
</div>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index e46a5f8a5..cc07a624d 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -925,7 +925,7 @@ 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)
- 773.9615 774.3938 776.3110 771.1796 2.1171
+ 754.3905 753.7758 757.3666 752.0289 2.2220
</pre></div>
</div>
</div>
@@ -947,7 +947,7 @@ 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 27.927 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 24.657 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 36c8f33ee..8bf882ed9 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,102 +625,28 @@ 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_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer: int32, 0, 16) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global;
- for (i1.outer: int32, 0, 32) {
- for (i.inner.init: int32, 0, 8) {
- let cse_var_1: int32 = (i.inner.init*16)
- {
- compute_5: Buffer(compute_4, float32, [128], [])[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, (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])) {
- for (i.inner: int32, 0, 8) {
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- let cse_var_2: int32 = (i.inner*16)
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_3: int32 = ((i.inner*16) + 1)
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_4: int32 = ((i.inner*16) + 2)
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_5: int32 = ((i.inner*16) + 3)
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_6: int32 = ((i.inner*16) + 4)
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_7: int32 = ((i.inner*16) + 5)
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_8: int32 = ((i.inner*16) + 6)
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_9: int32 = ((i.inner*16) + 7)
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 32) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [1024], [])[(((i.inner.init*32) + (nb_j.inner*16)) + j.init)] = 0f32
}
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- let cse_var_10: int32 = ((i.inner*16) + 8)
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_11: int32 = ((i.inner*16) + 9)
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_12: int32 = ((i.inner*16) + 10)
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_13: int32 = ((i.inner*16) + 11)
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_14: int32 = ((i.inner*16) + 12)
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_15: int32 = ((i.inner*16) + 13)
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_16: int32 = ((i.inner*16) + 14)
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + 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) {
- let cse_var_17: int32 = ((i.inner*16) + 15)
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 32) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_2: int32 = (((i.inner*32) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
}
}
}
- for (i0.inner: int32, 0, 8) {
- let cse_var_18: int32 = (((i0.outer*4096) + (i0.inner*512)) + (i1.outer*16))
- compute[ramp(cse_var_18, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_18, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 32) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ compute[ramp(cse_var_4, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -758,7 +684,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.840 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.655 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 5bf8deb63..d23efb532 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:47.017</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:45.693</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,7 +336,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:46.981</p></td>
+<td><p>00:45.656</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>
@@ -344,7 +344,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
-<td><p>00:00.005</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index 2ea951ca3..b9b768dc9 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1436,8 +1436,8 @@ No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
-No: 9 GFLOPS: 214.47/214.47 result: MeasureResult(costs=(0.0010794016068965517,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.261305332183838, timestamp=1662538808.5707426) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
-No: 10 GFLOPS: 0.00/214.47 result: Traceback (most recent call last):
+No: 9 GFLOPS: 80.86/80.86 result: MeasureResult(costs=(0.0028629368857142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9043185710906982, timestamp=1662538783.2651484) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+No: 10 GFLOPS: 0.00/80.86 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
@@ -1560,8 +1560,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
-No: 11 GFLOPS: 260.97/260.97 result: MeasureResult(costs=(0.0008870867790055248,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8471014499664307, timestamp=1662538809.500747) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
-No: 12 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+No: 11 GFLOPS: 259.11/259.11 result: MeasureResult(costs=(0.0008934569642857143,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6702837944030762, timestamp=1662538784.0759976) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+No: 12 GFLOPS: 0.00/259.11 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
@@ -1684,7 +1684,7 @@ Traceback (most recent call last):
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, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
-No: 13 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/259.11 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
@@ -1807,7 +1807,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
-No: 14 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/259.11 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
@@ -1930,9 +1930,9 @@ Traceback (most recent call last):
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, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
-No: 15 GFLOPS: 5.33/260.97 result: MeasureResult(costs=(0.04344341825,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9088964462280273, timestamp=1662538814.2537436) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
-No: 16 GFLOPS: 3.34/260.97 result: MeasureResult(costs=(0.06939141925,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.742975473403931, timestamp=1662538815.5034032) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
-No: 17 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+No: 15 GFLOPS: 5.47/259.11 result: MeasureResult(costs=(0.04230818525,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8662571907043457, timestamp=1662538788.7046597) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+No: 16 GFLOPS: 3.34/259.11 result: MeasureResult(costs=(0.0693959645,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.610472679138184, timestamp=1662538789.9481373) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+No: 17 GFLOPS: 0.00/259.11 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
@@ -1950,8 +1950,8 @@ No: 17 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
-No: 18 GFLOPS: 27.14/260.97 result: MeasureResult(costs=(0.008530872562500002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3425092697143555, timestamp=1662538826.5791588) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
-No: 19 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+No: 18 GFLOPS: 27.90/259.11 result: MeasureResult(costs=(0.00829776292857143,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3258106708526611, timestamp=1662538801.0125623) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+No: 19 GFLOPS: 0.00/259.11 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
@@ -2074,7 +2074,7 @@ Traceback (most recent call last):
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, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
-No: 20 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+No: 20 GFLOPS: 0.00/259.11 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
@@ -2237,7 +2237,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
-Time cost of this operator: 0.001253
+Time cost of this operator: 0.001264
</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 5c8a662b3..ed8bbd119 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -584,10 +584,10 @@ the tuned operator.</p>
########## 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 313.7 98.707 (1, 2, 10, 10, 3) 2 1 [313.7]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.117 0.981 (1, 6, 10, 10) 1 1 [3.117]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.992 0.312 (1, 1, 10, 10, 3) 1 1 [0.992]
-Total_time - 317.809 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.0 98.726 (1, 2, 10, 10, 3) 2 1 [309.0]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.018 0.964 (1, 6, 10, 10) 1 1 [3.018]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.309 (1, 1, 10, 10, 3) 1 1 [0.969]
+Total_time - 312.986 - - - - -
</pre></div>
</div>
</div>
@@ -640,10 +640,10 @@ Total_time -
########## 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 216.6 98.597 (1, 1, 10, 10, 6) 2 1 [216.6]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.198 1.001 (1, 6, 10, 10) 1 1 [2.198]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.883 0.402 (1, 3, 10, 10, 1) 1 1 [0.883]
-Total_time - 219.681 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 220.5 98.62 (1, 1, 10, 10, 6) 2 1 [220.5]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.24 1.002 (1, 6, 10, 10) 1 1 [2.24]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.845 0.378 (1, 3, 10, 10, 1) 1 1 [0.845]
+Total_time - 223.585 - - - - -
</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 358e59b1d..592e6b022 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -516,7 +516,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpqxrrffw5/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp77owt4nb/images/random'
</pre></div>
</div>
</div>
@@ -576,8 +576,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpqxrrffw5/images/target contains 8144 images
-/tmp/tmpqxrrffw5/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], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp77owt4nb/images/target contains 8144 images
+/tmp/tmp77owt4nb/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -689,13 +689,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 57s - loss: 0.2220 - accuracy: 0.9241 - val_loss: 0.1741 - val_accuracy: 0.9517
+328/328 - 57s - loss: 0.2266 - accuracy: 0.9204 - val_loss: 0.1380 - val_accuracy: 0.9532
Epoch 2/3
-328/328 - 58s - loss: 0.0987 - accuracy: 0.9621 - val_loss: 0.1086 - val_accuracy: 0.9664
+328/328 - 53s - loss: 0.0999 - accuracy: 0.9626 - val_loss: 0.1135 - val_accuracy: 0.9645
Epoch 3/3
-328/328 - 61s - loss: 0.0683 - accuracy: 0.9748 - val_loss: 0.1066 - val_accuracy: 0.9675
+328/328 - 53s - loss: 0.0648 - accuracy: 0.9760 - val_loss: 0.1153 - val_accuracy: 0.9619
-<keras.callbacks.History object at 0x7fc571c977d0>
+<keras.callbacks.History object at 0x7f3c71a73e10>
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 52.566 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 7.448 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 d76e1a520..ac4f57544 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:51.379</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:02.454</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,19 +336,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:52.566</p></td>
+<td><p>05:07.448</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>00:46.390</p></td>
+<td><p>00:43.777</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>00:08.816</p></td>
+<td><p>00:07.810</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>00:03.605</p></td>
+<td><p>00:03.417</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 c965cb460..32030e1ef 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:48.320</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:44.205</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,19 +336,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:36.579</p></td>
+<td><p>00:32.466</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>00:10.171</p></td>
+<td><p>00:10.217</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>00:01.563</p></td>
+<td><p>00:01.515</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
-<td><p>00:00.008</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 9580f73cf..1e4f4800e 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -522,7 +522,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fc4f6412680>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f3bd6615560>
</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 14f4a00f7..934d532fc 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.366</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.253</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,35 +336,35 @@
</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>00:02.019</p></td>
+<td><p>00:01.967</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>00:01.024</p></td>
+<td><p>00:00.999</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.569</p></td>
+<td><p>00:00.555</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></td>
-<td><p>00:00.550</p></td>
+<td><p>00:00.540</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>00:00.108</p></td>
+<td><p>00:00.104</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.049</p></td>
+<td><p>00:00.044</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.031</p></td>
+<td><p>00:00.028</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.017</p></td>
+<td><p>00:00.016</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 194ea4a10..07a71795f 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -577,7 +577,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpdxsk3kes/input0.cc'\nsource_filename = \"/tmp/tmpdxsk3kes/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/tmpsvrfghet/input0.cc'\nsource_filename = \"/tmp/tmpsvrfghet/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 3153785d7..aa2238b85 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -224,7 +224,17 @@
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
+<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
+<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
+<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
+</ul>
+</li>
<li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/reference/api/doxygen/elemwise_8h_source.html b/docs/reference/api/doxygen/elemwise_8h_source.html
index b431fc170..029d6a5c2 100644
--- a/docs/reference/api/doxygen/elemwise_8h_source.html
+++ b/docs/reference/api/doxygen/elemwise_8h_source.html
@@ -66,7 +66,7 @@ $(function() {
<div class="title">elemwise.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="elemwise_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 more co [...]
+<a href="elemwise_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 more co [...]
<div class="ttc" id="namespacetvm_1_1topi_html_af6b3e60333fce92bcf0930e45683a8f6"><div class="ttname"><a href="namespacetvm_1_1topi.html#af6b3e60333fce92bcf0930e45683a8f6">tvm::topi::negative</a></div><div class="ttdeci">Tensor negative(const Tensor &x, std::string name="T_negative", std::string tag=kElementWise)</div><div class="ttdoc">Creates an operation that returns the negation of a given tensor. </div><div class="ttdef"><b>Definition:</b> elemwise.h:166</div></div>
<div class="ttc" id="namespacetvm_html_aac2abc149c1a47944c37b560181b15c0"><div class="ttname"><a href="namespacetvm.html#aac2abc149c1a47944c37b560181b15c0">tvm::min</a></div><div class="ttdeci">PrimExpr min(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">take minimum of two values </div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a7ac1dc0d99ce93090a4cdf90ab19d4b8"><div class="ttname"><a href="namespacetvm_1_1topi.html#a7ac1dc0d99ce93090a4cdf90ab19d4b8">tvm::topi::minimum</a></div><div class="ttdeci">tvm::PrimExpr minimum(const tvm::PrimExpr &a, const tvm::PrimExpr &b)</div><div class="ttdef"><b>Definition:</b> broadcast.h:354</div></div>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 7409d793b..e27b6a873 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1602,7 +1602,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1886,7 +1886,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 47f86a395..4c38492fa 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/6cd31e7bf/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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 d73277189..84087f5a7 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/6cd31e7bf/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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 840e1a810..bf7b63f82 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/6cd31e7bf/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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 e5a1cd7e4..71ad5d384 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/6cd31e7bf/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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 abe722340..e68f96f31 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/6cd31e7bf/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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 bb98988d8..04cae9ba4 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/6cd31e7bf/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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 314ecbbb0..b2a0da476 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/6cd31e7bf/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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 510b8d44a..fa9e070e6 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/6cd31e7bf/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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 bafa17297..3b036c121 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/6cd31e7bf/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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 f69f05870..65c4b2de5 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/6cd31e7bf/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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 d93f3467b..c85e08247 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/6cd31e7bf/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/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/6cd31e7bf/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L414">runtime.ts:414</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -305,7 +305,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -322,7 +322,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L474">runtime.ts:474</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -346,7 +346,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L443">runtime.ts:443</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index a338b2d62..092605b96 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -122,7 +122,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L158">runtime.ts:158</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
</section>
@@ -164,7 +164,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L165">runtime.ts:165</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index 9c92cc30e..e918bd3d2 100644
--- a/docs/reference/api/typedoc/classes/rpcserver.html
+++ b/docs/reference/api/typedoc/classes/rpcserver.html
@@ -115,7 +115,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index 958f95a8d..a88f9c328 100644
--- a/docs/reference/api/typedoc/classes/scalar.html
+++ b/docs/reference/api/typedoc/classes/scalar.html
@@ -112,7 +112,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index 759169d0c..d1e59cef6 100644
--- a/docs/reference/api/typedoc/classes/webgpucontext.html
+++ b/docs/reference/api/typedoc/classes/webgpucontext.html
@@ -120,7 +120,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -145,7 +145,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">GPUDevice</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
</ul>
</aside>
</section>
@@ -155,7 +155,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
</ul>
</aside>
</section>
@@ -172,7 +172,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -209,7 +209,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/enums/argtypecode.html b/docs/reference/api/typedoc/enums/argtypecode.html
index 911dcadb3..885493d40 100644
--- a/docs/reference/api/typedoc/enums/argtypecode.html
+++ b/docs/reference/api/typedoc/enums/argtypecode.html
@@ -106,7 +106,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 6</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index b246107cc..a88c23270 100644
--- a/docs/reference/api/typedoc/enums/aynccallbackcode.html
+++ b/docs/reference/api/typedoc/enums/aynccallbackcode.html
@@ -93,7 +93,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Exception<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L676">runtime.ts:676</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L675">runtime.ts:675</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index c35145e6a..8f54c5f3a 100644
--- a/docs/reference/api/typedoc/enums/dldatatypecode.html
+++ b/docs/reference/api/typedoc/enums/dldatatypecode.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L240">runtime.ts:240</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L243">runtime.ts:243</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L241">runtime.ts:241</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index cd04ebdb7..58a20955b 100644
--- a/docs/reference/api/typedoc/enums/rpcserverstate.html
+++ b/docs/reference/api/typedoc/enums/rpcserverstate.html
@@ -90,7 +90,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index 7664cb5af..4d1248cbb 100644
--- a/docs/reference/api/typedoc/enums/sizeof.html
+++ b/docs/reference/api/typedoc/enums/sizeof.html
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index 45c3ae826..470a6ec0f 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L36">runtime.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L246">runtime.ts:246</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L247">runtime.ts:247</a></li>
</ul>
</aside>
</section>
@@ -1549,7 +1549,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
</section>
@@ -1559,7 +1559,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L249">runtime.ts:249</a></li>
</ul>
</aside>
</section>
@@ -1569,7 +1569,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L250">runtime.ts:250</a></li>
</ul>
</aside>
</section>
@@ -1580,7 +1580,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L175">runtime.ts:175</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1589,7 +1589,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L176">runtime.ts:176</a></li>
</ul>
</aside>
</section>
@@ -1599,7 +1599,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L180">runtime.ts:180</a></li>
</ul>
</aside>
</section>
@@ -1609,7 +1609,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L177">runtime.ts:177</a></li>
</ul>
</aside>
</section>
@@ -1619,7 +1619,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L178">runtime.ts:178</a></li>
</ul>
</aside>
</section>
@@ -1629,7 +1629,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L179">runtime.ts:179</a></li>
</ul>
</aside>
</section>
@@ -1640,7 +1640,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L183">runtime.ts:183</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1649,7 +1649,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L186">runtime.ts:186</a></li>
</ul>
</aside>
</section>
@@ -1659,7 +1659,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L184">runtime.ts:184</a></li>
</ul>
</aside>
</section>
@@ -1669,7 +1669,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L185">runtime.ts:185</a></li>
</ul>
</aside>
</section>
@@ -1679,7 +1679,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
</section>
@@ -1689,7 +1689,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L187">runtime.ts:187</a></li>
</ul>
</aside>
</section>
@@ -1699,7 +1699,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L188">runtime.ts:188</a></li>
</ul>
</aside>
</section>
@@ -1709,7 +1709,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/runtime.ts#L190">runtime.ts:190</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index 6ec620346..7f808e416 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -113,7 +113,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/types.ts#L52">types.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/interfaces/functioninfo.html b/docs/reference/api/typedoc/interfaces/functioninfo.html
index 3ac432564..f747ddcc5 100644
--- a/docs/reference/api/typedoc/interfaces/functioninfo.html
+++ b/docs/reference/api/typedoc/interfaces/functioninfo.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">arg_<wbr>types<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">launch_<wbr>param_<wbr>tags<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">name<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/libraryprovider.html b/docs/reference/api/typedoc/interfaces/libraryprovider.html
index 7c0513dcb..a1dbc1dbb 100644
--- a/docs/reference/api/typedoc/interfaces/libraryprovider.html
+++ b/docs/reference/api/typedoc/interfaces/libraryprovider.html
@@ -112,7 +112,7 @@
<div class="tsd-signature tsd-kind-icon">imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/types.ts#L34">types.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -127,7 +127,7 @@
<div class="tsd-signature tsd-kind-icon">start<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>inst<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">Instance</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6cd31e7bf/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/291dd2f06/web/src/types.ts#L39">types.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/searchindex.js b/docs/searchindex.js
index 7b12fb473..9a061f054 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
+Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
diff --git a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
index d2cc5b3a1..150ecd862 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:23.251</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:23.010</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -336,7 +336,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:23.244</p></td>
+<td><p>00:23.003</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 420ed894f..8b7897c6c 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -571,7 +571,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 26.12s!
+resnet18_v1 inference graph built in 25.05s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_detection.html b/docs/topic/vta/tutorials/frontend/deploy_detection.html
index d951d001d..5a08c5726 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -589,7 +589,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
"target_host parameter is going to be deprecated. "
/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 17.52s!
+yolov3-tiny inference graph built in 17.37s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index 31ed69305..465db9abb 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:35.359</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:35.870</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:49.156</p></td>
+<td><p>00:50.386</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:46.203</p></td>
+<td><p>00:45.484</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index 22f92cef9..22ee4671d 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.304</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.278</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.893</p></td>
+<td><p>00:02.861</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></td>
-<td><p>00:00.410</p></td>
+<td><p>00:00.417</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index 7cb27bb40..ba0f821ed 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.765</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.750</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.412</p></td>
+<td><p>00:00.404</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></td>
-<td><p>00:00.352</p></td>
+<td><p>00:00.345</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index 5ff2b6e5a..af50a0210 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -565,7 +565,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 95.308 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 94.049 ms
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index 6ef76c8e5..6905630cb 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -669,16 +669,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 9.37/9.37 result: MeasureResult(costs=(0.028644973599999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6037588119506836, timestamp=1662537521.942411) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.51/9.37 result: MeasureResult(costs=(0.10708118039999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8712053298950195, timestamp=1662537523.8243418) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 10.89/10.89 result: MeasureResult(costs=(0.0246387222,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5891413688659668, timestamp=1662537524.991608) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.69/10.89 result: MeasureResult(costs=(0.1584580492,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6713852882385254, timestamp=1662537528.2955613) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.55/10.89 result: MeasureResult(costs=(0.0757060276,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3639497756958008, timestamp=1662537529.7837975) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.84/10.89 result: MeasureResult(costs=(0.1461511332,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4779767990112305, timestamp=1662537532.8961031) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.87/10.89 result: MeasureResult(costs=(0.3088538152,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.078850746154785, timestamp=1662537538.0101764) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 10.14/10.89 result: MeasureResult(costs=(0.0264776046,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.578754186630249, timestamp=1662537538.604207) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.66/10.89 result: MeasureResult(costs=(0.1619709292,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6991984844207764, timestamp=1662537541.4238858) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.77/10.89 result: MeasureResult(costs=(0.0968786178,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.665210247039795, timestamp=1662537543.1423182) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 9.12/9.12 result: MeasureResult(costs=(0.029440913000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6066429615020752, timestamp=1662537520.205738) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.59/9.12 result: MeasureResult(costs=(0.10350975679999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.791125774383545, timestamp=1662537522.5778143) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.64/11.64 result: MeasureResult(costs=(0.0230526156,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5854988098144531, timestamp=1662537523.1529157) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.64/11.64 result: MeasureResult(costs=(0.1636105772,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7520909309387207, timestamp=1662537526.5029535) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.55/11.64 result: MeasureResult(costs=(0.0756971984,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3548974990844727, timestamp=1662537527.9882061) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.69/11.64 result: MeasureResult(costs=(0.159028207,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7103192806243896, timestamp=1662537530.7405684) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.87/11.64 result: MeasureResult(costs=(0.30897949739999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.073216676712036, timestamp=1662537536.4244936) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 9.88/11.64 result: MeasureResult(costs=(0.0271777442,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5799770355224609, timestamp=1662537537.0253024) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.89/11.64 result: MeasureResult(costs=(0.1420222946,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.37844181060791, timestamp=1662537539.5241234) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.49/11.64 result: MeasureResult(costs=(0.10785104279999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.834287405014038, timestamp=1662537541.4143353) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
</pre></div>
</div>
<p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index 00eab861b..651dd1c01 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -551,7 +551,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 504.8379361799995, 'median': 504.92999955000073, 'std': 0.4890225566327642}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 501.0427243799995, 'median': 500.7832751500018, 'std': 1.0385531205208194}
</pre></div>
</div>
</div>
@@ -706,178 +706,178 @@ depending on the specifics of the model and the target platform.</p>
"target_host parameter is going to be deprecated. "
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 17.15/ 17.15 GFLOPS | Progress: (4/20) | 6.91 s
-[Task 1/25] Current/Best: 6.12/ 17.15 GFLOPS | Progress: (8/20) | 10.08 s
-[Task 1/25] Current/Best: 11.44/ 22.19 GFLOPS | Progress: (12/20) | 12.67 s
-[Task 1/25] Current/Best: 16.30/ 22.55 GFLOPS | Progress: (16/20) | 14.41 s
-[Task 1/25] Current/Best: 11.49/ 23.60 GFLOPS | Progress: (20/20) | 16.20 s Done.
+[Task 1/25] Current/Best: 17.39/ 17.39 GFLOPS | Progress: (4/20) | 6.62 s
+[Task 1/25] Current/Best: 6.16/ 17.39 GFLOPS | Progress: (8/20) | 9.60 s
+[Task 1/25] Current/Best: 11.46/ 22.50 GFLOPS | Progress: (12/20) | 12.10 s
+[Task 1/25] Current/Best: 16.41/ 22.74 GFLOPS | Progress: (16/20) | 13.81 s
+[Task 1/25] Current/Best: 11.42/ 23.77 GFLOPS | Progress: (20/20) | 15.58 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 11.75/ 13.20 GFLOPS | Progress: (4/20) | 4.17 s
-[Task 2/25] Current/Best: 13.80/ 18.00 GFLOPS | Progress: (8/20) | 5.52 s
-[Task 2/25] Current/Best: 20.01/ 20.01 GFLOPS | Progress: (12/20) | 6.89 s
-[Task 2/25] Current/Best: 12.63/ 20.01 GFLOPS | Progress: (16/20) | 8.21 s
-[Task 2/25] Current/Best: 19.58/ 20.01 GFLOPS | Progress: (20/20) | 9.89 s Done.
+[Task 2/25] Current/Best: 12.25/ 13.17 GFLOPS | Progress: (4/20) | 3.90 s
+[Task 2/25] Current/Best: 13.96/ 18.56 GFLOPS | Progress: (8/20) | 5.22 s
+[Task 2/25] Current/Best: 20.93/ 20.93 GFLOPS | Progress: (12/20) | 6.55 s
+[Task 2/25] Current/Best: 12.44/ 20.93 GFLOPS | Progress: (16/20) | 7.81 s
+[Task 2/25] Current/Best: 19.81/ 20.93 GFLOPS | Progress: (20/20) | 9.44 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 1.62/ 10.76 GFLOPS | Progress: (4/20) | 6.07 s
-[Task 3/25] Current/Best: 15.13/ 16.67 GFLOPS | Progress: (8/20) | 8.08 s
-[Task 3/25] Current/Best: 14.74/ 16.67 GFLOPS | Progress: (12/20) | 9.85 s
-[Task 3/25] Current/Best: 7.16/ 23.49 GFLOPS | Progress: (16/20) | 11.82 s
-[Task 3/25] Current/Best: 12.45/ 23.49 GFLOPS | Progress: (20/20) | 16.52 s Done.
+[Task 3/25] Current/Best: 1.62/ 10.82 GFLOPS | Progress: (4/20) | 5.94 s
+[Task 3/25] Current/Best: 15.29/ 16.77 GFLOPS | Progress: (8/20) | 7.90 s
+[Task 3/25] Current/Best: 14.78/ 16.77 GFLOPS | Progress: (12/20) | 9.65 s
+[Task 3/25] Current/Best: 7.21/ 23.73 GFLOPS | Progress: (16/20) | 11.57 s
+[Task 3/25] Current/Best: 12.34/ 23.73 GFLOPS | Progress: (20/20) | 16.13 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.37/ 19.82 GFLOPS | Progress: (4/20) | 2.60 s
-[Task 4/25] Current/Best: 6.71/ 19.82 GFLOPS | Progress: (8/20) | 7.51 s
-[Task 4/25] Current/Best: 20.69/ 20.69 GFLOPS | Progress: (12/20) | 12.65 s
-[Task 4/25] Current/Best: 16.73/ 20.69 GFLOPS | Progress: (16/20) | 15.11 s
-[Task 4/25] Current/Best: 12.90/ 20.69 GFLOPS | Progress: (20/20) | 17.26 s Done.
+[Task 4/25] Current/Best: 9.53/ 20.44 GFLOPS | Progress: (4/20) | 2.48 s
+[Task 4/25] Current/Best: 6.80/ 20.44 GFLOPS | Progress: (8/20) | 6.93 s
+[Task 4/25] Current/Best: 21.78/ 21.78 GFLOPS | Progress: (12/20) | 11.56 s
+[Task 4/25] Current/Best: 17.26/ 21.78 GFLOPS | Progress: (16/20) | 13.83 s
+[Task 4/25] Current/Best: 13.24/ 21.78 GFLOPS | Progress: (20/20) | 15.83 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.49/ 10.02 GFLOPS | Progress: (4/20) | 2.79 s
-[Task 5/25] Current/Best: 11.26/ 13.00 GFLOPS | Progress: (8/20) | 4.92 s
-[Task 5/25] Current/Best: 9.54/ 17.23 GFLOPS | Progress: (12/20) | 8.12 s
-[Task 5/25] Current/Best: 11.17/ 22.13 GFLOPS | Progress: (16/20) | 9.59 s
-[Task 5/25] Current/Best: 10.76/ 22.13 GFLOPS | Progress: (20/20) | 11.63 s Done.
+[Task 5/25] Current/Best: 9.56/ 9.93 GFLOPS | Progress: (4/20) | 2.71 s
+[Task 5/25] Current/Best: 11.77/ 13.06 GFLOPS | Progress: (8/20) | 4.81 s
+[Task 5/25] Current/Best: 9.73/ 17.92 GFLOPS | Progress: (12/20) | 7.97 s
+[Task 5/25] Current/Best: 11.81/ 22.46 GFLOPS | Progress: (16/20) | 9.45 s
+[Task 5/25] Current/Best: 11.83/ 22.46 GFLOPS | Progress: (20/20) | 11.32 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.02/ 19.83 GFLOPS | Progress: (4/20) | 4.35 s
-[Task 6/25] Current/Best: 18.20/ 19.83 GFLOPS | Progress: (8/20) | 6.25 s
-[Task 6/25] Current/Best: 12.28/ 19.83 GFLOPS | Progress: (12/20) | 8.26 s
-[Task 6/25] Current/Best: 19.50/ 19.83 GFLOPS | Progress: (16/20) | 10.61 s
-[Task 6/25] Current/Best: 3.70/ 19.83 GFLOPS | Progress: (20/20) | 13.21 s Done.
+[Task 6/25] Current/Best: 12.09/ 19.93 GFLOPS | Progress: (4/20) | 4.08 s
+[Task 6/25] Current/Best: 18.78/ 19.93 GFLOPS | Progress: (8/20) | 5.86 s
+[Task 6/25] Current/Best: 13.19/ 19.93 GFLOPS | Progress: (12/20) | 7.81 s
+[Task 6/25] Current/Best: 19.80/ 19.93 GFLOPS | Progress: (16/20) | 10.08 s
+[Task 6/25] Current/Best: 3.75/ 19.93 GFLOPS | Progress: (20/20) | 12.63 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 10.76/ 12.21 GFLOPS | Progress: (4/20) | 3.81 s
-[Task 7/25] Current/Best: 19.25/ 20.73 GFLOPS | Progress: (8/20) | 5.39 s
-[Task 7/25] Current/Best: 15.19/ 20.73 GFLOPS | Progress: (12/20) | 7.42 s
-[Task 7/25] Current/Best: 12.12/ 20.73 GFLOPS | Progress: (16/20) | 9.52 s
-[Task 7/25] Current/Best: 6.34/ 21.16 GFLOPS | Progress: (20/20) | 12.05 s Done.
+[Task 7/25] Current/Best: 10.98/ 12.61 GFLOPS | Progress: (4/20) | 3.76 s
+[Task 7/25] Current/Best: 19.79/ 21.12 GFLOPS | Progress: (8/20) | 5.31 s
+[Task 7/25] Current/Best: 14.54/ 21.12 GFLOPS | Progress: (12/20) | 7.25 s
+[Task 7/25] Current/Best: 12.11/ 21.12 GFLOPS | Progress: (16/20) | 9.33 s
+[Task 7/25] Current/Best: 6.31/ 21.36 GFLOPS | Progress: (20/20) | 11.84 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 10.22/ 14.06 GFLOPS | Progress: (4/20) | 3.13 s
-[Task 8/25] Current/Best: 9.76/ 14.06 GFLOPS | Progress: (8/20) | 8.39 s
-[Task 8/25] Current/Best: 13.71/ 14.06 GFLOPS | Progress: (12/20) | 15.19 s
-[Task 8/25] Current/Best: 18.95/ 18.95 GFLOPS | Progress: (16/20) | 17.31 s
-[Task 8/25] Current/Best: 19.81/ 19.81 GFLOPS | Progress: (20/20) | 24.53 s Done.
+[Task 8/25] Current/Best: 10.13/ 14.21 GFLOPS | Progress: (4/20) | 3.00 s
+[Task 8/25] Current/Best: 9.70/ 14.21 GFLOPS | Progress: (8/20) | 7.86 s
+[Task 8/25] Current/Best: 13.16/ 14.21 GFLOPS | Progress: (12/20) | 14.16 s
+[Task 8/25] Current/Best: 19.03/ 19.03 GFLOPS | Progress: (16/20) | 16.25 s
+[Task 8/25] Current/Best: 19.85/ 19.85 GFLOPS | Progress: (20/20) | 22.80 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.07/ 15.61 GFLOPS | Progress: (4/20) | 12.13 s
-[Task 9/25] Current/Best: 22.22/ 22.22 GFLOPS | Progress: (8/20) | 14.03 s
-[Task 9/25] Current/Best: 8.16/ 22.22 GFLOPS | Progress: (12/20) | 16.67 s
-[Task 9/25] Current/Best: 17.58/ 22.22 GFLOPS | Progress: (16/20) | 19.65 s
-[Task 9/25] Current/Best: 8.80/ 22.22 GFLOPS | Progress: (20/20) | 28.57 s
+[Task 9/25] Current/Best: 14.24/ 15.43 GFLOPS | Progress: (4/20) | 12.04 s
+[Task 9/25] Current/Best: 23.28/ 23.28 GFLOPS | Progress: (8/20) | 13.93 s
+[Task 9/25] Current/Best: 8.23/ 23.28 GFLOPS | Progress: (12/20) | 16.31 s
+[Task 9/25] Current/Best: 17.68/ 23.28 GFLOPS | Progress: (16/20) | 18.92 s
+[Task 9/25] Current/Best: 8.90/ 23.28 GFLOPS | Progress: (20/20) | 26.90 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.20/ 18.20 GFLOPS | Progress: (4/20) | 2.74 s
-[Task 10/25] Current/Best: 15.44/ 18.20 GFLOPS | Progress: (8/20) | 4.45 s
-[Task 10/25] Current/Best: 12.91/ 19.02 GFLOPS | Progress: (12/20) | 6.06 s
-[Task 10/25] Current/Best: 18.87/ 20.32 GFLOPS | Progress: (16/20) | 7.21 s
-[Task 10/25] Current/Best: 8.92/ 20.32 GFLOPS | Progress: (20/20) | 8.79 s Done.
+[Task 10/25] Current/Best: 18.04/ 18.04 GFLOPS | Progress: (4/20) | 2.70 s
+[Task 10/25] Current/Best: 15.66/ 18.04 GFLOPS | Progress: (8/20) | 4.31 s
+[Task 10/25] Current/Best: 12.20/ 19.14 GFLOPS | Progress: (12/20) | 5.87 s
+[Task 10/25] Current/Best: 19.09/ 20.48 GFLOPS | Progress: (16/20) | 7.00 s
+[Task 10/25] Current/Best: 8.89/ 20.48 GFLOPS | Progress: (20/20) | 8.57 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 11.47/ 18.01 GFLOPS | Progress: (4/20) | 3.62 s
-[Task 11/25] Current/Best: 16.84/ 18.01 GFLOPS | Progress: (8/20) | 6.50 s
-[Task 11/25] Current/Best: 15.82/ 18.01 GFLOPS | Progress: (12/20) | 8.64 s
-[Task 11/25] Current/Best: 11.94/ 20.74 GFLOPS | Progress: (16/20) | 11.62 s
-[Task 11/25] Current/Best: 19.33/ 21.32 GFLOPS | Progress: (20/20) | 13.78 s Done.
+[Task 11/25] Current/Best: 12.22/ 18.06 GFLOPS | Progress: (4/20) | 3.45 s
+[Task 11/25] Current/Best: 16.71/ 18.06 GFLOPS | Progress: (8/20) | 6.22 s
+[Task 11/25] Current/Best: 17.47/ 18.06 GFLOPS | Progress: (12/20) | 8.33 s
+[Task 11/25] Current/Best: 13.58/ 20.87 GFLOPS | Progress: (16/20) | 11.10 s
+[Task 11/25] Current/Best: 19.06/ 21.23 GFLOPS | Progress: (20/20) | 13.18 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.76/ 18.00 GFLOPS | Progress: (4/20) | 5.95 s
-[Task 12/25] Current/Best: 5.26/ 18.00 GFLOPS | Progress: (8/20) | 10.01 s
-[Task 12/25] Current/Best: 17.72/ 18.82 GFLOPS | Progress: (12/20) | 12.05 s
-[Task 12/25] Current/Best: 12.74/ 18.82 GFLOPS | Progress: (16/20) | 15.11 s
-[Task 12/25] Current/Best: 14.95/ 18.82 GFLOPS | Progress: (20/20) | 17.05 s Done.
+[Task 12/25] Current/Best: 7.75/ 18.12 GFLOPS | Progress: (4/20) | 5.55 s
+[Task 12/25] Current/Best: 5.23/ 18.12 GFLOPS | Progress: (8/20) | 9.33 s
+[Task 12/25] Current/Best: 19.26/ 19.26 GFLOPS | Progress: (12/20) | 11.33 s
+[Task 12/25] Current/Best: 12.84/ 19.26 GFLOPS | Progress: (16/20) | 14.17 s
+[Task 12/25] Current/Best: 15.22/ 19.26 GFLOPS | Progress: (20/20) | 16.10 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.81/ 17.18 GFLOPS | Progress: (4/20) | 3.99 s
-[Task 13/25] Current/Best: 15.25/ 20.45 GFLOPS | Progress: (8/20) | 6.66 s
-[Task 13/25] Current/Best: 19.22/ 21.08 GFLOPS | Progress: (12/20) | 9.85 s
-[Task 13/25] Current/Best: 12.16/ 21.08 GFLOPS | Progress: (16/20) | 13.46 s
-[Task 13/25] Current/Best: 18.29/ 21.08 GFLOPS | Progress: (20/20) | 15.81 s Done.
+[Task 13/25] Current/Best: 8.83/ 17.27 GFLOPS | Progress: (4/20) | 3.80 s
+[Task 13/25] Current/Best: 15.02/ 20.62 GFLOPS | Progress: (8/20) | 6.27 s
+[Task 13/25] Current/Best: 19.44/ 21.05 GFLOPS | Progress: (12/20) | 9.27 s
+[Task 13/25] Current/Best: 12.18/ 21.05 GFLOPS | Progress: (16/20) | 12.77 s
+[Task 13/25] Current/Best: 18.41/ 21.05 GFLOPS | Progress: (20/20) | 15.04 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 12.36/ 12.99 GFLOPS | Progress: (4/20) | 3.59 s
-[Task 14/25] Current/Best: 6.05/ 13.13 GFLOPS | Progress: (8/20) | 5.81 s
-[Task 14/25] Current/Best: 20.47/ 20.47 GFLOPS | Progress: (12/20) | 8.55 s
-[Task 14/25] Current/Best: 16.95/ 20.47 GFLOPS | Progress: (16/20) | 10.29 s Done.
+[Task 14/25] Current/Best: 13.84/ 13.84 GFLOPS | Progress: (4/20) | 3.35 s
+[Task 14/25] Current/Best: 6.11/ 13.84 GFLOPS | Progress: (8/20) | 5.54 s
+[Task 14/25] Current/Best: 20.26/ 20.26 GFLOPS | Progress: (12/20) | 8.11 s
+[Task 14/25] Current/Best: 16.78/ 20.26 GFLOPS | Progress: (16/20) | 9.79 s Done.
-[Task 14/25] Current/Best: 16.93/ 20.47 GFLOPS | Progress: (20/20) | 12.12 s
+[Task 14/25] Current/Best: 17.35/ 20.26 GFLOPS | Progress: (20/20) | 11.60 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 15.96/ 17.41 GFLOPS | Progress: (4/20) | 3.00 s
-[Task 15/25] Current/Best: 14.06/ 17.69 GFLOPS | Progress: (8/20) | 4.35 s
-[Task 15/25] Current/Best: 10.30/ 21.79 GFLOPS | Progress: (12/20) | 6.64 s
-[Task 15/25] Current/Best: 20.05/ 21.79 GFLOPS | Progress: (16/20) | 10.57 s
-[Task 15/25] Current/Best: 9.61/ 21.79 GFLOPS | Progress: (20/20) | 11.63 s
+[Task 15/25] Current/Best: 16.15/ 17.50 GFLOPS | Progress: (4/20) | 2.85 s
+[Task 15/25] Current/Best: 14.45/ 17.78 GFLOPS | Progress: (8/20) | 4.20 s
+[Task 15/25] Current/Best: 10.37/ 22.24 GFLOPS | Progress: (12/20) | 6.33 s
+[Task 15/25] Current/Best: 20.27/ 22.24 GFLOPS | Progress: (16/20) | 9.39 s
+[Task 15/25] Current/Best: 9.65/ 22.24 GFLOPS | Progress: (20/20) | 10.43 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 19.89/ 19.89 GFLOPS | Progress: (4/20) | 3.21 s
-[Task 16/25] Current/Best: 3.02/ 19.89 GFLOPS | Progress: (8/20) | 4.86 s
-[Task 16/25] Current/Best: 19.42/ 19.89 GFLOPS | Progress: (12/20) | 6.12 s
-[Task 16/25] Current/Best: 18.05/ 19.89 GFLOPS | Progress: (16/20) | 7.55 s
-[Task 16/25] Current/Best: 9.85/ 21.48 GFLOPS | Progress: (20/20) | 9.81 s Done.
+[Task 16/25] Current/Best: 20.48/ 20.48 GFLOPS | Progress: (4/20) | 3.10 s
+[Task 16/25] Current/Best: 3.04/ 20.48 GFLOPS | Progress: (8/20) | 4.73 s
+[Task 16/25] Current/Best: 19.55/ 20.48 GFLOPS | Progress: (12/20) | 5.96 s
+[Task 16/25] Current/Best: 17.98/ 20.48 GFLOPS | Progress: (16/20) | 7.34 s
+[Task 16/25] Current/Best: 9.82/ 21.76 GFLOPS | Progress: (20/20) | 9.43 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 14.09/ 18.08 GFLOPS | Progress: (4/20) | 5.05 s
-[Task 17/25] Current/Best: 14.27/ 22.85 GFLOPS | Progress: (8/20) | 8.10 s
-[Task 17/25] Current/Best: 16.57/ 22.85 GFLOPS | Progress: (12/20) | 10.23 s
-[Task 17/25] Current/Best: 16.31/ 22.85 GFLOPS | Progress: (16/20) | 12.50 s
-[Task 17/25] Current/Best: 9.98/ 22.85 GFLOPS | Progress: (20/20) | 14.76 s Done.
+[Task 17/25] Current/Best: 14.24/ 18.19 GFLOPS | Progress: (4/20) | 4.84 s
+[Task 17/25] Current/Best: 14.35/ 22.93 GFLOPS | Progress: (8/20) | 7.74 s
+[Task 17/25] Current/Best: 16.72/ 22.93 GFLOPS | Progress: (12/20) | 9.80 s
+[Task 17/25] Current/Best: 16.36/ 22.93 GFLOPS | Progress: (16/20) | 11.95 s
+[Task 17/25] Current/Best: 10.00/ 22.93 GFLOPS | Progress: (20/20) | 14.12 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.48/ 16.58 GFLOPS | Progress: (4/20) | 4.06 s
-[Task 18/25] Current/Best: 10.53/ 17.23 GFLOPS | Progress: (8/20) | 7.92 s
-[Task 18/25] Current/Best: 18.96/ 18.96 GFLOPS | Progress: (12/20) | 9.91 s
-[Task 18/25] Current/Best: 9.71/ 18.96 GFLOPS | Progress: (16/20) | 13.89 s
-[Task 18/25] Current/Best: 20.41/ 20.41 GFLOPS | Progress: (20/20) | 15.46 s Done.
+[Task 18/25] Current/Best: 11.39/ 17.93 GFLOPS | Progress: (4/20) | 3.81 s
+[Task 18/25] Current/Best: 10.59/ 19.29 GFLOPS | Progress: (8/20) | 7.34 s
+[Task 18/25] Current/Best: 19.53/ 19.53 GFLOPS | Progress: (12/20) | 9.27 s
+[Task 18/25] Current/Best: 9.77/ 19.53 GFLOPS | Progress: (16/20) | 12.93 s
+[Task 18/25] Current/Best: 20.56/ 20.56 GFLOPS | Progress: (20/20) | 14.47 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 4.93/ 20.04 GFLOPS | Progress: (4/20) | 6.85 s
-[Task 19/25] Current/Best: 2.68/ 20.04 GFLOPS | Progress: (8/20) | 10.24 s
-[Task 19/25] Current/Best: 18.93/ 20.27 GFLOPS | Progress: (12/20) | 13.28 s
-[Task 19/25] Current/Best: 14.42/ 21.34 GFLOPS | Progress: (16/20) | 16.36 s
-[Task 19/25] Current/Best: 2.68/ 22.20 GFLOPS | Progress: (20/20) | 19.23 s Done.
+[Task 19/25] Current/Best: 6.58/ 20.13 GFLOPS | Progress: (4/20) | 6.28 s
+[Task 19/25] Current/Best: 2.69/ 20.13 GFLOPS | Progress: (8/20) | 9.54 s
+[Task 19/25] Current/Best: 19.13/ 20.81 GFLOPS | Progress: (12/20) | 12.35 s
+[Task 19/25] Current/Best: 15.12/ 21.24 GFLOPS | Progress: (16/20) | 15.18 s
+[Task 19/25] Current/Best: 2.69/ 22.59 GFLOPS | Progress: (20/20) | 18.00 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 9.06/ 14.89 GFLOPS | Progress: (4/20) | 3.59 s Done.
+[Task 20/25] Current/Best: 9.62/ 15.06 GFLOPS | Progress: (4/20) | 3.41 s Done.
Done.
-[Task 20/25] Current/Best: 10.00/ 14.89 GFLOPS | Progress: (8/20) | 7.17 s
-[Task 20/25] Current/Best: 2.32/ 16.32 GFLOPS | Progress: (12/20) | 11.25 s
-[Task 20/25] Current/Best: 12.37/ 16.32 GFLOPS | Progress: (16/20) | 15.23 s
-[Task 20/25] Current/Best: 12.94/ 21.50 GFLOPS | Progress: (20/20) | 17.40 s
+[Task 20/25] Current/Best: 10.26/ 15.06 GFLOPS | Progress: (8/20) | 6.92 s
+[Task 20/25] Current/Best: 2.32/ 16.31 GFLOPS | Progress: (12/20) | 10.93 s
+[Task 20/25] Current/Best: 12.35/ 16.31 GFLOPS | Progress: (16/20) | 14.79 s
+[Task 20/25] Current/Best: 13.25/ 21.69 GFLOPS | Progress: (20/20) | 16.91 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.36/ 17.32 GFLOPS | Progress: (4/20) | 3.52 s
-[Task 21/25] Current/Best: 13.71/ 17.32 GFLOPS | Progress: (8/20) | 5.21 s
-[Task 21/25] Current/Best: 1.60/ 17.32 GFLOPS | Progress: (12/20) | 7.46 s
-[Task 21/25] Current/Best: 17.70/ 17.70 GFLOPS | Progress: (16/20) | 11.19 s
-[Task 21/25] Current/Best: 4.44/ 17.70 GFLOPS | Progress: (20/20) | 19.06 s
+[Task 21/25] Current/Best: 6.38/ 17.53 GFLOPS | Progress: (4/20) | 3.35 s
+[Task 21/25] Current/Best: 14.56/ 17.53 GFLOPS | Progress: (8/20) | 4.98 s
+[Task 21/25] Current/Best: 1.61/ 17.53 GFLOPS | Progress: (12/20) | 7.21 s
+[Task 21/25] Current/Best: 18.19/ 18.19 GFLOPS | Progress: (16/20) | 10.75 s
+[Task 21/25] Current/Best: 4.45/ 18.19 GFLOPS | Progress: (20/20) | 18.00 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 2.69/ 16.72 GFLOPS | Progress: (4/20) | 2.89 s
-[Task 22/25] Current/Best: 9.10/ 20.45 GFLOPS | Progress: (8/20) | 4.93 s
-[Task 22/25] Current/Best: 19.32/ 20.45 GFLOPS | Progress: (12/20) | 7.42 s
-[Task 22/25] Current/Best: 14.97/ 20.45 GFLOPS | Progress: (16/20) | 9.60 s
-[Task 22/25] Current/Best: 14.71/ 20.45 GFLOPS | Progress: (20/20) | 11.44 s Done.
+[Task 22/25] Current/Best: 2.70/ 16.96 GFLOPS | Progress: (4/20) | 2.78 s
+[Task 22/25] Current/Best: 9.05/ 21.28 GFLOPS | Progress: (8/20) | 4.77 s
+[Task 22/25] Current/Best: 19.56/ 21.28 GFLOPS | Progress: (12/20) | 7.15 s
+[Task 22/25] Current/Best: 15.03/ 21.28 GFLOPS | Progress: (16/20) | 9.21 s
+[Task 22/25] Current/Best: 14.70/ 21.28 GFLOPS | Progress: (20/20) | 10.90 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 17.18/ 19.81 GFLOPS | Progress: (4/20) | 3.48 s
-[Task 23/25] Current/Best: 15.99/ 19.81 GFLOPS | Progress: (8/20) | 7.08 s
-[Task 23/25] Current/Best: 20.55/ 20.91 GFLOPS | Progress: (12/20) | 9.00 s
-[Task 23/25] Current/Best: 4.84/ 20.91 GFLOPS | Progress: (16/20) | 16.74 s
-[Task 23/25] Current/Best: 6.62/ 20.91 GFLOPS | Progress: (20/20) | 21.21 s Done.
+[Task 23/25] Current/Best: 17.28/ 20.07 GFLOPS | Progress: (4/20) | 3.37 s
+[Task 23/25] Current/Best: 15.19/ 20.07 GFLOPS | Progress: (8/20) | 6.76 s
+[Task 23/25] Current/Best: 20.70/ 21.07 GFLOPS | Progress: (12/20) | 8.61 s
+[Task 23/25] Current/Best: 5.77/ 21.07 GFLOPS | Progress: (16/20) | 15.98 s
+[Task 23/25] Current/Best: 7.40/ 21.07 GFLOPS | Progress: (20/20) | 20.29 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.43/ 8.43 GFLOPS | Progress: (4/20) | 11.99 s
-[Task 24/25] Current/Best: 1.70/ 8.43 GFLOPS | Progress: (8/20) | 23.11 s
-[Task 24/25] Current/Best: 2.26/ 8.43 GFLOPS | Progress: (12/20) | 34.82 s Done.
+[Task 24/25] Current/Best: 8.58/ 8.58 GFLOPS | Progress: (4/20) | 11.89 s
+[Task 24/25] Current/Best: 1.92/ 8.58 GFLOPS | Progress: (8/20) | 23.02 s
+[Task 24/25] Current/Best: 4.10/ 8.58 GFLOPS | Progress: (12/20) | 34.61 s Done.
-[Task 24/25] Current/Best: 6.84/ 8.57 GFLOPS | Progress: (16/20) | 40.82 s
-[Task 24/25] Current/Best: 2.81/ 8.68 GFLOPS | Progress: (20/20) | 47.07 s Done.
+[Task 24/25] Current/Best: 7.10/ 8.85 GFLOPS | Progress: (16/20) | 40.09 s
+[Task 24/25] Current/Best: 3.21/ 8.85 GFLOPS | Progress: (20/20) | 46.13 s Done.
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 1.51/ 2.55 GFLOPS | Progress: (4/20) | 11.78 s
-[Task 25/25] Current/Best: 4.55/ 6.86 GFLOPS | Progress: (8/20) | 23.24 s
-[Task 25/25] Current/Best: 5.48/ 6.86 GFLOPS | Progress: (12/20) | 34.84 s
-[Task 25/25] Current/Best: 5.52/ 8.30 GFLOPS | Progress: (16/20) | 36.82 s
-[Task 25/25] Current/Best: 2.53/ 8.30 GFLOPS | Progress: (20/20) | 47.58 s
+[Task 25/25] Current/Best: 1.54/ 2.85 GFLOPS | Progress: (4/20) | 11.69 s
+[Task 25/25] Current/Best: 5.50/ 7.39 GFLOPS | Progress: (8/20) | 23.03 s
+[Task 25/25] Current/Best: 5.79/ 7.39 GFLOPS | Progress: (12/20) | 34.39 s
+[Task 25/25] Current/Best: 5.70/ 9.11 GFLOPS | Progress: (16/20) | 36.18 s
+[Task 25/25] Current/Best: 2.83/ 9.11 GFLOPS | Progress: (20/20) | 46.87 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -981,8 +981,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 417.65380139999934, 'median': 417.4471308999955, 'std': 0.7647686871230543}
-unoptimized: {'mean': 504.8379361799995, 'median': 504.92999955000073, 'std': 0.4890225566327642}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 416.6093637100016, 'median': 415.2053465999984, 'std': 3.2585566053229775}
+unoptimized: {'mean': 501.0427243799995, 'median': 500.7832751500018, 'std': 1.0385531205208194}
</pre></div>
</div>
</div>
@@ -996,7 +996,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 55.101 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 28.988 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/57a45d9bef1af358191e7d50043e652c/autotvm_relay_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">autotvm_relay_x86.py</span></code></a></p>
diff --git a/docs/tutorial/cross_compilation_and_rpc.html b/docs/tutorial/cross_compilation_and_rpc.html
index 874c31389..4d1b42582 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -527,7 +527,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.264e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.255e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 9710d46a7..3479b9d61 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -484,7 +484,7 @@ we can schedule the following series of operations ending with <code class="code
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x847d4e0)), stage(b, placeholder(b, 0x1a6b7dc0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x15710cc0)), stage(b, placeholder(b, 0x156e8e30)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[ [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index d393f848f..a38b1c483 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>13:58.736</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:24.317</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,50 +336,50 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>10:55.101</p></td>
+<td><p>10:28.988</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:04.899</p></td>
+<td><p>01:00.955</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>00:58.655</p></td>
+<td><p>00:55.559</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:32.816</p></td>
+<td><p>00:31.846</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:25.088</p></td>
+<td><p>00:24.880</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:01.260</p></td>
+<td><p>00:01.182</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.739</p></td>
+<td><p>00:00.723</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></td>
-<td><p>00:00.170</p></td>
+<td><p>00:00.176</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
-<td><p>00:00.005</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
-<td><p>00:00.002</p></td>
+<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index f77798ca2..6ec465a2e 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -542,7 +542,7 @@ helper function to run a profile of the TVM generated code.</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000009
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
naive: 0.000007
</pre></div>
</div>
@@ -594,7 +594,7 @@ compile and run this new schedule with the parallel operation applied:</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-parallel: 0.000009
+parallel: 0.000006
</pre></div>
</div>
</div>
@@ -635,7 +635,7 @@ factor to be the number of threads on your CPU.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-vector: 0.000026
+vector: 0.000025
@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, [(stride: int32*n: int32)], [], type="auto"),
@@ -668,10 +668,10 @@ vector: 0.000026
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 9.224419998190569e-06 1.0
- naive 6.6517e-06 0.721096827909481
-parallel 9.4665e-06 1.026243384609213
- vector 2.5711e-05 2.787275514888024
+ numpy 8.222219998970103e-06 1.0
+ naive 6.6622e-06 0.8102677866603536
+parallel 6.0359e-06 0.7340961444422606
+ vector 2.4501300000000002e-05 2.9798886435864014
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -987,7 +987,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.020310
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019648
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1030,7 +1030,7 @@ optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-none: 3.606828
+none: 3.348520
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1097,7 +1097,7 @@ schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-blocking: 0.337259
+blocking: 0.328356
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1158,7 +1158,7 @@ already cache friendly from our previous optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-vectorization: 0.355468
+vectorization: 0.360574
@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], []),
@@ -1215,7 +1215,7 @@ more cache friendly.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-loop permutation: 0.147487
+loop permutation: 0.125586
@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], []),
@@ -1293,7 +1293,7 @@ optimized schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-array packing: 0.113672
+array packing: 0.108727
@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], []),
@@ -1369,7 +1369,7 @@ to `C</cite> when all the block results are ready.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-block caching: 0.115491
+block caching: 0.110984
@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], []),
@@ -1438,7 +1438,7 @@ of thread-level parallelization.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-parallelization: 0.150194
+parallelization: 0.147097
@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], []),
@@ -1500,13 +1500,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.6068279385000004 1.0
- blocking 0.3372588413 0.09350566399356951
- vectorization 0.3554675789 0.09855407160005285
-loop permutation 0.1474866838 0.04089096744141791
- array packing 0.11367241349999999 0.031515895806017796
- block caching 0.11549136509999999 0.032020203644100166
- parallelization 0.150194414 0.041641690859936756
+ none 3.3485195541 1.0
+ blocking 0.3283564355 0.09806018158023096
+ vectorization 0.36057413809999994 0.10768165819981702
+loop permutation 0.12558638090000002 0.0375050462961249
+ array packing 0.1087265983 0.0324700502844228
+ block caching 0.11098382700000001 0.03314414779633256
+ parallelization 0.147096591 0.043928843365985945
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1538,7 +1538,7 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.899 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.955 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-tensor-expr-get-started-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/40a01cffb015a67aaec0fad7e27cf80d/tensor_expr_get_started.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tensor_expr_get_started.py</span></code></a></p>