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 2022/09/16 22:51:51 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@e037ae49928592afdfa8d2c27198fc68592f9528)
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 0b55d43a84 deploying docs (apache/tvm@e037ae49928592afdfa8d2c27198fc68592f9528)
0b55d43a84 is described below
commit 0b55d43a848756b168bfaa39ddc73c386d15a0dc
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri Sep 16 22:51:45 2022 +0000
deploying docs (apache/tvm@e037ae49928592afdfa8d2c27198fc68592f9528)
---
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1027 ++++++++++++++------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 394 ++++++--
.../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 | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 11 +-
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 | 47 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 14 +-
docs/how_to/compile_models/from_pytorch.html | 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 | 77 +-
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 | 37 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1027 ++++++++++++++------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 394 ++++++--
.../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 | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
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 | 7 +-
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 | 28 +-
docs/tutorial/tensor_expr_get_started.html | 43 +-
123 files changed, 2922 insertions(+), 1587 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 6df1306753..0a8147bffc 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -315,7 +315,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 3.739 seconds)
+ **Total running time of the script:** ( 1 minutes 8.226 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_keras.rst.txt b/docs/_sources/how_to/compile_models/from_keras.rst.txt
index d6841bde26..450643400b 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -228,7 +228,7 @@ Look up prediction top 1 index in 1000 class synset.
.. code-block:: none
Relay top-1 id: 285, class name: Egyptian cat
-
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 956ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 961ms/step
Keras top-1 id: 285, class name: Egyptian cat
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index c1493b7a4d..0f397de659 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.zip6af49eb7-2eb6-46f4-afb2-64fc96795a78 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip68faadb9-bd2f-43bf-9eb6-b38b0759d537 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 0cd38ef958..82151f0636 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -116,7 +116,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 62.7MB/s]
30%|##9 | 12.3M/41.5M [00:00<00:00, 43.3MB/s]
40%|#### | 16.8M/41.5M [00:00<00:00, 27.0MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 35.4MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 41.3MB/s]
96%|#########5| 39.7M/41.5M [00:00<00:00, 50.5MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 43.3MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 52.0MB/s]
27%|##7 | 11.3M/41.5M [00:00<00:00, 47.6MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 37.0MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 45.0MB/s]
65%|######5 | 27.1M/41.5M [00:00<00:00, 46.5MB/s]
87%|########6 | 36.0M/41.5M [00:00<00:00, 60.5MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 49.9MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index ac7f183c3c..2c93e8c005 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]
45%|####5 | 20.2M/44.7M [00:00<00:00, 212MB/s]
94%|#########4| 42.1M/44.7M [00:00<00:00, 222MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 213MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
10%|# | 4.59M/44.7M [00:00<00:00, 48.1MB/s]
21%|## | 9.17M/44.7M [00:00<00:00, 43.4MB/s]
69%|######8 | 30.7M/44.7M [00:00<00:00, 122MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 121MB/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 be173c3c75..f53575e083 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -416,7 +416,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.852 seconds)
+ **Total running time of the script:** ( 1 minutes 5.017 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 86a9ea7407..b88255c9e4 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
=================
-**05:13.640** total execution time for **how_to_compile_models** files:
+**05:16.648** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:05.852 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:08.226 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:03.739 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:05.017 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:40.250 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:40.200 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:28.998 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:28.877 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:26.685 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:27.580 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.383 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.317 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.449 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:23.050 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:21.013 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.984 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.806 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.971 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.464 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.426 | 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 0551bb623d..2c1fe778fe 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -434,7 +434,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.4739 16.3781 17.2318 16.0584 0.3946
+ 16.1065 16.0002 17.0928 15.9543 0.3298
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 eb1b5a2961..ba31ea736f 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]
1%|1 | 2.19M/170M [00:00<00:07, 22.7MB/s]
3%|3 | 5.56M/170M [00:00<00:05, 30.0MB/s]
5%|4 | 8.43M/170M [00:00<00:06, 25.7MB/s]
6%|6 | 10.9M/170M [00:00<00:06, 25.1MB/s]
9%|9 | 15.4M/170M [00:00<00:05, 30.9MB/s]
11%|# | 18.4M/170M [00:00<00:07, 20.6MB/s]
12%|#2 | 21.2M/170M [00:00<00:06, 22.6MB/s]
14%|#4 | 24.4M/170M [00:01<00:06, 24.8MB/s]
16%|#6 | 27.6M/170M [00:01<00:05, 27.1MB/s]
18%|#8 | 31.2M/170M [00:01<00:04, 29.8MB/s]
21%|##1 | 36.0M/170M [00:01<00:04, 35.0MB/s]
23%|##3 | 39.5M/170M [00:01<00:04, 32.9MB/s]
25%|##5 | 42.8M/170M [00:01<00:04, 29.3MB/s]
27%|##6 | 45.7M/170M [00:01<00:04, 27.3MB/s]
29%|##8 | 48.5M/170M [00:01<00:04, 26.1MB/s]
30%|### | 51.0M/170M [00:01<00:05, 24.9MB/s]
31%|###1 | 53.5M/170M [00:02<00:05, 22.9MB/
s]
33%|###2 | 55.9M/170M [00:02<00:05, 23.4MB/s]
34%|###4 | 58.3M/170M [00:02<00:04, 23.9MB/s]
36%|###5 | 60.6M/170M [00:02<00:05, 22.6MB/s]
37%|###6 | 62.8M/170M [00:02<00:05, 22.0MB/s]
38%|###8 | 65.2M/170M [00:02<00:04, 22.9MB/s]
40%|###9 | 67.4M/170M [00:02<00:04, 22.5MB/s]
41%|#### | 69.6M/170M [00:02<00:04, 22.4MB/s]
42%|####2 | 72.1M/170M [00:02<00:04, 23.5MB/s]
44%|####3 | 74.5M/170M [00:03<00:04, 23.7MB/s]
45%|####5 | 76.8M/170M [00:03<00:04, 22.3MB/s]
46%|####6 | 78.9M/170M [00:03<00:04, 22.4MB/s]
48%|####7 | 81.2M/170M [00:03<00:04, 22.7MB/s]
49%|####9 | 83.4M/170M [00:03<00:04, 22.4MB/s]
50%|##### | 85.5M/170M [00:03<00:03, 22.2MB/s]
52%|#####1 | 87.6M/170M [00:03<00:04, 20.4MB/s]
53%|#####2 | 89.6M/170M [00:03<00:04, 19.1MB/s]
54%|#####3 | 91.6M/170M [00:03<00:04, 19.4MB/s]
55%|#####5 | 93.7M/170M [00:04<00:
03, 20.2MB/s]
56%|#####6 | 95.7M/170M [00:04<00:03, 20.4MB/s]
58%|#####7 | 98.2M/170M [00:04<00:03, 21.9MB/s]
59%|#####9 | 100M/170M [00:04<00:03, 22.4MB/s]
60%|###### | 103M/170M [00:04<00:03, 22.1MB/s]
62%|######1 | 105M/170M [00:04<00:03, 21.4MB/s]
63%|######2 | 107M/170M [00:04<00:03, 20.1MB/s]
64%|######4 | 109M/170M [00:04<00:03, 19.8MB/s]
65%|######5 | 111M/170M [00:04<00:03, 20.4MB/s]
66%|######6 | 113M/170M [00:05<00:02, 20.0MB/s]
68%|######7 | 115M/170M [00:05<00:02, 19.8MB/s]
69%|######8 | 117M/170M [00:05<00:02, 19.7MB/s]
70%|######9 | 119M/170M [00:05<00:02, 19.8MB/s]
71%|#######1 | 121M/170M [00:05<00:02, 21.8MB/s]
73%|#######2 | 124M/170M [00:05<00:02, 22.6MB/s]
74%|#######4 | 126M/170M [00:05<00:02, 19.8MB/s]
75%|#######5 | 128M/170M [00:05<00:02, 20.2MB/s]
77%|#######6 | 130M/170M [00:05<00:02, 20.3MB/s]
78%|#######8 | 133M/170M [00:06<00:01,
22.5MB/s]
80%|######## | 136M/170M [00:06<00:01, 27.6MB/s]
83%|########2 | 141M/170M [00:06<00:00, 32.4MB/s]
85%|########4 | 144M/170M [00:06<00:00, 31.9MB/s]
87%|########7 | 148M/170M [00:06<00:00, 35.1MB/s]
89%|########9 | 151M/170M [00:06<00:00, 29.6MB/s]
91%|######### | 154M/170M [00:06<00:00, 23.0MB/s]
93%|#########3| 158M/170M [00:06<00:00, 26.4MB/s]
95%|#########4| 161M/170M [00:07<00:00, 24.7MB/s]
97%|#########7| 165M/170M [00:07<00:00, 28.3MB/s]
99%|#########8| 168M/170M [00:07<00:00, 17.8MB/s]
100%|##########| 170M/170M [00:07<00:00, 23.1MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
2%|2 | 3.88M/170M [00:00<00:04, 40.6MB/s]
5%|4 | 8.14M/170M [00:00<00:03, 42.9MB/s]
13%|#3 | 22.2M/170M [00:00<00:01, 90.4MB/s]
25%|##5 | 43.2M/170M [00:00<00:00, 142MB/s]
39%|###9 | 66.3M/170M [00:00<00:00, 177MB/s]
49%|####8 | 83.1M/170M [00:00<00:00, 168MB/s]
60%|#####9 | 102M/170M [00:00<00:00, 176MB/s]
71%|####### | 120M/170M [00:00<00:00, 183MB/s]
81%|########1 | 138M/170M [00:00<00:00, 177MB/s]
94%|#########3| 159M/170M [00:01<00:00, 190MB/s]
100%|##########| 170M/170M [00:01<00:00, 164MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -288,7 +288,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 11.278 seconds)
+ **Total running time of the script:** ( 3 minutes 2.203 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 8a51bac484..d7786c634e 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]
23%|##3 | 3.14M/13.6M [00:00<00:00, 32.9MB/s]
47%|####6 | 6.33M/13.6M [00:00<00:00, 33.2MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 59.4MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 179MB/s]
@@ -405,7 +405,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.4300 90.3387 92.9575 90.1677 0.3304
+ 90.4479 90.2844 96.0755 90.0569 0.6561
@@ -454,7 +454,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 11.583 seconds)
+ **Total running time of the script:** ( 1 minutes 10.674 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 9e134d365f..4344d35726 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -432,7 +432,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.0103 119.8265 127.9406 119.0140 1.1466
+ 120.8376 120.7808 126.3305 119.9395 0.6892
@@ -469,7 +469,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 1.045 seconds)
+ **Total running time of the script:** ( 2 minutes 1.067 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 9096e5b67e..bbcc2da8ab 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -253,7 +253,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 27.804 seconds)
+ **Total running time of the script:** ( 1 minutes 24.407 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 dadef4c8b5..c9715110ba 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]
4%|4 | 5615/132723 [00:00<00:02, 56146.97KB/s]
10%|9 | 13144/132723 [00:00<00:01, 67404.34KB/s]
16%|#5 | 20679/132723 [00:00<00:01, 71029.30KB/s]
21%|##1 | 28223/132723 [00:00<00:01, 72765.68KB/s]
27%|##6 | 35813/132723 [00:00<00:01, 73894.04KB/s]
33%|###2 | 43345/132723 [00:00<00:01, 74364.99KB/s]
38%|###8 | 50850/132723 [00:00<00:01, 74586.08KB/s]
44%|####3 | 58309/132723 [00:00<00:01, 73202.23KB/s]
50%|####9 | 65794/132723 [00:00<00:00, 73708.38KB/s]
55%|#####5 | 73257/132723 [00:01<00:00, 73987.07KB/s]
61%|###### | 80715/132723 [00:01<00:00, 74165.59KB/s]
67%|######6 | 88270/132723 [00:01<00:00, 74583.08KB/s]
72%|#######2 | 95745/132723 [00:01<00:00, 74631.57KB/s]
78%|#######7 | 103210/132723 [00:01<00:00, 74597.70KB/s]
83%|########3 | 110695/132723 [00:01<00:00, 74669.77KB/s]
89%|########9
| 118189/132723 [00:01<00:00, 74749.15KB/s]
95%|#########4| 125667/132723 [00:01<00:00, 74755.17KB/s]
100%|##########| 132723/132723 [00:01<00:00, 73681.81KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|4 | 5357/132723 [00:00<00:02, 53566.48KB/s]
10%|# | 13641/132723 [00:00<00:01, 70779.22KB/s]
16%|#6 | 21886/132723 [00:00<00:01, 76103.81KB/s]
23%|##2 | 30206/132723 [00:00<00:01, 78902.68KB/s]
29%|##8 | 38419/132723 [00:00<00:01, 80064.43KB/s]
35%|###5 | 46749/132723 [00:00<00:01, 81159.68KB/s]
41%|####1 | 54865/132723 [00:00<00:00, 79255.25KB/s]
48%|####7 | 63162/132723 [00:00<00:00, 80417.31KB/s]
54%|#####3 | 71335/132723 [00:00<00:00, 80821.14KB/s]
60%|#####9 | 79620/132723 [00:01<00:00, 81440.03KB/s]
66%|######6 | 87849/132723 [00:01<00:00, 81695.58KB/s]
72%|#######2 | 96181/132723 [00:01<00:00, 82185.69KB/s]
79%|#######8 | 104453/132723 [00:01<00:00, 82345.77KB/s]
85%|########4 | 112748/132723 [00:01<00:00, 82526.77KB/s]
91%|#########1| 121043/132723 [00:01<00:00, 82652.66KB/s]
97%|########
#7| 129398/132723 [00:01<00:00, 82920.03KB/s]
100%|##########| 132723/132723 [00:01<00:00, 80457.86KB/s]
@@ -234,7 +234,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 41.660 seconds)
+ **Total running time of the script:** ( 2 minutes 37.475 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 f267ecf469..7bf3465f3d 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**11:50.869** total execution time for **how_to_deploy_models** files:
+**11:32.085** 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``) | 03:11.278 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:02.203 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:41.660 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:37.475 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:01.045 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:01.067 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:27.804 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:24.407 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:11.583 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:10.674 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:30.935 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:30.283 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:23.459 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:23.187 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:23.098 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.782 | 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 40b2a2a3be..38e0435c33 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -472,7 +472,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip7eb617de-6f45-41f8-86c1-2d9b84746fb9 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipc1796861-b587-4024-a9f3-655dead537e7 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 0d0b7bad8e..c8063c24c0 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
=================
-**00:41.930** total execution time for **how_to_extend_tvm** files:
+**00:41.783** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:38.691 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:38.655 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.268 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.195 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.963 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.926 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 9ff58728b7..3523928875 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: 7015us [7015us] (46.03%; 46.03%)
- FoldScaleAxis: 8223us [7us] (53.97%; 53.97%)
- FoldConstant: 8217us [1790us] (53.92%; 99.92%)
- InferType: 6427us [6427us] (42.18%; 78.22%)
+ InferType: 6634us [6634us] (45.73%; 45.73%)
+ FoldScaleAxis: 7874us [5us] (54.27%; 54.27%)
+ FoldConstant: 7869us [1631us] (54.24%; 99.94%)
+ InferType: 6238us [6238us] (43.00%; 79.27%)
@@ -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: 6511us [6511us] (44.38%; 44.38%)
- FoldScaleAxis: 8159us [5us] (55.62%; 55.62%)
- FoldConstant: 8154us [1761us] (55.58%; 99.93%)
- InferType: 6393us [6393us] (43.58%; 78.41%)
+ InferType: 6309us [6309us] (44.52%; 44.52%)
+ FoldScaleAxis: 7862us [5us] (55.48%; 55.48%)
+ FoldConstant: 7858us [1642us] (55.45%; 99.94%)
+ InferType: 6216us [6216us] (43.86%; 79.11%)
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 02e079ecff..c6a20ada62 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.182425 ms
+ Convolution: 41.674519 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 da9b9340e2..4ee313bfda 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -671,7 +671,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 7.178219 ms
+ conv2d with tensor core: 7.042579 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 7d24bdbf16..128fa8e143 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: 0.019142
- Baseline: 3.404615
+ Numpy running time: 0.019217
+ Baseline: 3.252773
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.322602
+ Opt1: 0.301739
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.351764
+ Opt2: 0.341203
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.120582
+ Opt3: 0.117069
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.111994
+ Opt4: 0.110063
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111022
+ Opt5: 0.111081
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147406
+ Opt6: 0.147204
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 78a12305a2..afaefb1ba0 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:35.003** total execution time for **how_to_optimize_operators** files:
+**00:34.179** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.822 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.953 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.192 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.223 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:00.989 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.003 | 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 27d2b719f2..810ece1db6 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
=================
-**06:26.936** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:37.063** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:25.032 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:28.920 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:24.803 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:23.130 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:57.856 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:56.970 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:21.180 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:30.580 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:09.199 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.806 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.866 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.658 | 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 0fbe33180e..0a15548f8d 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -240,185 +240,439 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 8;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
allocate(conv2d_nchw: Pointer(local float32), float32, [28]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [28], [], scope="local")[0] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[6] = 0f32
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [49], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[13] = 0f32
conv2d_nchw_1[14] = 0f32
- conv2d_nchw_1[15] = 0f32
- conv2d_nchw_1[16] = 0f32
- conv2d_nchw_1[17] = 0f32
- conv2d_nchw_1[18] = 0f32
- conv2d_nchw_1[19] = 0f32
- conv2d_nchw_1[20] = 0f32
conv2d_nchw_1[21] = 0f32
+ conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[15] = 0f32
conv2d_nchw_1[22] = 0f32
+ conv2d_nchw_1[2] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[16] = 0f32
conv2d_nchw_1[23] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[17] = 0f32
conv2d_nchw_1[24] = 0f32
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[18] = 0f32
conv2d_nchw_1[25] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[19] = 0f32
conv2d_nchw_1[26] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ conv2d_nchw_1[20] = 0f32
conv2d_nchw_1[27] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- let cse_var_2: int32 = (rc.outer.outer*392)
- let cse_var_1: int32 = (rc.outer.outer*72)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((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" = 112;
- 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" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 12), 81)) && (floormod((threadIdx.x_1 + 12), 81) < 72)) && (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" = 112;
- 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" = 112;
- if @tir.likely((threadIdx.x_1 < 88), dtype=bool) {
- 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_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 112), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 224), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 336), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 448), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 560), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 672), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 784), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 896), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1120), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1232), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1344), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1456), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1568), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1680), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1792), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1904), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2128), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2240), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2352), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2464), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2576), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2688), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2800), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2912), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 193536)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3136), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3248)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3248), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3360), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3472)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3472), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3584), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3696)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3696), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3808), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3920), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4144)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4144), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4256), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4368)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4368), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4480), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 4592)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4592), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- }
- for (rc.outer.inner: int32, 0, 8) {
- for (ry.outer.inner: int32, 0, 3) {
- for (ff.outer.inner: int32, 0, 4) {
- let cse_var_9: int32 = (ff.outer.inner*7)
- let cse_var_8: int32 = (cse_var_9 + 6)
- let cse_var_7: int32 = (cse_var_9 + 5)
- let cse_var_6: int32 = (cse_var_9 + 4)
- let cse_var_5: int32 = (cse_var_9 + 3)
- let cse_var_4: int32 = (cse_var_9 + 2)
- let cse_var_3: int32 = (cse_var_9 + 1)
+ for (rc.outer.outer: int32, 0, 16) {
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_4: int32 = (rc.outer.outer*1568)
+ let cse_var_3: int32 = (ry.outer.outer*7)
+ let cse_var_2: int32 = (rc.outer.outer*288)
+ let cse_var_1: int32 = (ry.outer.outer*3)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 56), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 168), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 280), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 392), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 384)], 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 560), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 616), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 672), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 728)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 728), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 784), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 840)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 840), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 896), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 952)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 952), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 776)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1064)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1064), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1120), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1176), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1232), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1288)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1288), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1344)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1344), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1400)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1400), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1456)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1456), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1512)] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 1168)], 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1568), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1624)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1624), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1680)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1680), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1736)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1736), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1792)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1792), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1848)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1848), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1904)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1904), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1960), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 56), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 112), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 168), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 280), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 336), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 448), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 504), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 560), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 616), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + 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*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 728), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 784), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 840), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 896), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 952), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 1008), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1064), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 1120), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 1232), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1288), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + 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*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1400), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 1456), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1512), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 1568), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1624)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1624), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 1680), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1736)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1736), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 1792), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1848)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1848), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 1904), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + 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*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2072)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2072), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 2128), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2184)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2184), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 2240), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2296)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2296), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2408)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2408), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2464), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2520)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2520), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2576), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2632)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2632), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2744), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2800), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2856)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2856), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2912), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2968)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2968), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 48), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3024), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 16)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ }
+ for (rc.outer.inner: int32, 0, 2) {
+ for (yy.outer.inner: int32, 0, 7) {
+ let cse_var_7: int32 = (yy.outer.inner + 7)
+ let cse_var_6: int32 = (yy.outer.inner + 21)
+ let cse_var_5: int32 = (yy.outer.inner + 14)
{
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[(((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48))]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 768)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1536)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2304)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 769)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1537)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2305)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 770)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1538)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2306)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 3)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 771)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1539)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2307)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 4)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 772)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1540)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2308)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 5)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 773)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1541)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2309)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 6)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 774)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1542)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2310)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 7)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 775)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1543)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2311)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 8)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 776)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1544)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2312)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 9)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 777)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1545)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2313)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 10)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 778)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1546)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2314)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 11)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 779)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1547)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2315)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 12)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 780)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1548)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2316)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 13)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 781)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1549)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2317)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 14)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 782)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1550)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2318)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 15)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 783)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1551)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2319)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 16)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 784)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1552)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2320)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 17)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 785)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1553)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2321)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 18)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 786)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1554)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2322)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 19)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 787)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1555)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2323)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 20)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 788)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1556)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2324)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 21)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 789)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1557)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2325)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 22)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 790)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1558)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2326)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 23)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 791)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1559)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2327)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 24)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 792)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1560)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2328)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 25)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 793)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1561)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2329)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 26)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 794)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1562)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2330)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 27)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 795)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1563)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2331)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 28)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 796)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1564)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2332)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 29)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 797)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1565)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2333)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 30)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 798)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1566)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2334)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 31)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 799)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1567)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2335)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 32)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 800)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1568)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2336)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 33)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 801)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1569)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2337)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 34)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 802)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1570)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2338)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 35)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 803)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1571)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2339)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 36)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 804)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1572)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2340)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 37)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 805)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1573)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2341)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 38)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 806)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1574)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2342)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 39)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 807)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1575)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2343)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 40)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 808)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1576)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2344)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 41)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 809)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1577)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2345)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 42)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 810)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1578)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2346)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 43)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 811)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1579)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2347)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 44)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 812)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1580)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2348)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 45)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 813)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1581)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2349)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 46)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 814)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1582)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2350)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 47)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 815)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1583)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2351)]))
}
}
}
}
}
}
- for (i1.inner: int32, 0, 4) {
- for (i2.inner: int32, 0, 7) {
- compute[(((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias[(((blockIdx.x*64) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
- }
+ for (i2.inner: int32, 0, 7) {
+ compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7)) + 392)] = max((conv2d_nchw_1[(i2.inner + 7)] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 8)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7)) + 784)] = max((conv2d_nchw_1[(i2.inner + 14)] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7)) + 1176)] = max((conv2d_nchw_1[(i2.inner + 21)] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 24)]), 0f32)
}
}
}
@@ -473,7 +727,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.412 ms
+ Execution time of this operator: 0.392 ms
@@ -522,9 +776,9 @@ 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=16)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=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=4)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=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)
@@ -533,19 +787,19 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=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=16)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=4)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
@@ -570,14 +824,14 @@ 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=112)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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=112)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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", 64)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -595,125 +849,338 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ 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[28];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[4608];
+ __shared__ float pad_temp_shared[2016];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
conv2d_nchw[14] = 0.000000e+00f;
- conv2d_nchw[15] = 0.000000e+00f;
- conv2d_nchw[16] = 0.000000e+00f;
- conv2d_nchw[17] = 0.000000e+00f;
- conv2d_nchw[18] = 0.000000e+00f;
- conv2d_nchw[19] = 0.000000e+00f;
- conv2d_nchw[20] = 0.000000e+00f;
conv2d_nchw[21] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[15] = 0.000000e+00f;
conv2d_nchw[22] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[16] = 0.000000e+00f;
conv2d_nchw[23] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[17] = 0.000000e+00f;
conv2d_nchw[24] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[18] = 0.000000e+00f;
conv2d_nchw[25] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[19] = 0.000000e+00f;
conv2d_nchw[26] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ conv2d_nchw[20] = 0.000000e+00f;
conv2d_nchw[27] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((9 <= ((((int)threadIdx.x) + 12) % 81)) && (((((int)threadIdx.x) + 12) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 88) {
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 112) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 336) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 560) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1232) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1456) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1568) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1680) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1904) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2128) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2240) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2352) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2464) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2576) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2688) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2800) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2912) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 193536)];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3136) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3248)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3248) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3360) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3472)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3472) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3584) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 3696)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3696) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3808) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3920) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 4144)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4144) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4256) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4368)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4368) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4480) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 16) {
- kernel_shared[(((int)threadIdx.x) + 4592)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4592) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 56) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- for (int ff_outer_inner = 0; ff_outer_inner < 4; ++ff_outer_inner) {
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 56) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 112) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 168) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 280) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 336) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 448) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 504)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 384)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 560) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 616) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 672) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 728)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 728) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 840)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 840) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 896) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 952)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 952) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 776)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1064)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1064) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1120) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1232)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1232) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1288)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1288) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1344) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1400)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1400) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1456)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1456) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1512)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 1168)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1624)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1624) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1680)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1680) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1736)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1736) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1848)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1848) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1904)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1904) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 56) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 168) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 280) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 504) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 616) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 728) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 840) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 952) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1008) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1064) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1288) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1400) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1512) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1624)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1624) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1736)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1736) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1848)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1848) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 2072)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2072) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2184)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2184) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2296)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2296) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2408)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2408) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2520)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2520) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2576) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2632)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2632) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2800) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2856)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2856) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2968)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2968) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 48) {
+ kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3024) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 144)];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
+ for (int yy_outer_inner = 0; yy_outer_inner < 7; ++yy_outer_inner) {
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48))]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[(((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 768)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[(((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1536)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[(((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2304)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 769)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1537)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2305)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 770)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1538)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2306)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 771)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1539)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2307)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 772)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1540)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2308)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 773)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1541)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2309)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 774)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1542)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2310)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 775)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1543)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2311)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 776)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1544)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2312)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 777)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1545)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2313)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 778)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1546)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2314)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 779)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1547)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2315)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 780)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1548)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2316)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 781)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1549)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2317)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 782)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1550)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2318)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 783)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1551)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2319)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 784)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1552)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2320)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 785)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1553)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2321)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 786)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1554)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2322)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 787)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1555)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2323)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 788)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1556)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2324)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 789)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1557)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2325)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 790)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1558)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2326)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 791)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1559)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2327)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 792)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1560)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2328)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 793)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1561)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2329)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 794)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1562)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2330)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 795)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1563)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2331)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 796)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1564)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2332)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 797)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1565)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2333)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 798)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1566)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2334)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 799)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1567)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2335)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 800)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1568)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2336)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 801)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1569)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2337)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 802)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1570)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2338)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 803)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1571)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2339)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 804)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1572)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2340)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 805)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1573)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2341)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 806)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1574)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2342)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 807)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1575)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2343)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 808)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1576)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2344)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 809)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1577)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2345)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 810)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1578)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2346)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 811)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1579)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2347)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 812)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1580)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2348)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 813)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1581)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2349)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 814)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1582)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2350)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 815)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1583)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2351)]));
}
}
}
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[(((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 64) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
- }
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 392)] = max((conv2d_nchw[(i2_inner + 7)] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 8)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 784)] = max((conv2d_nchw[(i2_inner + 14)] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 1176)] = max((conv2d_nchw[(i2_inner + 21)] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 24)]), 0.000000e+00f);
}
}
@@ -775,7 +1242,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 25.032 seconds)
+ **Total running time of the script:** ( 3 minutes 28.920 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 db8782c13b..39f8bd8ac9 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -643,7 +643,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.1969 8.1998 8.2006 8.1903 0.0047
+ 8.2603 8.2608 8.2631 8.2572 0.0024
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 2a6ad11da3..5c2db05e3c 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -662,7 +662,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 759.9851 759.6576 760.9176 759.3800 0.6691
+ 753.6400 754.2528 754.2978 752.3693 0.8987
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 24.803 seconds)
+ **Total running time of the script:** ( 1 minutes 23.130 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 7410fd352f..e69edb9fcd 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
@@ -397,103 +397,339 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 64) {
- let cse_var_1: int32 = ((i.outer.inner*1024) + (i.inner.init*16))
- {
- compute_5: Buffer(compute_4, float32, [2048], [])[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[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])) {
- for (i.inner: int32, 0, 64) {
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_2: int32 = ((i.outer.inner*1024) + (i.inner*16))
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
+ let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ let cse_var_1: int32 = (i.outer.inner*64)
+ {
+ compute_5: Buffer(compute_4, float32, [512], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
+ compute_5[(cse_var_1 + 16)] = 0f32
+ compute_5[(cse_var_1 + 17)] = 0f32
+ compute_5[(cse_var_1 + 18)] = 0f32
+ compute_5[(cse_var_1 + 19)] = 0f32
+ compute_5[(cse_var_1 + 20)] = 0f32
+ compute_5[(cse_var_1 + 21)] = 0f32
+ compute_5[(cse_var_1 + 22)] = 0f32
+ compute_5[(cse_var_1 + 23)] = 0f32
+ compute_5[(cse_var_1 + 24)] = 0f32
+ compute_5[(cse_var_1 + 25)] = 0f32
+ compute_5[(cse_var_1 + 26)] = 0f32
+ compute_5[(cse_var_1 + 27)] = 0f32
+ compute_5[(cse_var_1 + 28)] = 0f32
+ compute_5[(cse_var_1 + 29)] = 0f32
+ compute_5[(cse_var_1 + 30)] = 0f32
+ compute_5[(cse_var_1 + 31)] = 0f32
+ compute_5[(cse_var_1 + 32)] = 0f32
+ compute_5[(cse_var_1 + 33)] = 0f32
+ compute_5[(cse_var_1 + 34)] = 0f32
+ compute_5[(cse_var_1 + 35)] = 0f32
+ compute_5[(cse_var_1 + 36)] = 0f32
+ compute_5[(cse_var_1 + 37)] = 0f32
+ compute_5[(cse_var_1 + 38)] = 0f32
+ compute_5[(cse_var_1 + 39)] = 0f32
+ compute_5[(cse_var_1 + 40)] = 0f32
+ compute_5[(cse_var_1 + 41)] = 0f32
+ compute_5[(cse_var_1 + 42)] = 0f32
+ compute_5[(cse_var_1 + 43)] = 0f32
+ compute_5[(cse_var_1 + 44)] = 0f32
+ compute_5[(cse_var_1 + 45)] = 0f32
+ compute_5[(cse_var_1 + 46)] = 0f32
+ compute_5[(cse_var_1 + 47)] = 0f32
+ compute_5[(cse_var_1 + 48)] = 0f32
+ compute_5[(cse_var_1 + 49)] = 0f32
+ compute_5[(cse_var_1 + 50)] = 0f32
+ compute_5[(cse_var_1 + 51)] = 0f32
+ compute_5[(cse_var_1 + 52)] = 0f32
+ compute_5[(cse_var_1 + 53)] = 0f32
+ compute_5[(cse_var_1 + 54)] = 0f32
+ compute_5[(cse_var_1 + 55)] = 0f32
+ compute_5[(cse_var_1 + 56)] = 0f32
+ compute_5[(cse_var_1 + 57)] = 0f32
+ compute_5[(cse_var_1 + 58)] = 0f32
+ compute_5[(cse_var_1 + 59)] = 0f32
+ compute_5[(cse_var_1 + 60)] = 0f32
+ compute_5[(cse_var_1 + 61)] = 0f32
+ compute_5[(cse_var_1 + 62)] = 0f32
+ compute_5[(cse_var_1 + 63)] = 0f32
+ for (elem_idx: int32, 0, (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[((placeholder_3[cse_var_2]*16) + (elem_idx*16))]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_3: int32 = (cse_var_1 + 1)
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_4: int32 = (cse_var_1 + 2)
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_5: int32 = (cse_var_1 + 3)
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_6: int32 = (cse_var_1 + 4)
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_7: int32 = (cse_var_1 + 5)
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_8: int32 = (cse_var_1 + 6)
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_9: int32 = (cse_var_1 + 7)
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_10: int32 = (cse_var_1 + 8)
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_11: int32 = (cse_var_1 + 9)
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_12: int32 = (cse_var_1 + 10)
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_13: int32 = (cse_var_1 + 11)
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_14: int32 = (cse_var_1 + 12)
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_15: int32 = (cse_var_1 + 13)
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_16: int32 = (cse_var_1 + 14)
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_17: int32 = (cse_var_1 + 15)
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_18: int32 = (cse_var_1 + 16)
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_2]*16) + (elem_idx*16))]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_19: int32 = (cse_var_1 + 17)
+ compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 1)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_20: int32 = (cse_var_1 + 18)
+ compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 2)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_21: int32 = (cse_var_1 + 19)
+ compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 3)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_22: int32 = (cse_var_1 + 20)
+ compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 4)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_23: int32 = (cse_var_1 + 21)
+ compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 5)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_24: int32 = (cse_var_1 + 22)
+ compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 6)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_25: int32 = (cse_var_1 + 23)
+ compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 7)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_26: int32 = (cse_var_1 + 24)
+ compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 8)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_27: int32 = (cse_var_1 + 25)
+ compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 9)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_28: int32 = (cse_var_1 + 26)
+ compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 10)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_29: int32 = (cse_var_1 + 27)
+ compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 11)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_30: int32 = (cse_var_1 + 28)
+ compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 12)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_31: int32 = (cse_var_1 + 29)
+ compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 13)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_32: int32 = (cse_var_1 + 30)
+ compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 14)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_33: int32 = (cse_var_1 + 31)
+ compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 15)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_34: int32 = (cse_var_1 + 32)
+ compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[((placeholder_3[cse_var_2]*16) + (elem_idx*16))]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_35: int32 = (cse_var_1 + 33)
+ compute_5[cse_var_35] = (compute_5[cse_var_35] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 1)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_36: int32 = (cse_var_1 + 34)
+ compute_5[cse_var_36] = (compute_5[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 2)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_37: int32 = (cse_var_1 + 35)
+ compute_5[cse_var_37] = (compute_5[cse_var_37] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 3)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_38: int32 = (cse_var_1 + 36)
+ compute_5[cse_var_38] = (compute_5[cse_var_38] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 4)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_39: int32 = (cse_var_1 + 37)
+ compute_5[cse_var_39] = (compute_5[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 5)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_40: int32 = (cse_var_1 + 38)
+ compute_5[cse_var_40] = (compute_5[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 6)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_41: int32 = (cse_var_1 + 39)
+ compute_5[cse_var_41] = (compute_5[cse_var_41] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 7)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_42: int32 = (cse_var_1 + 40)
+ compute_5[cse_var_42] = (compute_5[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 8)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_43: int32 = (cse_var_1 + 41)
+ compute_5[cse_var_43] = (compute_5[cse_var_43] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 9)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_44: int32 = (cse_var_1 + 42)
+ compute_5[cse_var_44] = (compute_5[cse_var_44] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 10)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_45: int32 = (cse_var_1 + 43)
+ compute_5[cse_var_45] = (compute_5[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 11)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_46: int32 = (cse_var_1 + 44)
+ compute_5[cse_var_46] = (compute_5[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 12)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_47: int32 = (cse_var_1 + 45)
+ compute_5[cse_var_47] = (compute_5[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 13)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_48: int32 = (cse_var_1 + 46)
+ compute_5[cse_var_48] = (compute_5[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 14)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_49: int32 = (cse_var_1 + 47)
+ compute_5[cse_var_49] = (compute_5[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 15)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_50: int32 = (cse_var_1 + 48)
+ compute_5[cse_var_50] = (compute_5[cse_var_50] + (placeholder_1[((placeholder_3[cse_var_2]*16) + (elem_idx*16))]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_3: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 1)
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_51: int32 = (cse_var_1 + 49)
+ compute_5[cse_var_51] = (compute_5[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 1)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_4: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 2)
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_52: int32 = (cse_var_1 + 50)
+ compute_5[cse_var_52] = (compute_5[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 2)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_5: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 3)
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_53: int32 = (cse_var_1 + 51)
+ compute_5[cse_var_53] = (compute_5[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 3)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_6: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 4)
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_54: int32 = (cse_var_1 + 52)
+ compute_5[cse_var_54] = (compute_5[cse_var_54] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 4)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_7: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 5)
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_55: int32 = (cse_var_1 + 53)
+ compute_5[cse_var_55] = (compute_5[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 5)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_8: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 6)
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_56: int32 = (cse_var_1 + 54)
+ compute_5[cse_var_56] = (compute_5[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 6)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_9: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 7)
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_57: int32 = (cse_var_1 + 55)
+ compute_5[cse_var_57] = (compute_5[cse_var_57] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 7)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_10: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 8)
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_58: int32 = (cse_var_1 + 56)
+ compute_5[cse_var_58] = (compute_5[cse_var_58] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 8)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_11: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 9)
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_59: int32 = (cse_var_1 + 57)
+ compute_5[cse_var_59] = (compute_5[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 9)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_12: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 10)
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_60: int32 = (cse_var_1 + 58)
+ compute_5[cse_var_60] = (compute_5[cse_var_60] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 10)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_13: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 11)
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_61: int32 = (cse_var_1 + 59)
+ compute_5[cse_var_61] = (compute_5[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 11)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_14: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 12)
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_62: int32 = (cse_var_1 + 60)
+ compute_5[cse_var_62] = (compute_5[cse_var_62] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 12)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_15: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 13)
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_63: int32 = (cse_var_1 + 61)
+ compute_5[cse_var_63] = (compute_5[cse_var_63] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 13)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_16: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 14)
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_64: int32 = (cse_var_1 + 62)
+ compute_5[cse_var_64] = (compute_5[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 14)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_17: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 15)
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_65: int32 = (cse_var_1 + 63)
+ compute_5[cse_var_65] = (compute_5[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 15)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- let cse_var_18: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*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_66: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute[ramp(cse_var_66, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_66, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -549,7 +785,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.834 ms
+ Execution time of this operator: 3.060 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 9bf28e2e62..4ae5f9176f 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
@@ -5,12 +5,12 @@
Computation times
=================
-**00:45.606** total execution time for **how_to_tune_with_autotvm** files:
+**00:47.320** 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``) | 00:45.570 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:47.282 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.022 | 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 |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 3e122cbff7..0b849584c2 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: 80.73/80.73 result: MeasureResult(costs=(0.0028675722571428574,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9275405406951904, timestamp=1663361933.6527922) [('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: 0.00/80.73 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 80.83/80.83 result: MeasureResult(costs=(0.002864093714285714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8326270580291748, timestamp=1663364523.1702492) [('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: 0.00/80.83 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: 258.79/258.79 result: MeasureResult(costs=(0.0008945659329608938,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7172877788543701, timestamp=1663361934.577884) [('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: 0.00/258.79 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 259.99/259.99 result: MeasureResult(costs=(0.0008904298674033151,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4686949253082275, timestamp=1663364524.089343) [('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: 0.00/259.99 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: 0.00/258.79 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/259.99 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: 0.00/258.79 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/259.99 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: 5.45/258.79 result: MeasureResult(costs=(0.04248450725,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8850071430206299, timestamp=1663361939.2082422) [('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: 3.35/258.79 result: MeasureResult(costs=(0.06910582175,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.617069482803345, timestamp=1663361940.44951) [('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: 0.00/258.79 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 5.27/259.99 result: MeasureResult(costs=(0.04395220375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8667688369750977, timestamp=1663364528.6761594) [('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: 3.34/259.99 result: MeasureResult(costs=(0.06935163675,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.5678369998931885, timestamp=1663364529.915958) [('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: 0.00/259.99 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: 26.01/258.79 result: MeasureResult(costs=(0.008900514083333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1445872783660889, timestamp=1663361951.3518827) [('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: 0.00/258.79 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 28.24/259.99 result: MeasureResult(costs=(0.008197034642857143,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2898228168487549, timestamp=1663364540.9808195) [('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: 0.00/259.99 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: 0.00/258.79 result: Traceback (most recent call last):
+ No: 20 GFLOPS: 0.00/259.99 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: 0.001295
+ Time cost of this operator: 0.001298
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 82a31f134b..e536a12386 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -327,10 +327,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.6 98.709 (1, 2, 10, 10, 3) 2 1 [310.6]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.11 0.988 (1, 6, 10, 10) 1 1 [3.11]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.952 0.302 (1, 1, 10, 10, 3) 1 1 [0.952]
- Total_time - 314.662 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 308.3 98.724 (1, 2, 10, 10, 3) 2 1 [308.3]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.03 0.97 (1, 6, 10, 10) 1 1 [3.03]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.955 0.306 (1, 1, 10, 10, 3) 1 1 [0.955]
+ Total_time - 312.285 - - - - -
@@ -394,10 +394,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 150.8 98.21 (1, 6, 10, 10, 1) 2 1 [150.8]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.773 1.155 (1, 6, 10, 10) 1 1 [1.773]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.976 0.635 (1, 1, 10, 10, 3) 1 1 [0.976]
- Total_time - 153.549 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 215.4 98.481 (1, 1, 10, 10, 6) 2 1 [215.4]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.342 1.071 (1, 6, 10, 10) 1 1 [2.342]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.981 0.448 (1, 3, 10, 10, 1) 1 1 [0.981]
+ Total_time - 218.723 - - - - -
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 be75e8d7f4..1661447f10 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/tmpxklxu0qs/images/random'
+ '/tmp/tmp_xr3u1rf/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpxklxu0qs/images/target contains 8144 images
- /tmp/tmpxklxu0qs/images/random contains 5000 images
+ /tmp/tmp_xr3u1rf/images/target contains 8144 images
+ /tmp/tmp_xr3u1rf/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2161 - accuracy: 0.9242 - val_loss: 0.1244 - val_accuracy: 0.9596 - 47s/epoch - 143ms/step
+ 328/328 - 47s - loss: 0.2197 - accuracy: 0.9246 - val_loss: 0.1452 - val_accuracy: 0.9562 - 47s/epoch - 143ms/step
Epoch 2/3
- 328/328 - 44s - loss: 0.0984 - accuracy: 0.9625 - val_loss: 0.1315 - val_accuracy: 0.9573 - 44s/epoch - 133ms/step
+ 328/328 - 43s - loss: 0.0923 - accuracy: 0.9645 - val_loss: 0.1146 - val_accuracy: 0.9630 - 43s/epoch - 132ms/step
Epoch 3/3
- 328/328 - 44s - loss: 0.0633 - accuracy: 0.9760 - val_loss: 0.1014 - val_accuracy: 0.9656 - 44s/epoch - 133ms/step
+ 328/328 - 43s - loss: 0.0686 - accuracy: 0.9753 - val_loss: 0.1057 - val_accuracy: 0.9671 - 43s/epoch - 132ms/step
- <keras.callbacks.History object at 0x7f989fe99c50>
+ <keras.callbacks.History object at 0x7fcc28f0ff90>
@@ -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 36.005 seconds)
+ **Total running time of the script:** ( 4 minutes 25.413 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 4e48edae3b..2f3ade4029 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
=================
-**05:29.401** total execution time for **how_to_work_with_microtvm** files:
+**05:19.263** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:36.005 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:25.413 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.701 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.374 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.434 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.112 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.259 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.362 | 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 8c3ad62562..2b535a2c43 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
=================
-**00:39.701** total execution time for **how_to_work_with_relay** files:
+**00:43.462** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.340 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.786 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:07.088 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.137 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.266 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.531 | 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 579361e0ff..7e11a03120 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 0x7f9840862950>
+ <function my_cuda_math_rule at 0x7fcba642a680>
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 c55e80a9f5..aed7652e69 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
=================
-**00:04.018** total execution time for **how_to_work_with_schedules** files:
+**00:07.677** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.998 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.359 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.847 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.064 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.506 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.542 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.481 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.529 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.102 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.099 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.042 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.027 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.016 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.015 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index 3e6d07acfa..dbd4e38954 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/tmp01wk34o2/input0.cc'\nsource_filename = \"/tmp/tmp01wk34o2/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/tmpw0vyrezu/input0.cc'\nsource_filename = \"/tmp/tmpw0vyrezu/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 49b156a28d..79f5caac48 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:21.987** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:21.982** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.981 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.975 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 7a9208f608..1aa72c2287 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -289,7 +289,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 23.70s!
+ resnet18_v1 inference graph built in 23.07s!
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 c73f1a32f6..6eebc0d683 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -333,7 +333,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 16.73s!
+ yolov3-tiny inference graph built in 16.46s!
diff --git a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
index 05467a1fe4..961910d36d 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
=================
-**01:33.683** total execution time for **topic_vta_tutorials_frontend** files:
+**01:31.924** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.857 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.788 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.826 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.135 | 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 74ff4694aa..41918eac4a 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
=================
-**00:02.974** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.040** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.624 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.643 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.349 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.397 | 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 cf03ae5831..8642b2c251 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
=================
-**00:00.640** total execution time for **topic_vta_tutorials** files:
+**00:00.744** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.351 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.403 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.288 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.341 | 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 4f1ab6b2cf..6716075441 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -203,13 +203,6 @@ trials, we can load the best schedule from the log file and apply it.
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
- .T*E
-
-
@@ -333,7 +326,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.972 ms
+ Execution time of this operator: 93.509 ms
@@ -451,7 +444,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 9.998 seconds)
+ **Total running time of the script:** ( 1 minutes 12.891 seconds)
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 792b9f9b67..8def051a7c 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: 10.70/10.70 result: MeasureResult(costs=(0.025083385200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5382473468780518, timestamp=1663360668.9268305) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.93/10.70 result: MeasureResult(costs=(0.0917467508,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6064765453338623, timestamp=1663360670.5603414) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.65/11.65 result: MeasureResult(costs=(0.023040918400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5842595100402832, timestamp=1663360671.6458154) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.77/11.65 result: MeasureResult(costs=(0.1516779954,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5544826984405518, timestamp=1663360674.241922) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.62/11.65 result: MeasureResult(costs=(0.07417769240000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3270087242126465, timestamp=1663360675.6968253) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.79/11.65 result: MeasureResult(costs=(0.150218111,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5316474437713623, timestamp=1663360678.8133185) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.85/11.65 result: MeasureResult(costs=(0.31656924760000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.191319704055786, timestamp=1663360684.6076777) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.46/11.65 result: MeasureResult(costs=(0.025653009400000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5560874938964844, timestamp=1663360685.183841) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.62/11.65 result: MeasureResult(costs=(0.16537150939999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7618985176086426, timestamp=1663360688.0655835) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.66/11.65 result: MeasureResult(costs=(0.1007671628,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.73246431350708, timestamp=1663360689.8412776) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 10.80/10.80 result: MeasureResult(costs=(0.0248582544,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.533137321472168, timestamp=1663363264.1401277) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.87/10.80 result: MeasureResult(costs=(0.09344741259999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6491446495056152, timestamp=1663363265.8013742) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.79/11.79 result: MeasureResult(costs=(0.022762087,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5608391761779785, timestamp=1663363266.8792121) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.87/11.79 result: MeasureResult(costs=(0.14323182240000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4019856452941895, timestamp=1663363269.8742616) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.33/11.79 result: MeasureResult(costs=(0.08062546620000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.434044361114502, timestamp=1663363271.4348295) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.82/11.79 result: MeasureResult(costs=(0.147721219,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4914937019348145, timestamp=1663363274.5062902) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.86/11.79 result: MeasureResult(costs=(0.31339139239999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.134791374206543, timestamp=1663363279.6860335) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.51/11.79 result: MeasureResult(costs=(0.025543893800000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5579173564910889, timestamp=1663363280.256034) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.92/11.79 result: MeasureResult(costs=(0.1396194626,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3373494148254395, timestamp=1663363282.7134404) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.79/11.79 result: MeasureResult(costs=(0.096203392,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6488864421844482, timestamp=1663363284.419518) [('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 4491452ce6..59c710bebe 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -320,7 +320,7 @@ standard deviation.
.. code-block:: none
- {'mean': 518.1210708800063, 'median': 517.8918785499718, 'std': 2.360912984889522}
+ {'mean': 509.63054053000286, 'median': 510.2050166499964, 'std': 1.692568446876928}
@@ -554,30 +554,30 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.49/ 17.49 GFLOPS | Progress: (4/20) | 6.53 s
[Task 1/25] Current/Best: 6.09/ 17.49 GFLOPS | Progress: (8/20) | 9.65 s
[Task 1/25] Current/Best: 11.17/ 21.53 GFLOPS | Progress: (12/20) | 12.20 s
[Task 1/25] Current/Best: 16.37/ 22.14 GFLOPS | Progress: (16/20) | 13.92 s
[Task 1/25] Current/Best: 11.34/ 23.27 GFLOPS | Progress: (20/20) | 15.71 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.16/ 12.16 GFLOPS | Progress: (4/20) | 4.01 s
[Task 2/25] Current/Best: 12.44/ 18.28 GFLOPS | Progress: (8/20) | 5.33 s
[Task 2/25] Current/Best: 20.86/ 20.86 GFLOPS | Progress: (12/20) | 6.70 s
[Task 2/25] Current/Best: 11.18/ 20.86 GFLOPS | Progress: (16/20) | 8.00 s
[Task 2/25] Current/Best: 16.69/ 20.86 GFLOPS | Progress: (20/20) | 9.63 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/ 10.05 GFLOPS | Progress: (4/20) | 5.95 s
[Task 3/25] Current/Best: 15.13/ 16.85 GFLOPS | Progress: (8/20) | 7.92 s
[Task 3/25] Current/Best: 14.95/ 16.85 GFLOPS | Progress: (12/20) | 9.67 s
[Task 3/25] Current/Best: 6.82/ 22.84 GFLOPS | Progress: (16/20) | 11.69 s
[Task 3/25] Current/Best: 11.00/ 22.84 GFLOPS | Progress: (20/20) | 16.35 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.05/ 18.90 GFLOPS | Progress: (4/20) | 2.50 s
[Task 4/25] Current/Best: 6.43/ 18.90 GFLOPS | Progress: (8/20) | 7.36 s
[Task 4/25] Current/Best: 20.69/ 20.69 GFLOPS | Progress: (12/20) | 12.39 s
[Task 4/25] Current/Best: 15.81/ 20.69 GFLOPS | Progress: (16/20) | 14.87 s
[Task 4/25] Current/Best: 12.59/ 20.69 GFLOPS | Progress: (20/20) | 16.89 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.08/ 9.74 GFLOPS | Progress: (4/20) | 2.69 s
[Task 5/25] Current/Best: 11.32/ 11.38 GFLOPS | Progress: (8/20) | 4.78 s
[Task 5/25] Current/Best: 9.64/ 17.86 GFLOPS | Progress: (12/20) | 8.09 s
[Task 5/25] Current/Best: 11.19/ 22.18 GFLOPS | Progress: (16/20) | 9.55 s
[Task 5/25] Current/Best: 11.83/ 22.18 GFLOPS | Progress: (20/20) | 11.48 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.05/ 20.00 GFLOPS | Progress: (4/20) | 4.27 s
[Task 6/25] Current/Best: 18.78/ 20.00 GFLOPS | Progress: (8/20) | 6.05 s
[Task 6/25] Current/Best: 13.23/ 20.00 GFLOPS | Progress: (12/20) | 8.08 s
[Task 6/25] Current/Best: 19.38/ 20.00 GFLOPS | Progress: (16/20) | 10.39 s
[Task 6/25] Current/Best: 3.70/ 20.00 GFLOPS | Progress: (20/20) | 13.02 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 9.76/ 12.00 GFLOPS | Progress: (4/20) | 3.72 s
[Task 7/25] Current/Best: 18.88/ 19.35 GFLOPS | Progress: (8/20) | 5.29 s
[Task 7/25] Current/Best: 16.01/ 19.52 GFLOPS | Progress: (12/20) | 7.24 s
[Task 7/25] Current/Best: 12.12/ 19.53 GFLOPS | Progress: (16/20) | 9.35 s
[Task 7/25] Current/Best: 6.10/ 20.38 GFLOPS | Progress: (20/20) | 11.88 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.15/ 13.94 GFLOPS | Progress: (4/20) | 2.98 s
[Task 8/25] Current/Best: 9.02/ 13.94 GFLOPS | Progress: (8/20) | 8.34 s
[Task 8/25] Current/Best: 12.81/ 13.94 GFLOPS | Progress: (12/20) | 15.01 s
[Task 8/25] Current/Best: 19.13/ 19.13 GFLOPS | Progress: (16/20) | 17.19 s
[Task 8/25] Current/Best: 18.58/ 19.13 GFLOPS | Progress: (20/20) | 24.55 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.28/ 14.28 GFLOPS | Progress: (4/20) | 12.03 s
[Task 9/25] Current/Best: 22.36/ 22.36 GFLOPS | Progress: (8/20) | 13.87 s
[Task 9/25] Current/Best: 7.97/ 22.36 GFLOPS | Progress: (12/20) | 16.49 s
[Task 9/25] Current/Best: 17.69/ 22.36 GFLOPS | Progress: (16/20) | 19.29 s
[Task 9/25] Current/Best: 8.95/ 22.36 GFLOPS | Progress: (20/20) | 28.22 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.15/ 18.15 GFLOPS | Progress: (4/20) | 2.65 s
[Task 10/25] Current/Best: 15.73/ 18.15 GFLOPS | Progress: (8/20) | 4.33 s
[Task 10/25] Current/Best: 11.40/ 18.81 GFLOPS | Progress: (12/20) | 5.92 s
[Task 10/25] Current/Best: 19.01/ 20.07 GFLOPS | Progress: (16/20) | 7.05 s
[Task 10/25] Current/Best: 8.44/ 20.07 GFLOPS | Progress: (20/20
) | 8.61 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 10.84/ 18.07 GFLOPS | Progress: (4/20) | 3.54 s
[Task 11/25] Current/Best: 14.22/ 18.07 GFLOPS | Progress: (8/20) | 6.42 s
[Task 11/25] Current/Best: 15.93/ 18.07 GFLOPS | Progress: (12/20) | 8.57 s
[Task 11/25] Current/Best: 11.80/ 20.63 GFLOPS | Progress: (16/20) | 11.52 s
[Task 11/25] Current/Best: 18.07/ 20.63 GFLOPS | Progress: (20/20) | 13.71 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.77/ 18.11 GFLOPS | Progress: (4/20) | 5.91 s
[Task 12/25] Current/Best: 4.96/ 18.11 GFLOPS | Progress: (8/20) | 9.95 s
[Task 12/25] Current/Best: 19.05/ 19.05 GFLOPS | Progress: (12/20) | 12.00 s
[Task 12/25] Current/Best: 14.57/ 19.05 GFLOPS | Progress: (16/20) | 14.99 s
[Task 12/25] Current/Best: 15.16/ 19.05 GFLOPS | Progress: (20/20) | 16.99 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.61/ 17.27 GFLOPS | Progress: (4/20) | 3.87 s
[Task 13/25] Current/Best: 15.52/ 20.59 GFLOPS | Progress: (8/20) | 6.52 s
[Task 13/25] Current/Best: 18.65/ 21.20 GFLOPS | Progress: (12/20) | 9.60 s
[Task 13/25] Current/Best: 12.15/ 21.20 GFLOPS | Progress: (16/20) | 13.09 s
[Task 13/25] Current/Best: 17.71/ 21.20 GFLOPS | Progress: (20/20) | 15.51 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 12.12/ 13.07 GFLOPS | Progress: (4/20) | 3.51 s
[Task 14/25] Current/Best: 6.07/ 13.11 GFLOPS | Progress: (8/20) | 5.77 s
[Task 14/25] Current/Best: 19.21/ 19.21 GFLOPS | Progress: (12/20) | 8.50 s
[Task 14/25] Current/Best: 15.63/ 19.21 GFLOPS | Progress: (16/20) | 10.21 s Done.
-
[Task 14/25] Current/Best: 17.02/ 19.21 GFLOPS | Progress: (20/20) | 11.98 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 14.78/ 16.95 GFLOPS | Progress: (4/20) | 2.82 s
[Task 15/25] Current/Best: 12.56/ 17.80 GFLOPS | Progress: (8/20) | 4.15 s
[Task 15/25] Current/Best: 9.67/ 20.61 GFLOPS | Progress: (12/20) | 6.45 s
[Task 15/25] Current/Best: 19.69/ 20.61 GFLOPS | Progress: (16/20) | 9.64 s
[Task 15/25] Current/Best: 9.25/ 20.61 GFLOPS | Progress: (20/20) | 10.68 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 17.70/ 17.70 GFLOPS | Progress: (4/20) | 3.07 s
[Task 16/25] Current/Best: 3.03/ 17.70 GFLOPS | Progress: (8/20) | 4.70 s
[Task 16/25] Current/Best: 18.52/ 19.40 GFLOPS | Progress: (12/20) | 5.94 s
[Task 16/25] Current/Best: 17.60/ 19.40 GFLOPS | Progress: (16/20) |
7.35 s
[Task 16/25] Current/Best: 9.93/ 19.76 GFLOPS | Progress: (20/20) | 9.55 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.40/ 16.11 GFLOPS | Progress: (4/20) | 4.93 s
[Task 17/25] Current/Best: 12.76/ 22.73 GFLOPS | Progress: (8/20) | 7.78 s
[Task 17/25] Current/Best: 16.39/ 22.73 GFLOPS | Progress: (12/20) | 9.90 s
[Task 17/25] Current/Best: 16.45/ 22.73 GFLOPS | Progress: (16/20) | 12.16 s
[Task 17/25] Current/Best: 9.97/ 22.73 GFLOPS | Progress: (20/20) | 14.37 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 10.33/ 17.24 GFLOPS | Progress: (4/20) | 3.93 s
[Task 18/25] Current/Best: 10.60/ 18.46 GFLOPS | Progress: (8/20) | 7.71 s
[Task 18/25] Current/Best: 18.61/ 18.61 GFLOPS | Progress: (12/20) | 9.69 s
[Task 18/25] Current/Best: 10.04/ 18.61 GFLOPS | Progress: (16/20) | 13.63 s
[Task 18/25] Current/Best: 20.48/ 20.48 GFLOPS | Progress: (20/20) | 15.18 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.12/ 19.61 GFLOPS | Progress: (4/20) | 6.33 s
[Task 19/25] Current/Best: 2.69/ 19.61 GFLOPS | Progress: (8/20) | 9.67 s
[Task 19/25] Current/Best: 18.10/ 20.22 GFLOPS | Progress: (12/20) | 12.70 s
[Task 19/25] Current/Best: 13.39/ 20.74 GFLOPS | Progress: (16/20) | 15.73 s
[Task 19/25] Current/Best: 2.69/ 21.94 GFLOPS | Progress: (20/20) | 18.59 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.96/ 14.97 GFLOPS | Progress: (4/20) | 3.43 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.40/ 17.40 GFLOPS | Progress: (4/20) | 6.46 s
[Task 1/25] Current/Best: 6.02/ 17.40 GFLOPS | Progress: (8/20) | 9.55 s
[Task 1/25] Current/Best: 11.19/ 21.96 GFLOPS | Progress: (12/20) | 12.07 s
[Task 1/25] Current/Best: 16.42/ 22.14 GFLOPS | Progress: (16/20) | 13.77 s
[Task 1/25] Current/Best: 11.33/ 23.61 GFLOPS | Progress: (20/20) | 15.57 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.05/ 12.45 GFLOPS | Progress: (4/20) | 3.97 s
[Task 2/25] Current/Best: 12.41/ 18.48 GFLOPS | Progress: (8/20) | 5.28 s
[Task 2/25] Current/Best: 20.33/ 20.33 GFLOPS | Progress: (12/20) | 6.60 s
[Task 2/25] Current/Best: 10.68/ 20.33 GFLOPS | Progress: (16/20) | 7.92 s
[Task 2/25] Current/Best: 16.62/ 20.33 GFLOPS | Progress: (20/20) | 9.56 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.19 GFLOPS | Progress: (4/20) | 5.89 s
[Task 3/25] Current/Best: 15.24/ 16.86 GFLOPS | Progress: (8/20) | 7.83 s
[Task 3/25] Current/Best: 14.99/ 16.86 GFLOPS | Progress: (12/20) | 9.57 s
[Task 3/25] Current/Best: 6.83/ 23.28 GFLOPS | Progress: (16/20) | 11.57 s
[Task 3/25] Current/Best: 11.08/ 23.28 GFLOPS | Progress: (20/20) | 16.23 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 8.97/ 18.79 GFLOPS | Progress: (4/20) | 2.45 s
[Task 4/25] Current/Best: 6.42/ 18.79 GFLOPS | Progress: (8/20) | 7.22 s
[Task 4/25] Current/Best: 21.33/ 21.33 GFLOPS | Progress: (12/20) | 12.14 s
[Task 4/25] Current/Best: 16.15/ 21.33 GFLOPS | Progress: (16/20) | 14.62 s
[Task 4/25] Current/Best: 12.90/ 21.33 GFLOPS | Progress: (20/20) | 16.68 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.44/ 10.05 GFLOPS | Progress: (4/20) | 2.62 s
[Task 5/25] Current/Best: 11.69/ 11.69 GFLOPS | Progress: (8/20) | 4.69 s
[Task 5/25] Current/Best: 10.05/ 17.95 GFLOPS | Progress: (12/20) | 7.90 s
[Task 5/25] Current/Best: 11.68/ 22.10 GFLOPS | Progress: (16/20) | 9.37 s
[Task 5/25] Current/Best: 11.95/ 22.10 GFLOPS | Progress: (20/20) | 11.28 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 11.91/ 19.91 GFLOPS | Progress: (4/20) | 4.15 s
[Task 6/25] Current/Best: 18.91/ 19.91 GFLOPS | Progress: (8/20) | 5.95 s
[Task 6/25] Current/Best: 13.16/ 19.91 GFLOPS | Progress: (12/20) | 7.95 s
[Task 6/25] Current/Best: 19.25/ 19.91 GFLOPS | Progress: (16/20) | 10.20 s
[Task 6/25] Current/Best: 3.74/ 19.91 GFLOPS | Progress: (20/20) | 12.80 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 9.77/ 12.12 GFLOPS | Progress: (4/20) | 3.74 s
[Task 7/25] Current/Best: 19.30/ 20.09 GFLOPS | Progress: (8/20) | 5.29 s
[Task 7/25] Current/Best: 16.00/ 20.09 GFLOPS | Progress: (12/20) | 7.23 s
[Task 7/25] Current/Best: 12.18/ 20.09 GFLOPS | Progress: (16/20) | 9.32 s
[Task 7/25] Current/Best: 6.13/ 20.23 GFLOPS | Progress: (20/20) | 11.83 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.50/ 14.10 GFLOPS | Progress: (4/20) | 2.91 s
[Task 8/25] Current/Best: 9.58/ 14.10 GFLOPS | Progress: (8/20) | 8.05 s
[Task 8/25] Current/Best: 13.20/ 14.10 GFLOPS | Progress: (12/20) | 14.66 s
[Task 8/25] Current/Best: 19.09/ 19.09 GFLOPS | Progress: (16/20) | 16.78 s
[Task 8/25] Current/Best: 19.22/ 19.22 GFLOPS | Progress: (20/20) | 23.88 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.39/ 14.39 GFLOPS | Progress: (4/20) | 11.98 s
[Task 9/25] Current/Best: 23.08/ 23.08 GFLOPS | Progress: (8/20) | 13.80 s
[Task 9/25] Current/Best: 7.81/ 23.08 GFLOPS | Progress: (12/20) | 16.39 s
[Task 9/25] Current/Best: 17.83/ 23.08 GFLOPS | Progress: (16/20) | 19.27 s
[Task 9/25] Current/Best: 8.95/ 23.08 GFLOPS | Progress: (20/20) | 28.04 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.25/ 18.25 GFLOPS | Progress: (4/20) | 2.60 s
[Task 10/25] Current/Best: 15.33/ 18.25 GFLOPS | Progress: (8/20) | 4.25 s
[Task 10/25] Current/Best: 11.54/ 18.87 GFLOPS | Progress: (12/20) | 5.82 s
[Task 10/25] Current/Best: 19.02/ 20.31 GFLOPS | Progress: (16/20) | 6.92 s
[Task 10/25] Current/Best: 8.62/ 20.31 GFLOPS | Progress: (20/20
) | 8.46 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 10.89/ 18.15 GFLOPS | Progress: (4/20) | 3.48 s
[Task 11/25] Current/Best: 14.78/ 18.15 GFLOPS | Progress: (8/20) | 6.34 s
[Task 11/25] Current/Best: 15.90/ 18.15 GFLOPS | Progress: (12/20) | 8.44 s
[Task 11/25] Current/Best: 11.86/ 20.62 GFLOPS | Progress: (16/20) | 11.45 s
[Task 11/25] Current/Best: 17.93/ 20.62 GFLOPS | Progress: (20/20) | 13.58 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.80/ 17.89 GFLOPS | Progress: (4/20) | 5.75 s
[Task 12/25] Current/Best: 5.13/ 17.89 GFLOPS | Progress: (8/20) | 9.72 s
[Task 12/25] Current/Best: 18.79/ 18.79 GFLOPS | Progress: (12/20) | 11.72 s
[Task 12/25] Current/Best: 15.17/ 18.79 GFLOPS | Progress: (16/20) | 14.70 s
[Task 12/25] Current/Best: 15.06/ 18.79 GFLOPS | Progress: (20/20) | 16.69 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.39/ 17.23 GFLOPS | Progress: (4/20) | 3.85 s
[Task 13/25] Current/Best: 15.14/ 20.66 GFLOPS | Progress: (8/20) | 6.49 s
[Task 13/25] Current/Best: 18.64/ 21.70 GFLOPS | Progress: (12/20) | 9.53 s
[Task 13/25] Current/Best: 12.27/ 21.70 GFLOPS | Progress: (16/20) | 12.99 s
[Task 13/25] Current/Best: 17.66/ 21.70 GFLOPS | Progress: (20/20) | 15.35 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 12.08/ 13.33 GFLOPS | Progress: (4/20) | 3.45 s
[Task 14/25] Current/Best: 6.10/ 13.33 GFLOPS | Progress: (8/20) | 5.63 s
[Task 14/25] Current/Best: 19.60/ 19.60 GFLOPS | Progress: (12/20) | 8.31 s
[Task 14/25] Current/Best: 16.28/ 19.60 GFLOPS | Progress: (16/20) | 9.99 s Done.
+
[Task 14/25] Current/Best: 16.91/ 19.60 GFLOPS | Progress: (20/20) | 11.75 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 15.61/ 17.10 GFLOPS | Progress: (4/20) | 2.76 s
[Task 15/25] Current/Best: 12.66/ 17.72 GFLOPS | Progress: (8/20) | 4.09 s
[Task 15/25] Current/Best: 9.96/ 20.73 GFLOPS | Progress: (12/20) | 6.37 s
[Task 15/25] Current/Best: 20.02/ 20.73 GFLOPS | Progress: (16/20) | 9.82 s
[Task 15/25] Current/Best: 9.49/ 20.73 GFLOPS | Progress: (20/20) | 10.85 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 19.25/ 19.25 GFLOPS | Progress: (4/20) | 3.09 s
[Task 16/25] Current/Best: 3.02/ 19.25 GFLOPS | Progress: (8/20) | 4.73 s
[Task 16/25] Current/Best: 18.36/ 19.25 GFLOPS | Progress: (12/20) | 5.95 s
[Task 16/25] Current/Best: 18.48/ 19.25 GFLOPS | Progress: (16/20) |
7.34 s
[Task 16/25] Current/Best: 9.96/ 21.18 GFLOPS | Progress: (20/20) | 9.50 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.95/ 16.14 GFLOPS | Progress: (4/20) | 4.87 s
[Task 17/25] Current/Best: 12.73/ 22.86 GFLOPS | Progress: (8/20) | 7.80 s
[Task 17/25] Current/Best: 16.51/ 22.86 GFLOPS | Progress: (12/20) | 9.91 s
[Task 17/25] Current/Best: 16.44/ 22.86 GFLOPS | Progress: (16/20) | 12.14 s
[Task 17/25] Current/Best: 9.96/ 22.86 GFLOPS | Progress: (20/20) | 14.32 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 10.19/ 16.04 GFLOPS | Progress: (4/20) | 3.90 s
[Task 18/25] Current/Best: 10.57/ 18.55 GFLOPS | Progress: (8/20) | 7.63 s
[Task 18/25] Current/Best: 18.87/ 18.87 GFLOPS | Progress: (12/20) | 9.61 s
[Task 18/25] Current/Best: 10.04/ 18.87 GFLOPS | Progress: (16/20) | 13.54 s
[Task 18/25] Current/Best: 20.34/ 20.34 GFLOPS | Progress: (20/20) | 15.11 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.08/ 19.47 GFLOPS | Progress: (4/20) | 6.15 s
[Task 19/25] Current/Best: 2.69/ 19.47 GFLOPS | Progress: (8/20) | 9.46 s
[Task 19/25] Current/Best: 17.82/ 20.64 GFLOPS | Progress: (12/20) | 12.44 s
[Task 19/25] Current/Best: 13.48/ 20.64 GFLOPS | Progress: (16/20) | 15.50 s
[Task 19/25] Current/Best: 2.69/ 21.90 GFLOPS | Progress: (20/20) | 18.32 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.01/ 15.28 GFLOPS | Progress: (4/20) | 3.37 s Done.
Done.
-
[Task 20/25] Current/Best: 9.72/ 14.97 GFLOPS | Progress: (8/20) | 6.87 s
[Task 20/25] Current/Best: 2.32/ 14.97 GFLOPS | Progress: (12/20) | 10.88 s
[Task 20/25] Current/Best: 10.87/ 14.97 GFLOPS | Progress: (16/20) | 14.86 s
[Task 20/25] Current/Best: 11.53/ 21.52 GFLOPS | Progress: (20/20) | 17.02 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.31/ 17.58 GFLOPS | Progress: (4/20) | 3.36 s
[Task 21/25] Current/Best: 14.52/ 17.58 GFLOPS | Progress: (8/20) | 5.01 s
[Task 21/25] Current/Best: 1.61/ 17.58 GFLOPS | Progress: (12/20) | 7.21 s
[Task 21/25] Current/Best: 15.82/ 17.58 GFLOPS | Progress: (16/20) | 10.82 s
[Task 21/25] Current/Best: 4.44/ 17.58 GFLOPS | Progress: (20/20) | 18.29 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.62 GFLOPS | Progress: (4/20
) | 2.79 s
[Task 22/25] Current/Best: 9.22/ 20.76 GFLOPS | Progress: (8/20) | 4.84 s
[Task 22/25] Current/Best: 19.81/ 20.76 GFLOPS | Progress: (12/20) | 7.28 s
[Task 22/25] Current/Best: 15.18/ 20.76 GFLOPS | Progress: (16/20) | 9.47 s
[Task 22/25] Current/Best: 13.26/ 20.76 GFLOPS | Progress: (20/20) | 11.24 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 16.50/ 19.44 GFLOPS | Progress: (4/20) | 3.34 s
[Task 23/25] Current/Best: 14.05/ 19.79 GFLOPS | Progress: (8/20) | 6.80 s
[Task 23/25] Current/Best: 20.30/ 21.28 GFLOPS | Progress: (12/20) | 8.71 s
[Task 23/25] Current/Best: 6.30/ 21.28 GFLOPS | Progress: (16/20) | 15.85 s
[Task 23/25] Current/Best: 7.29/ 21.28 GFLOPS | Progress: (20/20) | 20.15 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.09/ 8.09 GFLOPS | Progress: (4/20) | 11.88 s
[Task 24/25] Current/Best: 1.85/ 8.09 GFLOPS | Progress: (8/20) | 23.00 s
[Task 24/25] Current/Best: 3.56/ 8.09 GFLOPS | Progress: (12/20) | 34.59 s Done.
-
[Task 24/25] Current/Best: 6.19/ 8.62 GFLOPS | Progress: (16/20) | 40.36 s
[Task 24/25] Current/Best: 2.89/ 8.62 GFLOPS | Progress: (20/20) | 46.48 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.85 GFLOPS | Progress: (4/20) | 11.64 s
[Task 25/25] Current/Best: 5.36/ 7.50 GFLOPS | Progress: (8/20) | 22.93 s
[Task 25/25] Current/Best: 5.85/ 7.50 GFLOPS | Progress: (12/20) | 34.28 s
[Task 25/25] Current/Best: 5.77/ 9.10 GFLOPS | Progress: (16/20) | 36.18 s
[Task 25/25] Current/Best: 2.86/ 9.10 GFLOPS | Progress: (20/20) | 46.91 s
+
[Task 20/25] Current/Best: 9.83/ 15.28 GFLOPS | Progress: (8/20) | 6.96 s
[Task 20/25] Current/Best: 2.32/ 15.28 GFLOPS | Progress: (12/20) | 10.98 s
[Task 20/25] Current/Best: 11.14/ 15.28 GFLOPS | Progress: (16/20) | 14.92 s
[Task 20/25] Current/Best: 11.49/ 21.40 GFLOPS | Progress: (20/20) | 17.08 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.31/ 17.52 GFLOPS | Progress: (4/20) | 3.34 s
[Task 21/25] Current/Best: 14.53/ 17.52 GFLOPS | Progress: (8/20) | 4.99 s
[Task 21/25] Current/Best: 1.61/ 17.52 GFLOPS | Progress: (12/20) | 7.18 s
[Task 21/25] Current/Best: 16.06/ 17.52 GFLOPS | Progress: (16/20) | 10.76 s
[Task 21/25] Current/Best: 4.44/ 17.52 GFLOPS | Progress: (20/20) | 18.16 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.78 GFLOPS | Progress: (4/20
) | 2.72 s
[Task 22/25] Current/Best: 8.93/ 20.99 GFLOPS | Progress: (8/20) | 4.69 s
[Task 22/25] Current/Best: 19.77/ 20.99 GFLOPS | Progress: (12/20) | 7.09 s
[Task 22/25] Current/Best: 15.29/ 20.99 GFLOPS | Progress: (16/20) | 9.23 s
[Task 22/25] Current/Best: 12.96/ 20.99 GFLOPS | Progress: (20/20) | 10.99 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 15.58/ 19.64 GFLOPS | Progress: (4/20) | 3.35 s
[Task 23/25] Current/Best: 13.75/ 19.82 GFLOPS | Progress: (8/20) | 6.66 s
[Task 23/25] Current/Best: 20.37/ 21.50 GFLOPS | Progress: (12/20) | 8.54 s
[Task 23/25] Current/Best: 6.47/ 21.50 GFLOPS | Progress: (16/20) | 15.65 s
[Task 23/25] Current/Best: 7.57/ 21.50 GFLOPS | Progress: (20/20) | 19.92 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.50/ 8.50 GFLOPS | Progress: (4/20) | 11.81 s
[Task 24/25] Current/Best: 1.96/ 8.50 GFLOPS | Progress: (8/20) | 22.88 s
[Task 24/25] Current/Best: 4.04/ 8.50 GFLOPS | Progress: (12/20) | 34.46 s Done.
+
[Task 24/25] Current/Best: 6.06/ 8.50 GFLOPS | Progress: (16/20) | 40.15 s
[Task 24/25] Current/Best: 2.95/ 8.50 GFLOPS | Progress: (20/20) | 46.11 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.88 GFLOPS | Progress: (4/20) | 11.63 s
[Task 25/25] Current/Best: 5.84/ 7.66 GFLOPS | Progress: (8/20) | 22.91 s
[Task 25/25] Current/Best: 5.89/ 7.66 GFLOPS | Progress: (12/20) | 34.41 s
[Task 25/25] Current/Best: 5.68/ 9.20 GFLOPS | Progress: (16/20) | 36.16 s
[Task 25/25] Current/Best: 2.84/ 9.20 GFLOPS | Progress: (20/20) | 46.89 s
@@ -737,8 +737,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 411.1838606100173, 'median': 411.4897552000457, 'std': 1.000769137550157}
- unoptimized: {'mean': 518.1210708800063, 'median': 517.8918785499718, 'std': 2.360912984889522}
+ optimized: {'mean': 410.4343596400008, 'median': 410.54452120000633, 'std': 0.7799474279614487}
+ unoptimized: {'mean': 509.63054053000286, 'median': 510.2050166499964, 'std': 1.692568446876928}
@@ -761,7 +761,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 38.588 seconds)
+ **Total running time of the script:** ( 10 minutes 30.264 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 4bf8df2adb..b4716d9f06 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
- 1.245e-07 secs/op
+ 1.304e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 31438f1d4b..5cac7c6897 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, 0x166b8150)), stage(b, placeholder(b, 0x1fcf2f90)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+ [stage(a, placeholder(a, 0x7560f10)), stage(b, placeholder(b, 0xca9f5b0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min= [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 74aac6fd40..0b2351c4a1 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
=================
-**13:50.077** total execution time for **tutorial** files:
+**13:40.694** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:38.588 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:30.264 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:09.998 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:12.891 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:03.301 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.116 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:32.041 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:32.418 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.496 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.836 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.759 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.291 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.723 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.713 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.163 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.156 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.004 | 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_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :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 a4e351afc0..f971a5a8b1 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -294,7 +294,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
+ Numpy running time: 0.000007
naive: 0.000007
@@ -449,7 +449,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000024
+ 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"),
@@ -501,10 +501,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.40468000205874e-06 1.0
- naive 6.772499999999999e-06 0.8058010535012712
- parallel 7.1025e-06 0.8450648922100819
- vector 2.44631e-05 2.9106521597500112
+ numpy 7.419700000355078e-06 1.0
+ naive 6.662500000000001e-06 0.8979473563191449
+ parallel 6.951400000000001e-06 0.9368842405578842
+ vector 2.4550700000000002e-05 3.30885345752862
@@ -925,7 +925,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018998
+ Numpy running time: 0.019511
@@ -983,7 +983,7 @@ optimizations.
.. code-block:: none
- none: 3.554445
+ none: 3.257721
@@ -1086,7 +1086,7 @@ schedule.
.. code-block:: none
- blocking: 0.318267
+ blocking: 0.303514
@@ -1182,7 +1182,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.343458
+ vectorization: 0.347067
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1256,7 +1256,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.126368
+ loop permutation: 0.117817
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1355,7 +1355,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.110780
+ array packing: 0.108332
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1448,7 +1448,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.111568
+ block caching: 0.110473
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1534,7 +1534,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.147295
+ parallelization: 0.144252
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1615,13 +1615,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.5544454010999997 1.0
- blocking 0.3182670935 0.0895405773855762
- vectorization 0.34345757870000004 0.09662761414022837
- loop permutation 0.12636830540000002 0.03555218638634669
- array packing 0.11078039839999998 0.031166718263759684
- block caching 0.1115676855 0.031388211917806635
- parallelization 0.1472945234 0.041439523407622615
+ none 3.2577210449999994 1.0
+ blocking 0.3035144557 0.09316772415668884
+ vectorization 0.34706732529999995 0.10653684600548725
+ loop permutation 0.1178172596 0.03616554578263469
+ array packing 0.108331731 0.03325383895784116
+ block caching 0.11047277930000002 0.03391106168207844
+ parallelization 0.144251878 0.044279996969476564
@@ -1661,11 +1661,6 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 3.301 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index ecbb88d4d4..499573ec5b 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-5d0a16749cdba494178dee7deefa2938d1f8a88b
+e037ae49928592afdfa8d2c27198fc68592f9528
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index c56f70e2fe..e47574e967 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -572,7 +572,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.739 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.226 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_keras.html b/docs/how_to/compile_models/from_keras.html
index e171d7df71..6feb98ce76 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -493,7 +493,7 @@ pip install -U tensorflow --user
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 956ms/step
+1/1 [==============================] - 1s 961ms/step
Keras top-1 id: 285, class name: Egyptian cat
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 5f7e83565e..495222073e 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.zip6af49eb7-2eb6-46f4-afb2-64fc96795a78 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.zip68faadb9-bd2f-43bf-9eb6-b38b0759d537 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 2c4f3f54d6..180bb9f99a 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -435,13 +435,13 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 15%|#5 | 6.33M/41.5M [00:00<00:00, 62.7MB/s]
- 30%|##9 | 12.3M/41.5M [00:00<00:00, 43.3MB/s]
- 40%|#### | 16.8M/41.5M [00:00<00:00, 27.0MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 35.4MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 41.3MB/s]
- 96%|#########5| 39.7M/41.5M [00:00<00:00, 50.5MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 43.3MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 52.0MB/s]
+ 27%|##7 | 11.3M/41.5M [00:00<00:00, 47.6MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 37.0MB/s]
+ 54%|#####3 | 22.3M/41.5M [00:00<00:00, 45.0MB/s]
+ 65%|######5 | 27.1M/41.5M [00:00<00:00, 46.5MB/s]
+ 87%|########6 | 36.0M/41.5M [00:00<00:00, 60.5MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 49.9MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 1a32e3faf7..8178402439 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,9 +414,10 @@ 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]
- 45%|####5 | 20.2M/44.7M [00:00<00:00, 212MB/s]
- 94%|#########4| 42.1M/44.7M [00:00<00:00, 222MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 213MB/s]
+ 10%|# | 4.59M/44.7M [00:00<00:00, 48.1MB/s]
+ 21%|## | 9.17M/44.7M [00:00<00:00, 43.4MB/s]
+ 69%|######8 | 30.7M/44.7M [00:00<00:00, 122MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 121MB/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 78e5090dc1..bca9fca0b8 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -632,7 +632,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.852 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.017 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 d78c36c9f4..707df6dde4 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>05:13.640</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:16.648</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -335,44 +335,44 @@
<col style="width: 8%" />
</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>01:05.852</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
+<td><p>01:08.226</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:03.739</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
+<td><p>01:05.017</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>00:40.250</p></td>
+<td><p>00:40.200</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:28.998</p></td>
+<td><p>00:28.877</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>00:26.685</p></td>
+<td><p>00:27.580</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>00:25.383</p></td>
+<td><p>00:24.317</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>00:22.449</p></td>
+<td><p>00:23.050</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>00:21.013</p></td>
+<td><p>00:19.984</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:16.806</p></td>
+<td><p>00:16.971</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>00:02.464</p></td>
+<td><p>00:02.426</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 d2987ebb67..a21faed2a2 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -649,7 +649,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.4739 16.3781 17.2318 16.0584 0.3946
+ 16.1065 16.0002 17.0928 15.9543 0.3298
</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 75f954621f..7aa3d41acf 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,70 +436,17 @@ 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]
- 1%|1 | 2.19M/170M [00:00<00:07, 22.7MB/s]
- 3%|3 | 5.56M/170M [00:00<00:05, 30.0MB/s]
- 5%|4 | 8.43M/170M [00:00<00:06, 25.7MB/s]
- 6%|6 | 10.9M/170M [00:00<00:06, 25.1MB/s]
- 9%|9 | 15.4M/170M [00:00<00:05, 30.9MB/s]
- 11%|# | 18.4M/170M [00:00<00:07, 20.6MB/s]
- 12%|#2 | 21.2M/170M [00:00<00:06, 22.6MB/s]
- 14%|#4 | 24.4M/170M [00:01<00:06, 24.8MB/s]
- 16%|#6 | 27.6M/170M [00:01<00:05, 27.1MB/s]
- 18%|#8 | 31.2M/170M [00:01<00:04, 29.8MB/s]
- 21%|##1 | 36.0M/170M [00:01<00:04, 35.0MB/s]
- 23%|##3 | 39.5M/170M [00:01<00:04, 32.9MB/s]
- 25%|##5 | 42.8M/170M [00:01<00:04, 29.3MB/s]
- 27%|##6 | 45.7M/170M [00:01<00:04, 27.3MB/s]
- 29%|##8 | 48.5M/170M [00:01<00:04, 26.1MB/s]
- 30%|### | 51.0M/170M [00:01<00:05, 24.9MB/s]
- 31%|###1 | 53.5M/170M [00:02<00:05, 22.9MB/s]
- 33%|###2 | 55.9M/170M [00:02<00:05, 23.4MB/s]
- 34%|###4 | 58.3M/170M [00:02<00:04, 23.9MB/s]
- 36%|###5 | 60.6M/170M [00:02<00:05, 22.6MB/s]
- 37%|###6 | 62.8M/170M [00:02<00:05, 22.0MB/s]
- 38%|###8 | 65.2M/170M [00:02<00:04, 22.9MB/s]
- 40%|###9 | 67.4M/170M [00:02<00:04, 22.5MB/s]
- 41%|#### | 69.6M/170M [00:02<00:04, 22.4MB/s]
- 42%|####2 | 72.1M/170M [00:02<00:04, 23.5MB/s]
- 44%|####3 | 74.5M/170M [00:03<00:04, 23.7MB/s]
- 45%|####5 | 76.8M/170M [00:03<00:04, 22.3MB/s]
- 46%|####6 | 78.9M/170M [00:03<00:04, 22.4MB/s]
- 48%|####7 | 81.2M/170M [00:03<00:04, 22.7MB/s]
- 49%|####9 | 83.4M/170M [00:03<00:04, 22.4MB/s]
- 50%|##### | 85.5M/170M [00:03<00:03, 22.2MB/s]
- 52%|#####1 | 87.6M/170M [00:03<00:04, 20.4MB/s]
- 53%|#####2 | 89.6M/170M [00:03<00:04, 19.1MB/s]
- 54%|#####3 | 91.6M/170M [00:03<00:04, 19.4MB/s]
- 55%|#####5 | 93.7M/170M [00:04<00:03, 20.2MB/s]
- 56%|#####6 | 95.7M/170M [00:04<00:03, 20.4MB/s]
- 58%|#####7 | 98.2M/170M [00:04<00:03, 21.9MB/s]
- 59%|#####9 | 100M/170M [00:04<00:03, 22.4MB/s]
- 60%|###### | 103M/170M [00:04<00:03, 22.1MB/s]
- 62%|######1 | 105M/170M [00:04<00:03, 21.4MB/s]
- 63%|######2 | 107M/170M [00:04<00:03, 20.1MB/s]
- 64%|######4 | 109M/170M [00:04<00:03, 19.8MB/s]
- 65%|######5 | 111M/170M [00:04<00:03, 20.4MB/s]
- 66%|######6 | 113M/170M [00:05<00:02, 20.0MB/s]
- 68%|######7 | 115M/170M [00:05<00:02, 19.8MB/s]
- 69%|######8 | 117M/170M [00:05<00:02, 19.7MB/s]
- 70%|######9 | 119M/170M [00:05<00:02, 19.8MB/s]
- 71%|#######1 | 121M/170M [00:05<00:02, 21.8MB/s]
- 73%|#######2 | 124M/170M [00:05<00:02, 22.6MB/s]
- 74%|#######4 | 126M/170M [00:05<00:02, 19.8MB/s]
- 75%|#######5 | 128M/170M [00:05<00:02, 20.2MB/s]
- 77%|#######6 | 130M/170M [00:05<00:02, 20.3MB/s]
- 78%|#######8 | 133M/170M [00:06<00:01, 22.5MB/s]
- 80%|######## | 136M/170M [00:06<00:01, 27.6MB/s]
- 83%|########2 | 141M/170M [00:06<00:00, 32.4MB/s]
- 85%|########4 | 144M/170M [00:06<00:00, 31.9MB/s]
- 87%|########7 | 148M/170M [00:06<00:00, 35.1MB/s]
- 89%|########9 | 151M/170M [00:06<00:00, 29.6MB/s]
- 91%|######### | 154M/170M [00:06<00:00, 23.0MB/s]
- 93%|#########3| 158M/170M [00:06<00:00, 26.4MB/s]
- 95%|#########4| 161M/170M [00:07<00:00, 24.7MB/s]
- 97%|#########7| 165M/170M [00:07<00:00, 28.3MB/s]
- 99%|#########8| 168M/170M [00:07<00:00, 17.8MB/s]
-100%|##########| 170M/170M [00:07<00:00, 23.1MB/s]
+ 2%|2 | 3.88M/170M [00:00<00:04, 40.6MB/s]
+ 5%|4 | 8.14M/170M [00:00<00:03, 42.9MB/s]
+ 13%|#3 | 22.2M/170M [00:00<00:01, 90.4MB/s]
+ 25%|##5 | 43.2M/170M [00:00<00:00, 142MB/s]
+ 39%|###9 | 66.3M/170M [00:00<00:00, 177MB/s]
+ 49%|####8 | 83.1M/170M [00:00<00:00, 168MB/s]
+ 60%|#####9 | 102M/170M [00:00<00:00, 176MB/s]
+ 71%|####### | 120M/170M [00:00<00:00, 183MB/s]
+ 81%|########1 | 138M/170M [00:00<00:00, 177MB/s]
+ 94%|#########3| 159M/170M [00:01<00:00, 190MB/s]
+100%|##########| 170M/170M [00:01<00:00, 164MB/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').
@@ -593,7 +540,7 @@ 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 11.278 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 2.203 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 a2e6c9cc35..a07d6cdbb8 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]
- 23%|##3 | 3.14M/13.6M [00:00<00:00, 32.9MB/s]
- 47%|####6 | 6.33M/13.6M [00:00<00:00, 33.2MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 59.4MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 179MB/s]
</pre></div>
</div>
</div>
@@ -567,7 +565,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.4300 90.3387 92.9575 90.1677 0.3304
+ 90.4479 90.2844 96.0755 90.0569 0.6561
</pre></div>
</div>
<div class="admonition note">
@@ -606,7 +604,7 @@ 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 11.583 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.674 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 0010d1439c..6a50cbe3c1 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -569,7 +569,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.0103 119.8265 127.9406 119.0140 1.1466
+ 120.8376 120.7808 126.3305 119.9395 0.6892
</pre></div>
</div>
<div class="admonition note">
@@ -597,7 +597,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 1.045 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 1.067 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 0633f8358d..403c74e6b5 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -507,7 +507,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 27.804 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 24.407 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 83f826f444..ab9351263a 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,24 +441,23 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 4%|4 | 5615/132723 [00:00<00:02, 56146.97KB/s]
- 10%|9 | 13144/132723 [00:00<00:01, 67404.34KB/s]
- 16%|#5 | 20679/132723 [00:00<00:01, 71029.30KB/s]
- 21%|##1 | 28223/132723 [00:00<00:01, 72765.68KB/s]
- 27%|##6 | 35813/132723 [00:00<00:01, 73894.04KB/s]
- 33%|###2 | 43345/132723 [00:00<00:01, 74364.99KB/s]
- 38%|###8 | 50850/132723 [00:00<00:01, 74586.08KB/s]
- 44%|####3 | 58309/132723 [00:00<00:01, 73202.23KB/s]
- 50%|####9 | 65794/132723 [00:00<00:00, 73708.38KB/s]
- 55%|#####5 | 73257/132723 [00:01<00:00, 73987.07KB/s]
- 61%|###### | 80715/132723 [00:01<00:00, 74165.59KB/s]
- 67%|######6 | 88270/132723 [00:01<00:00, 74583.08KB/s]
- 72%|#######2 | 95745/132723 [00:01<00:00, 74631.57KB/s]
- 78%|#######7 | 103210/132723 [00:01<00:00, 74597.70KB/s]
- 83%|########3 | 110695/132723 [00:01<00:00, 74669.77KB/s]
- 89%|########9 | 118189/132723 [00:01<00:00, 74749.15KB/s]
- 95%|#########4| 125667/132723 [00:01<00:00, 74755.17KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 73681.81KB/s]
+ 4%|4 | 5357/132723 [00:00<00:02, 53566.48KB/s]
+ 10%|# | 13641/132723 [00:00<00:01, 70779.22KB/s]
+ 16%|#6 | 21886/132723 [00:00<00:01, 76103.81KB/s]
+ 23%|##2 | 30206/132723 [00:00<00:01, 78902.68KB/s]
+ 29%|##8 | 38419/132723 [00:00<00:01, 80064.43KB/s]
+ 35%|###5 | 46749/132723 [00:00<00:01, 81159.68KB/s]
+ 41%|####1 | 54865/132723 [00:00<00:00, 79255.25KB/s]
+ 48%|####7 | 63162/132723 [00:00<00:00, 80417.31KB/s]
+ 54%|#####3 | 71335/132723 [00:00<00:00, 80821.14KB/s]
+ 60%|#####9 | 79620/132723 [00:01<00:00, 81440.03KB/s]
+ 66%|######6 | 87849/132723 [00:01<00:00, 81695.58KB/s]
+ 72%|#######2 | 96181/132723 [00:01<00:00, 82185.69KB/s]
+ 79%|#######8 | 104453/132723 [00:01<00:00, 82345.77KB/s]
+ 85%|########4 | 112748/132723 [00:01<00:00, 82526.77KB/s]
+ 91%|#########1| 121043/132723 [00:01<00:00, 82652.66KB/s]
+ 97%|#########7| 129398/132723 [00:01<00:00, 82920.03KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 80457.86KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -497,7 +496,7 @@ 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 41.660 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 37.475 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 26c04b3985..79590f9de3 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>11:50.869</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:32.085</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>03:11.278</p></td>
+<td><p>03:02.203</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>02:41.660</p></td>
+<td><p>02:37.475</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>02:01.045</p></td>
+<td><p>02:01.067</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></td>
-<td><p>01:27.804</p></td>
+<td><p>01:24.407</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:11.583</p></td>
+<td><p>01:10.674</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>00:30.935</p></td>
+<td><p>00:30.283</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>00:23.459</p></td>
+<td><p>00:23.187</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>00:23.098</p></td>
+<td><p>00:22.782</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 97048a83a2..d45653d00f 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -608,7 +608,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip7eb617de-6f45-41f8-86c1-2d9b84746fb9 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.zipc1796861-b587-4024-a9f3-655dead537e7 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 cdef6815ff..4001fb890a 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:41.930</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:41.783</strong> total execution time for <strong>how_to_extend_tvm</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="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:38.691</p></td>
+<td><p>00:38.655</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>00:02.268</p></td>
+<td><p>00:02.195</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>00:00.963</p></td>
+<td><p>00:00.926</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.008</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 07710eb6c3..5ae2565db1 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: 7015us [7015us] (46.03%; 46.03%)
-FoldScaleAxis: 8223us [7us] (53.97%; 53.97%)
- FoldConstant: 8217us [1790us] (53.92%; 99.92%)
- InferType: 6427us [6427us] (42.18%; 78.22%)
+InferType: 6634us [6634us] (45.73%; 45.73%)
+FoldScaleAxis: 7874us [5us] (54.27%; 54.27%)
+ FoldConstant: 7869us [1631us] (54.24%; 99.94%)
+ InferType: 6238us [6238us] (43.00%; 79.27%)
</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: 6511us [6511us] (44.38%; 44.38%)
-FoldScaleAxis: 8159us [5us] (55.62%; 55.62%)
- FoldConstant: 8154us [1761us] (55.58%; 99.93%)
- InferType: 6393us [6393us] (43.58%; 78.41%)
+InferType: 6309us [6309us] (44.52%; 44.52%)
+FoldScaleAxis: 7862us [5us] (55.48%; 55.48%)
+ FoldConstant: 7858us [1642us] (55.45%; 99.94%)
+ InferType: 6216us [6216us] (43.86%; 79.11%)
</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 ba6717f758..27fb313a6b 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -564,7 +564,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.182425 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 41.674519 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 230d3e69dc..2435a0b583 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -906,7 +906,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 7.178219 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 7.042579 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 2ae53c53cc..7b8525bedd 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: 0.019142
-Baseline: 3.404615
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019217
+Baseline: 3.252773
</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: 0.322602
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.301739
</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: 0.351764
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.341203
</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: 0.120582
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.117069
</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: 0.111994
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110063
</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: 0.111022
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111081
</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: 0.147406
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147204
</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 22de97cfa6..05664746b6 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>00:35.003</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.179</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>00:32.822</p></td>
+<td><p>00:31.953</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>00:01.192</p></td>
+<td><p>00:01.223</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>00:00.989</p></td>
+<td><p>00:01.003</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 2ed96390ed..9832817c5d 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>06:26.936</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:37.063</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -336,27 +336,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>03:25.032</p></td>
+<td><p>03:28.920</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>01:24.803</p></td>
+<td><p>01:23.130</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>00:57.856</p></td>
+<td><p>00:56.970</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:21.180</p></td>
+<td><p>00:30.580</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>00:09.199</p></td>
+<td><p>00:08.806</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:08.866</p></td>
+<td><p>00:08.658</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 87e0d829f5..114bb44a03 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
@@ -491,185 +491,439 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 8;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
allocate(conv2d_nchw: Pointer(local float32), float32, [28]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [28], [], scope="local")[0] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[6] = 0f32
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [49], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[13] = 0f32
conv2d_nchw_1[14] = 0f32
- conv2d_nchw_1[15] = 0f32
- conv2d_nchw_1[16] = 0f32
- conv2d_nchw_1[17] = 0f32
- conv2d_nchw_1[18] = 0f32
- conv2d_nchw_1[19] = 0f32
- conv2d_nchw_1[20] = 0f32
conv2d_nchw_1[21] = 0f32
+ conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[15] = 0f32
conv2d_nchw_1[22] = 0f32
+ conv2d_nchw_1[2] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[16] = 0f32
conv2d_nchw_1[23] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[17] = 0f32
conv2d_nchw_1[24] = 0f32
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[18] = 0f32
conv2d_nchw_1[25] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[19] = 0f32
conv2d_nchw_1[26] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ conv2d_nchw_1[20] = 0f32
conv2d_nchw_1[27] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- let cse_var_2: int32 = (rc.outer.outer*392)
- let cse_var_1: int32 = (rc.outer.outer*72)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((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" = 112;
- 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" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 12), 81)) && (floormod((threadIdx.x_1 + 12), 81) < 72)) && (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" = 112;
- 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" = 112;
- if @tir.likely((threadIdx.x_1 < 88), dtype=bool) {
- 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_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 112), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 224), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 336), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 448), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 560), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 672), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 784), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 896), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1120), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1232), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1344), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1456), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1568), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1680), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1792), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1904), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2128), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2240), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2352), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2464), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2576), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2688), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2800), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2912), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 193536)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3136), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3248)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3248), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3360), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3472)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3472), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3584), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3696)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3696), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3808), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3920), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4144)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4144), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4256), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4368)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4368), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4480), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 4592)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4592), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- }
- for (rc.outer.inner: int32, 0, 8) {
- for (ry.outer.inner: int32, 0, 3) {
- for (ff.outer.inner: int32, 0, 4) {
- let cse_var_9: int32 = (ff.outer.inner*7)
- let cse_var_8: int32 = (cse_var_9 + 6)
- let cse_var_7: int32 = (cse_var_9 + 5)
- let cse_var_6: int32 = (cse_var_9 + 4)
- let cse_var_5: int32 = (cse_var_9 + 3)
- let cse_var_4: int32 = (cse_var_9 + 2)
- let cse_var_3: int32 = (cse_var_9 + 1)
+ for (rc.outer.outer: int32, 0, 16) {
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_4: int32 = (rc.outer.outer*1568)
+ let cse_var_3: int32 = (ry.outer.outer*7)
+ let cse_var_2: int32 = (rc.outer.outer*288)
+ let cse_var_1: int32 = (ry.outer.outer*3)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 56), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 168), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 280), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 392), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 384)], 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 560), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 616), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 672), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 728)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 728), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 784), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 840)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 840), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 896), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 952)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 952), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 776)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1064)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1064), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1120), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1176), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1232), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1288)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1288), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1344)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1344), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1400)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1400), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1456)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1456), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1512)] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 1168)], 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1568), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1624)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1624), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1680)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1680), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1736)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1736), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1792)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1792), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1848)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1848), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1904)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1904), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1960), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 56), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 112), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 168), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 280), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 336), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 448), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 504), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 560), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 616), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + 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*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 728), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 784), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 840), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 896), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 952), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 1008), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1064), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 1120), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 1232), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1288), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + 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*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1400), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 1456), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1512), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 1568), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1624)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1624), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 1680), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1736)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1736), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 1792), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1848)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1848), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 1904), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + 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*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2072)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2072), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 2128), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2184)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2184), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + 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*147456) + (floordiv((threadIdx.x_2 + 2240), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2296)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2296), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2408)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2408), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2464), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2520)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2520), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2576), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2632)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2632), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2744), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2800), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2856)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2856), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2912), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2968)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2968), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 48), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3024), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 16)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ }
+ for (rc.outer.inner: int32, 0, 2) {
+ for (yy.outer.inner: int32, 0, 7) {
+ let cse_var_7: int32 = (yy.outer.inner + 7)
+ let cse_var_6: int32 = (yy.outer.inner + 21)
+ let cse_var_5: int32 = (yy.outer.inner + 14)
{
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[(((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*72)) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48))]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 768)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1536)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2304)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 769)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1537)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2305)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 770)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1538)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2306)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 3)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 771)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1539)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2307)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 4)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 772)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1540)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2308)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 5)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 773)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1541)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2309)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 6)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 774)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1542)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2310)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 7)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 775)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1543)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2311)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 8)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 776)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1544)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2312)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 9)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 777)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1545)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2313)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 10)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 778)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1546)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2314)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 11)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 779)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1547)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2315)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 12)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 780)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1548)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2316)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 13)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 781)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1549)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2317)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 14)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 782)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1550)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2318)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 15)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 783)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1551)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2319)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 16)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 784)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1552)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2320)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 17)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 785)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1553)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2321)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 18)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 786)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1554)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2322)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 19)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 787)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1555)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2323)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 20)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 788)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1556)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2324)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 21)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 789)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1557)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2325)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 22)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 790)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1558)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2326)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 23)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 791)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1559)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2327)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 24)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 792)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1560)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2328)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 25)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 793)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1561)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2329)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 26)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 794)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1562)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2330)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 27)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 795)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1563)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2331)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 28)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 796)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1564)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2332)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 29)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 797)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1565)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2333)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 30)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 798)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1566)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2334)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 31)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 799)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1567)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2335)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 32)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 800)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1568)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2336)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 33)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 801)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1569)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2337)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 34)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 802)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1570)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2338)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 35)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 803)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1571)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2339)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 36)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 804)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1572)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2340)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 37)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 805)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1573)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2341)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 38)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 806)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1574)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2342)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 39)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 807)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1575)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2343)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 40)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 808)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1576)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2344)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 41)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 809)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1577)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2345)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 42)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 810)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1578)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2346)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 43)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 811)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1579)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2347)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 44)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 812)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1580)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2348)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 45)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 813)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1581)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2349)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 46)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 814)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1582)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2350)]))
+ conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 47)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 815)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 1583)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*48)) + 2351)]))
}
}
}
}
}
}
- for (i1.inner: int32, 0, 4) {
- for (i2.inner: int32, 0, 7) {
- compute[(((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias[(((blockIdx.x*64) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
- }
+ for (i2.inner: int32, 0, 7) {
+ compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7)) + 392)] = max((conv2d_nchw_1[(i2.inner + 7)] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 8)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7)) + 784)] = max((conv2d_nchw_1[(i2.inner + 14)] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7)) + 1176)] = max((conv2d_nchw_1[(i2.inner + 21)] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 24)]), 0f32)
}
}
}
@@ -706,7 +960,7 @@ 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: 0.412 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.392 ms
</pre></div>
</div>
</div>
@@ -736,9 +990,9 @@ 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=16)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=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=4)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=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)
@@ -747,19 +1001,19 @@ conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, fact
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=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=16)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=4)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
@@ -784,14 +1038,14 @@ 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=112)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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=112)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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", 64)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -809,125 +1063,338 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+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[28];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[4608];
+ __shared__ float pad_temp_shared[2016];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
conv2d_nchw[14] = 0.000000e+00f;
- conv2d_nchw[15] = 0.000000e+00f;
- conv2d_nchw[16] = 0.000000e+00f;
- conv2d_nchw[17] = 0.000000e+00f;
- conv2d_nchw[18] = 0.000000e+00f;
- conv2d_nchw[19] = 0.000000e+00f;
- conv2d_nchw[20] = 0.000000e+00f;
conv2d_nchw[21] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[15] = 0.000000e+00f;
conv2d_nchw[22] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[16] = 0.000000e+00f;
conv2d_nchw[23] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[17] = 0.000000e+00f;
conv2d_nchw[24] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[18] = 0.000000e+00f;
conv2d_nchw[25] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[19] = 0.000000e+00f;
conv2d_nchw[26] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ conv2d_nchw[20] = 0.000000e+00f;
conv2d_nchw[27] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((9 <= ((((int)threadIdx.x) + 12) % 81)) && (((((int)threadIdx.x) + 12) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 88) {
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 112) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 336) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 560) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1232) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1456) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1568) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1680) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1904) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2128) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2240) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2352) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2464) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2576) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2688) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2800) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2912) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 193536)];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3136) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3248)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3248) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3360) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3472)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3472) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3584) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 3696)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3696) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3808) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3920) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 4144)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4144) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4256) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4368)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4368) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4480) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 16) {
- kernel_shared[(((int)threadIdx.x) + 4592)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4592) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 56) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- for (int ff_outer_inner = 0; ff_outer_inner < 4; ++ff_outer_inner) {
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 72)) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 56) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 112) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 168) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 280) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 336) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 448) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 504)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 384)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 560) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 616) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 672) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 728)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 728) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 840)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 840) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 896) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 952)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 952) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 776)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1064)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1064) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1120) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1232)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1232) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1288)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1288) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1344) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1400)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1400) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1456)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1456) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1512)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 1168)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1624)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1624) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1680)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1680) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1736)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1736) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1848)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1848) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1904)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1904) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 56) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 168) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 280) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 504) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 616) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 728) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 840) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 952) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1008) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1064) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1288) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1400) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1512) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1624)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1624) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1736)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1736) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1848)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1848) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 2072)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2072) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2184)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2184) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2296)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2296) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2408)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2408) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2520)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2520) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2576) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2632)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2632) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2800) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2856)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2856) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2968)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2968) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 48) {
+ kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3024) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 144)];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
+ for (int yy_outer_inner = 0; yy_outer_inner < 7; ++yy_outer_inner) {
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48))]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[(((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 768)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[(((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1536)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[(((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2304)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 769)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1537)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2305)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 770)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1538)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2306)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 771)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1539)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2307)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 772)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1540)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2308)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 773)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1541)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2309)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 774)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1542)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2310)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 775)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1543)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2311)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 776)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1544)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2312)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 777)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1545)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2313)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 778)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1546)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2314)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 779)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1547)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2315)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 780)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1548)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2316)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 781)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1549)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2317)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 782)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1550)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2318)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 783)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1551)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2319)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 784)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1552)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2320)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 785)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1553)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2321)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 786)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1554)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2322)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 787)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1555)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2323)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 788)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1556)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2324)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 789)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1557)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2325)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 790)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1558)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2326)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 791)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1559)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2327)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 792)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1560)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2328)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 793)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1561)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2329)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 794)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1562)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2330)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 795)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1563)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2331)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 796)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1564)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2332)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 797)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1565)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2333)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 798)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1566)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2334)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 799)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1567)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2335)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 800)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1568)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2336)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 801)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1569)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2337)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 802)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1570)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2338)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 803)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1571)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2339)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 804)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1572)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2340)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 805)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1573)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2341)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 806)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1574)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2342)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 807)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1575)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2343)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 808)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1576)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2344)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 809)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1577)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2345)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 810)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1578)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2346)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 811)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1579)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2347)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 812)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1580)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2348)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 813)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1581)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2349)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 814)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1582)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2350)]));
+ conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 815)]));
+ conv2d_nchw[(yy_outer_inner + 14)] = (conv2d_nchw[(yy_outer_inner + 14)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 1583)]));
+ conv2d_nchw[(yy_outer_inner + 21)] = (conv2d_nchw[(yy_outer_inner + 21)] + (pad_temp_shared[((((rc_outer_inner * 1008) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 48)) + 2351)]));
}
}
}
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[(((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 64) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
- }
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 392)] = max((conv2d_nchw[(i2_inner + 7)] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 8)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 784)] = max((conv2d_nchw[(i2_inner + 14)] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 1176)] = max((conv2d_nchw[(i2_inner + 21)] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 24)]), 0.000000e+00f);
}
}
</pre></div>
@@ -964,7 +1431,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 25.032 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 28.920 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 f6293f9839..7d84d24ad3 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -902,7 +902,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.1969 8.1998 8.2006 8.1903 0.0047
+ 8.2603 8.2608 8.2631 8.2572 0.0024
</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 5fbfbdc1d4..18f37ca472 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -921,7 +921,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 759.9851 759.6576 760.9176 759.3800 0.6691
+ 753.6400 754.2528 754.2978 752.3693 0.8987
</pre></div>
</div>
</div>
@@ -943,7 +943,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 24.803 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.130 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 6cc29007b4..5bcdce3946 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,103 +625,339 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 64) {
- let cse_var_1: int32 = ((i.outer.inner*1024) + (i.inner.init*16))
- {
- compute_5: Buffer(compute_4, float32, [2048], [])[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[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])) {
- for (i.inner: int32, 0, 64) {
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_2: int32 = ((i.outer.inner*1024) + (i.inner*16))
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
+ let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ let cse_var_1: int32 = (i.outer.inner*64)
+ {
+ compute_5: Buffer(compute_4, float32, [512], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
+ compute_5[(cse_var_1 + 16)] = 0f32
+ compute_5[(cse_var_1 + 17)] = 0f32
+ compute_5[(cse_var_1 + 18)] = 0f32
+ compute_5[(cse_var_1 + 19)] = 0f32
+ compute_5[(cse_var_1 + 20)] = 0f32
+ compute_5[(cse_var_1 + 21)] = 0f32
+ compute_5[(cse_var_1 + 22)] = 0f32
+ compute_5[(cse_var_1 + 23)] = 0f32
+ compute_5[(cse_var_1 + 24)] = 0f32
+ compute_5[(cse_var_1 + 25)] = 0f32
+ compute_5[(cse_var_1 + 26)] = 0f32
+ compute_5[(cse_var_1 + 27)] = 0f32
+ compute_5[(cse_var_1 + 28)] = 0f32
+ compute_5[(cse_var_1 + 29)] = 0f32
+ compute_5[(cse_var_1 + 30)] = 0f32
+ compute_5[(cse_var_1 + 31)] = 0f32
+ compute_5[(cse_var_1 + 32)] = 0f32
+ compute_5[(cse_var_1 + 33)] = 0f32
+ compute_5[(cse_var_1 + 34)] = 0f32
+ compute_5[(cse_var_1 + 35)] = 0f32
+ compute_5[(cse_var_1 + 36)] = 0f32
+ compute_5[(cse_var_1 + 37)] = 0f32
+ compute_5[(cse_var_1 + 38)] = 0f32
+ compute_5[(cse_var_1 + 39)] = 0f32
+ compute_5[(cse_var_1 + 40)] = 0f32
+ compute_5[(cse_var_1 + 41)] = 0f32
+ compute_5[(cse_var_1 + 42)] = 0f32
+ compute_5[(cse_var_1 + 43)] = 0f32
+ compute_5[(cse_var_1 + 44)] = 0f32
+ compute_5[(cse_var_1 + 45)] = 0f32
+ compute_5[(cse_var_1 + 46)] = 0f32
+ compute_5[(cse_var_1 + 47)] = 0f32
+ compute_5[(cse_var_1 + 48)] = 0f32
+ compute_5[(cse_var_1 + 49)] = 0f32
+ compute_5[(cse_var_1 + 50)] = 0f32
+ compute_5[(cse_var_1 + 51)] = 0f32
+ compute_5[(cse_var_1 + 52)] = 0f32
+ compute_5[(cse_var_1 + 53)] = 0f32
+ compute_5[(cse_var_1 + 54)] = 0f32
+ compute_5[(cse_var_1 + 55)] = 0f32
+ compute_5[(cse_var_1 + 56)] = 0f32
+ compute_5[(cse_var_1 + 57)] = 0f32
+ compute_5[(cse_var_1 + 58)] = 0f32
+ compute_5[(cse_var_1 + 59)] = 0f32
+ compute_5[(cse_var_1 + 60)] = 0f32
+ compute_5[(cse_var_1 + 61)] = 0f32
+ compute_5[(cse_var_1 + 62)] = 0f32
+ compute_5[(cse_var_1 + 63)] = 0f32
+ for (elem_idx: int32, 0, (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[((placeholder_3[cse_var_2]*16) + (elem_idx*16))]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_3: int32 = (cse_var_1 + 1)
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_4: int32 = (cse_var_1 + 2)
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_5: int32 = (cse_var_1 + 3)
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_6: int32 = (cse_var_1 + 4)
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_7: int32 = (cse_var_1 + 5)
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_8: int32 = (cse_var_1 + 6)
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_9: int32 = (cse_var_1 + 7)
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_10: int32 = (cse_var_1 + 8)
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_11: int32 = (cse_var_1 + 9)
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_12: int32 = (cse_var_1 + 10)
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_13: int32 = (cse_var_1 + 11)
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_14: int32 = (cse_var_1 + 12)
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_15: int32 = (cse_var_1 + 13)
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_16: int32 = (cse_var_1 + 14)
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_17: int32 = (cse_var_1 + 15)
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_18: int32 = (cse_var_1 + 16)
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_2]*16) + (elem_idx*16))]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_19: int32 = (cse_var_1 + 17)
+ compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 1)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_20: int32 = (cse_var_1 + 18)
+ compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 2)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_21: int32 = (cse_var_1 + 19)
+ compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 3)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_22: int32 = (cse_var_1 + 20)
+ compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 4)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_23: int32 = (cse_var_1 + 21)
+ compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 5)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_24: int32 = (cse_var_1 + 22)
+ compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 6)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_25: int32 = (cse_var_1 + 23)
+ compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 7)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_26: int32 = (cse_var_1 + 24)
+ compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 8)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_27: int32 = (cse_var_1 + 25)
+ compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 9)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_28: int32 = (cse_var_1 + 26)
+ compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 10)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_29: int32 = (cse_var_1 + 27)
+ compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 11)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_30: int32 = (cse_var_1 + 28)
+ compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 12)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_31: int32 = (cse_var_1 + 29)
+ compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 13)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_32: int32 = (cse_var_1 + 30)
+ compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 14)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_33: int32 = (cse_var_1 + 31)
+ compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 15)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_34: int32 = (cse_var_1 + 32)
+ compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[((placeholder_3[cse_var_2]*16) + (elem_idx*16))]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_35: int32 = (cse_var_1 + 33)
+ compute_5[cse_var_35] = (compute_5[cse_var_35] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 1)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_36: int32 = (cse_var_1 + 34)
+ compute_5[cse_var_36] = (compute_5[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 2)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_37: int32 = (cse_var_1 + 35)
+ compute_5[cse_var_37] = (compute_5[cse_var_37] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 3)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_38: int32 = (cse_var_1 + 36)
+ compute_5[cse_var_38] = (compute_5[cse_var_38] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 4)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_39: int32 = (cse_var_1 + 37)
+ compute_5[cse_var_39] = (compute_5[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 5)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_40: int32 = (cse_var_1 + 38)
+ compute_5[cse_var_40] = (compute_5[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 6)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_41: int32 = (cse_var_1 + 39)
+ compute_5[cse_var_41] = (compute_5[cse_var_41] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 7)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_42: int32 = (cse_var_1 + 40)
+ compute_5[cse_var_42] = (compute_5[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 8)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_43: int32 = (cse_var_1 + 41)
+ compute_5[cse_var_43] = (compute_5[cse_var_43] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 9)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_44: int32 = (cse_var_1 + 42)
+ compute_5[cse_var_44] = (compute_5[cse_var_44] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 10)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_45: int32 = (cse_var_1 + 43)
+ compute_5[cse_var_45] = (compute_5[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 11)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_46: int32 = (cse_var_1 + 44)
+ compute_5[cse_var_46] = (compute_5[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 12)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_47: int32 = (cse_var_1 + 45)
+ compute_5[cse_var_47] = (compute_5[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 13)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_48: int32 = (cse_var_1 + 46)
+ compute_5[cse_var_48] = (compute_5[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 14)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_49: int32 = (cse_var_1 + 47)
+ compute_5[cse_var_49] = (compute_5[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 15)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_50: int32 = (cse_var_1 + 48)
+ compute_5[cse_var_50] = (compute_5[cse_var_50] + (placeholder_1[((placeholder_3[cse_var_2]*16) + (elem_idx*16))]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_3: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 1)
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_51: int32 = (cse_var_1 + 49)
+ compute_5[cse_var_51] = (compute_5[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 1)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_4: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 2)
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_52: int32 = (cse_var_1 + 50)
+ compute_5[cse_var_52] = (compute_5[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 2)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_5: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 3)
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_53: int32 = (cse_var_1 + 51)
+ compute_5[cse_var_53] = (compute_5[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 3)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_6: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 4)
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_54: int32 = (cse_var_1 + 52)
+ compute_5[cse_var_54] = (compute_5[cse_var_54] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 4)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_7: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 5)
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_55: int32 = (cse_var_1 + 53)
+ compute_5[cse_var_55] = (compute_5[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 5)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_8: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 6)
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_56: int32 = (cse_var_1 + 54)
+ compute_5[cse_var_56] = (compute_5[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 6)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_9: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 7)
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_57: int32 = (cse_var_1 + 55)
+ compute_5[cse_var_57] = (compute_5[cse_var_57] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 7)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_10: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 8)
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_58: int32 = (cse_var_1 + 56)
+ compute_5[cse_var_58] = (compute_5[cse_var_58] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 8)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_11: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 9)
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_59: int32 = (cse_var_1 + 57)
+ compute_5[cse_var_59] = (compute_5[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 9)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_12: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 10)
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_60: int32 = (cse_var_1 + 58)
+ compute_5[cse_var_60] = (compute_5[cse_var_60] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 10)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_13: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 11)
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_61: int32 = (cse_var_1 + 59)
+ compute_5[cse_var_61] = (compute_5[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 11)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_14: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 12)
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_62: int32 = (cse_var_1 + 60)
+ compute_5[cse_var_62] = (compute_5[cse_var_62] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 12)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_15: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 13)
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_63: int32 = (cse_var_1 + 61)
+ compute_5[cse_var_63] = (compute_5[cse_var_63] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 13)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_16: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 14)
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_64: int32 = (cse_var_1 + 62)
+ compute_5[cse_var_64] = (compute_5[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 14)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_17: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 15)
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_65: int32 = (cse_var_1 + 63)
+ compute_5[cse_var_65] = (compute_5[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + 15)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- let cse_var_18: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*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_66: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute[ramp(cse_var_66, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_66, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -759,7 +995,7 @@ 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: 1.834 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 3.060 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 5b29d27cfa..034926ae2d 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>00:45.606</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:47.320</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</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>00:45.570</p></td>
+<td><p>00:47.282</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.020</p></td>
+<td><p>00:00.022</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
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 a5d8602422..17e75fc93d 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: 80.73/80.73 result: MeasureResult(costs=(0.0028675722571428574,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9275405406951904, timestamp=1663361933.6527922) [('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: 0.00/80.73 result: Traceback (most recent call last):
+No: 9 GFLOPS: 80.83/80.83 result: MeasureResult(costs=(0.002864093714285714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8326270580291748, timestamp=1663364523.1702492) [('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: 0.00/80.83 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: 258.79/258.79 result: MeasureResult(costs=(0.0008945659329608938,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7172877788543701, timestamp=1663361934.577884) [('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: 0.00/258.79 result: Traceback (most recent call last):
+No: 11 GFLOPS: 259.99/259.99 result: MeasureResult(costs=(0.0008904298674033151,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4686949253082275, timestamp=1663364524.089343) [('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: 0.00/259.99 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: 0.00/258.79 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/259.99 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: 0.00/258.79 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/259.99 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: 5.45/258.79 result: MeasureResult(costs=(0.04248450725,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8850071430206299, timestamp=1663361939.2082422) [('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: 3.35/258.79 result: MeasureResult(costs=(0.06910582175,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.617069482803345, timestamp=1663361940.44951) [('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: 0.00/258.79 result: Traceback (most recent call last):
+No: 15 GFLOPS: 5.27/259.99 result: MeasureResult(costs=(0.04395220375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8667688369750977, timestamp=1663364528.6761594) [('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: 3.34/259.99 result: MeasureResult(costs=(0.06935163675,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.5678369998931885, timestamp=1663364529.915958) [('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: 0.00/259.99 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: 0.00/258.79 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: 26.01/258.79 result: MeasureResult(costs=(0.008900514083333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1445872783660889, timestamp=1663361951.3518827) [('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: 0.00/258.79 result: Traceback (most recent call last):
+No: 18 GFLOPS: 28.24/259.99 result: MeasureResult(costs=(0.008197034642857143,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2898228168487549, timestamp=1663364540.9808195) [('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: 0.00/259.99 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: 0.00/258.79 result: Traceback (most recent call last):
+No: 20 GFLOPS: 0.00/259.99 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: 0.001295
+Time cost of this operator: 0.001298
</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 e3cee478d6..465f1ed103 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -582,10 +582,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.6 98.709 (1, 2, 10, 10, 3) 2 1 [310.6]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.11 0.988 (1, 6, 10, 10) 1 1 [3.11]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.952 0.302 (1, 1, 10, 10, 3) 1 1 [0.952]
-Total_time - 314.662 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 308.3 98.724 (1, 2, 10, 10, 3) 2 1 [308.3]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.03 0.97 (1, 6, 10, 10) 1 1 [3.03]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.955 0.306 (1, 1, 10, 10, 3) 1 1 [0.955]
+Total_time - 312.285 - - - - -
</pre></div>
</div>
</div>
@@ -636,10 +636,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 150.8 98.21 (1, 6, 10, 10, 1) 2 1 [150.8]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.773 1.155 (1, 6, 10, 10) 1 1 [1.773]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.976 0.635 (1, 1, 10, 10, 3) 1 1 [0.976]
-Total_time - 153.549 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 215.4 98.481 (1, 1, 10, 10, 6) 2 1 [215.4]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.342 1.071 (1, 6, 10, 10) 1 1 [2.342]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.981 0.448 (1, 3, 10, 10, 1) 1 1 [0.981]
+Total_time - 218.723 - - - - -
</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 576e8d119e..98eb76d171 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/tmpxklxu0qs/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp_xr3u1rf/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/tmpxklxu0qs/images/target contains 8144 images
-/tmp/tmpxklxu0qs/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/tmp_xr3u1rf/images/target contains 8144 images
+/tmp/tmp_xr3u1rf/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -689,13 +689,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 47s - loss: 0.2161 - accuracy: 0.9242 - val_loss: 0.1244 - val_accuracy: 0.9596 - 47s/epoch - 143ms/step
+328/328 - 47s - loss: 0.2197 - accuracy: 0.9246 - val_loss: 0.1452 - val_accuracy: 0.9562 - 47s/epoch - 143ms/step
Epoch 2/3
-328/328 - 44s - loss: 0.0984 - accuracy: 0.9625 - val_loss: 0.1315 - val_accuracy: 0.9573 - 44s/epoch - 133ms/step
+328/328 - 43s - loss: 0.0923 - accuracy: 0.9645 - val_loss: 0.1146 - val_accuracy: 0.9630 - 43s/epoch - 132ms/step
Epoch 3/3
-328/328 - 44s - loss: 0.0633 - accuracy: 0.9760 - val_loss: 0.1014 - val_accuracy: 0.9656 - 44s/epoch - 133ms/step
+328/328 - 43s - loss: 0.0686 - accuracy: 0.9753 - val_loss: 0.1057 - val_accuracy: 0.9671 - 43s/epoch - 132ms/step
-<keras.callbacks.History object at 0x7f989fe99c50>
+<keras.callbacks.History object at 0x7fcc28f0ff90>
</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 36.005 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 25.413 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 6fb6b2b253..4cfddb7ac3 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>05:29.401</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:19.263</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>04:36.005</p></td>
+<td><p>04:25.413</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>00:42.701</p></td>
+<td><p>00:42.374</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>00:07.434</p></td>
+<td><p>00:08.112</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>00:03.259</p></td>
+<td><p>00:03.362</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 083acd3331..487eaf54a6 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>00:39.701</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:43.462</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:31.340</p></td>
+<td><p>00:31.786</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>00:07.088</p></td>
+<td><p>00:10.137</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>00:01.266</p></td>
+<td><p>00:01.531</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index ddd5cbcac3..55f72a1aaf 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 0x7f9840862950>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fcba642a680>
</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 8037ed9238..403fdc3f07 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>00:04.018</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:07.677</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,23 +336,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:01.998</p></td>
+<td><p>00:05.359</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>00:00.847</p></td>
+<td><p>00:01.064</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>00:00.506</p></td>
+<td><p>00:00.542</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>00:00.481</p></td>
+<td><p>00:00.529</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>00:00.102</p></td>
+<td><p>00:00.099</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>
@@ -364,7 +364,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.016</p></td>
+<td><p>00:00.015</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index c53b81ca30..f4beba20dd 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/tmp01wk34o2/input0.cc'\nsource_filename = \"/tmp/tmp01wk34o2/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/tmpw0vyrezu/input0.cc'\nsource_filename = \"/tmp/tmpw0vyrezu/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index b0c96ea552..f0d64cb194 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 c7a1013e92..ce001a11c4 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/5d0a16749/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 3446340942..8a1f05df92 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/5d0a16749/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 4ad36f106a..53269aaf7f 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/5d0a16749/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 d5e10c9793..dc3da21804 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/5d0a16749/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 db3fa01b57..da27f8ab19 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/5d0a16749/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 b5fa832b4b..c4f2247bcf 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/5d0a16749/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 82933b8a09..2e37f4008a 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/5d0a16749/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 66d7bf4e5b..31f41da483 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/5d0a16749/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 e6c46b6412..6ff5fe99a5 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/5d0a16749/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 4ba0579aab..777abe94c0 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/5d0a16749/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 de0f76f487..d71f7838ff 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/5d0a16749/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 a85af9076b..955e66be22 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/5d0a16749/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 0016b732c6..d270af03d7 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/5d0a16749/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 412e24f5d8..35b933573f 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/5d0a16749/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 19ec9e744a..38c688cdfa 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/5d0a16749/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 0893e132cb..d3834b38b8 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/5d0a16749/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 31f7f3f5d8..76deea692c 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/5d0a16749/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 ec031d9107..614589e975 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/5d0a16749/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 537047de0d..049d933bf5 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/5d0a16749/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 734b4cfb4f..a7417c0dd5 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/5d0a16749/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 8dd5647113..59c545c287 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/5d0a16749/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 746a37e618..4cb66e9b03 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/5d0a16749/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 5fdb3a8075..c5bc988b81 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/5d0a16749/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 2e927f7bd4..77bebb645c 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/5d0a16749/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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/5d0a16749/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e037ae499/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 dd8446065a..1c18b80b80 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 f1c53661c3..34801706d6 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:21.987</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:21.982</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>00:21.981</p></td>
+<td><p>00:21.975</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 d75c80a465..ca26aacd59 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -569,7 +569,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 23.70s!
+resnet18_v1 inference graph built in 23.07s!
</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 d22f41ad3b..5db74e2535 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -587,7 +587,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 16.73s!
+yolov3-tiny inference graph built in 16.46s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index 5f96785850..81db8d8539 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>01:33.683</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:31.924</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>00:49.857</p></td>
+<td><p>00:48.788</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>00:43.826</p></td>
+<td><p>00:43.135</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 82a4bf120a..e02a858d57 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>00:02.974</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.040</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>00:02.624</p></td>
+<td><p>00:02.643</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>00:00.349</p></td>
+<td><p>00:00.397</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 2b20470003..4e320d2ad9 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>00:00.640</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.744</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>00:00.351</p></td>
+<td><p>00:00.403</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>00:00.288</p></td>
+<td><p>00:00.341</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 e4440ded73..fc1819faab 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -478,9 +478,6 @@ trials, we can load the best schedule from the log file and apply it.</p>
<a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sch</span></a><span class="p">,</span> <a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>.T*E
-</pre></div>
-</div>
</div>
<div class="section" id="inspecting-the-optimized-schedule">
<h2>Inspecting the Optimized Schedule<a class="headerlink" href="#inspecting-the-optimized-schedule" title="Permalink to this headline">¶</a></h2>
@@ -568,7 +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: 93.972 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.509 ms
</pre></div>
</div>
</div>
@@ -642,7 +639,7 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.998 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 12.891 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index 1c5dc5388d..1074856659 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: 10.70/10.70 result: MeasureResult(costs=(0.025083385200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5382473468780518, timestamp=1663360668.9268305) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.93/10.70 result: MeasureResult(costs=(0.0917467508,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6064765453338623, timestamp=1663360670.5603414) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.65/11.65 result: MeasureResult(costs=(0.023040918400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5842595100402832, timestamp=1663360671.6458154) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.77/11.65 result: MeasureResult(costs=(0.1516779954,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5544826984405518, timestamp=1663360674.241922) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.62/11.65 result: MeasureResult(costs=(0.07417769240000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3270087242126465, timestamp=1663360675.6968253) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.79/11.65 result: MeasureResult(costs=(0.150218111,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5316474437713623, timestamp=1663360678.8133185) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.85/11.65 result: MeasureResult(costs=(0.31656924760000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.191319704055786, timestamp=1663360684.6076777) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 10.46/11.65 result: MeasureResult(costs=(0.025653009400000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5560874938964844, timestamp=1663360685.183841) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.62/11.65 result: MeasureResult(costs=(0.16537150939999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7618985176086426, timestamp=1663360688.0655835) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.66/11.65 result: MeasureResult(costs=(0.1007671628,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.73246431350708, timestamp=1663360689.8412776) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 10.80/10.80 result: MeasureResult(costs=(0.0248582544,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.533137321472168, timestamp=1663363264.1401277) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.87/10.80 result: MeasureResult(costs=(0.09344741259999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6491446495056152, timestamp=1663363265.8013742) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.79/11.79 result: MeasureResult(costs=(0.022762087,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5608391761779785, timestamp=1663363266.8792121) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.87/11.79 result: MeasureResult(costs=(0.14323182240000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4019856452941895, timestamp=1663363269.8742616) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.33/11.79 result: MeasureResult(costs=(0.08062546620000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.434044361114502, timestamp=1663363271.4348295) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.82/11.79 result: MeasureResult(costs=(0.147721219,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4914937019348145, timestamp=1663363274.5062902) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.86/11.79 result: MeasureResult(costs=(0.31339139239999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.134791374206543, timestamp=1663363279.6860335) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 10.51/11.79 result: MeasureResult(costs=(0.025543893800000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5579173564910889, timestamp=1663363280.256034) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.92/11.79 result: MeasureResult(costs=(0.1396194626,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3373494148254395, timestamp=1663363282.7134404) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.79/11.79 result: MeasureResult(costs=(0.096203392,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6488864421844482, timestamp=1663363284.419518) [('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 b239e99250..1e7dc24d49 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -547,7 +547,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 518.1210708800063, 'median': 517.8918785499718, 'std': 2.360912984889522}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 509.63054053000286, 'median': 510.2050166499964, 'std': 1.692568446876928}
</pre></div>
</div>
</div>
@@ -699,178 +699,178 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 17.49/ 17.49 GFLOPS | Progress: (4/20) | 6.53 s
-[Task 1/25] Current/Best: 6.09/ 17.49 GFLOPS | Progress: (8/20) | 9.65 s
-[Task 1/25] Current/Best: 11.17/ 21.53 GFLOPS | Progress: (12/20) | 12.20 s
-[Task 1/25] Current/Best: 16.37/ 22.14 GFLOPS | Progress: (16/20) | 13.92 s
-[Task 1/25] Current/Best: 11.34/ 23.27 GFLOPS | Progress: (20/20) | 15.71 s Done.
+[Task 1/25] Current/Best: 17.40/ 17.40 GFLOPS | Progress: (4/20) | 6.46 s
+[Task 1/25] Current/Best: 6.02/ 17.40 GFLOPS | Progress: (8/20) | 9.55 s
+[Task 1/25] Current/Best: 11.19/ 21.96 GFLOPS | Progress: (12/20) | 12.07 s
+[Task 1/25] Current/Best: 16.42/ 22.14 GFLOPS | Progress: (16/20) | 13.77 s
+[Task 1/25] Current/Best: 11.33/ 23.61 GFLOPS | Progress: (20/20) | 15.57 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.16/ 12.16 GFLOPS | Progress: (4/20) | 4.01 s
-[Task 2/25] Current/Best: 12.44/ 18.28 GFLOPS | Progress: (8/20) | 5.33 s
-[Task 2/25] Current/Best: 20.86/ 20.86 GFLOPS | Progress: (12/20) | 6.70 s
-[Task 2/25] Current/Best: 11.18/ 20.86 GFLOPS | Progress: (16/20) | 8.00 s
-[Task 2/25] Current/Best: 16.69/ 20.86 GFLOPS | Progress: (20/20) | 9.63 s Done.
+[Task 2/25] Current/Best: 12.05/ 12.45 GFLOPS | Progress: (4/20) | 3.97 s
+[Task 2/25] Current/Best: 12.41/ 18.48 GFLOPS | Progress: (8/20) | 5.28 s
+[Task 2/25] Current/Best: 20.33/ 20.33 GFLOPS | Progress: (12/20) | 6.60 s
+[Task 2/25] Current/Best: 10.68/ 20.33 GFLOPS | Progress: (16/20) | 7.92 s
+[Task 2/25] Current/Best: 16.62/ 20.33 GFLOPS | Progress: (20/20) | 9.56 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/ 10.05 GFLOPS | Progress: (4/20) | 5.95 s
-[Task 3/25] Current/Best: 15.13/ 16.85 GFLOPS | Progress: (8/20) | 7.92 s
-[Task 3/25] Current/Best: 14.95/ 16.85 GFLOPS | Progress: (12/20) | 9.67 s
-[Task 3/25] Current/Best: 6.82/ 22.84 GFLOPS | Progress: (16/20) | 11.69 s
-[Task 3/25] Current/Best: 11.00/ 22.84 GFLOPS | Progress: (20/20) | 16.35 s Done.
+[Task 3/25] Current/Best: 1.63/ 10.19 GFLOPS | Progress: (4/20) | 5.89 s
+[Task 3/25] Current/Best: 15.24/ 16.86 GFLOPS | Progress: (8/20) | 7.83 s
+[Task 3/25] Current/Best: 14.99/ 16.86 GFLOPS | Progress: (12/20) | 9.57 s
+[Task 3/25] Current/Best: 6.83/ 23.28 GFLOPS | Progress: (16/20) | 11.57 s
+[Task 3/25] Current/Best: 11.08/ 23.28 GFLOPS | Progress: (20/20) | 16.23 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.05/ 18.90 GFLOPS | Progress: (4/20) | 2.50 s
-[Task 4/25] Current/Best: 6.43/ 18.90 GFLOPS | Progress: (8/20) | 7.36 s
-[Task 4/25] Current/Best: 20.69/ 20.69 GFLOPS | Progress: (12/20) | 12.39 s
-[Task 4/25] Current/Best: 15.81/ 20.69 GFLOPS | Progress: (16/20) | 14.87 s
-[Task 4/25] Current/Best: 12.59/ 20.69 GFLOPS | Progress: (20/20) | 16.89 s Done.
+[Task 4/25] Current/Best: 8.97/ 18.79 GFLOPS | Progress: (4/20) | 2.45 s
+[Task 4/25] Current/Best: 6.42/ 18.79 GFLOPS | Progress: (8/20) | 7.22 s
+[Task 4/25] Current/Best: 21.33/ 21.33 GFLOPS | Progress: (12/20) | 12.14 s
+[Task 4/25] Current/Best: 16.15/ 21.33 GFLOPS | Progress: (16/20) | 14.62 s
+[Task 4/25] Current/Best: 12.90/ 21.33 GFLOPS | Progress: (20/20) | 16.68 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.08/ 9.74 GFLOPS | Progress: (4/20) | 2.69 s
-[Task 5/25] Current/Best: 11.32/ 11.38 GFLOPS | Progress: (8/20) | 4.78 s
-[Task 5/25] Current/Best: 9.64/ 17.86 GFLOPS | Progress: (12/20) | 8.09 s
-[Task 5/25] Current/Best: 11.19/ 22.18 GFLOPS | Progress: (16/20) | 9.55 s
-[Task 5/25] Current/Best: 11.83/ 22.18 GFLOPS | Progress: (20/20) | 11.48 s Done.
+[Task 5/25] Current/Best: 9.44/ 10.05 GFLOPS | Progress: (4/20) | 2.62 s
+[Task 5/25] Current/Best: 11.69/ 11.69 GFLOPS | Progress: (8/20) | 4.69 s
+[Task 5/25] Current/Best: 10.05/ 17.95 GFLOPS | Progress: (12/20) | 7.90 s
+[Task 5/25] Current/Best: 11.68/ 22.10 GFLOPS | Progress: (16/20) | 9.37 s
+[Task 5/25] Current/Best: 11.95/ 22.10 GFLOPS | Progress: (20/20) | 11.28 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.05/ 20.00 GFLOPS | Progress: (4/20) | 4.27 s
-[Task 6/25] Current/Best: 18.78/ 20.00 GFLOPS | Progress: (8/20) | 6.05 s
-[Task 6/25] Current/Best: 13.23/ 20.00 GFLOPS | Progress: (12/20) | 8.08 s
-[Task 6/25] Current/Best: 19.38/ 20.00 GFLOPS | Progress: (16/20) | 10.39 s
-[Task 6/25] Current/Best: 3.70/ 20.00 GFLOPS | Progress: (20/20) | 13.02 s Done.
+[Task 6/25] Current/Best: 11.91/ 19.91 GFLOPS | Progress: (4/20) | 4.15 s
+[Task 6/25] Current/Best: 18.91/ 19.91 GFLOPS | Progress: (8/20) | 5.95 s
+[Task 6/25] Current/Best: 13.16/ 19.91 GFLOPS | Progress: (12/20) | 7.95 s
+[Task 6/25] Current/Best: 19.25/ 19.91 GFLOPS | Progress: (16/20) | 10.20 s
+[Task 6/25] Current/Best: 3.74/ 19.91 GFLOPS | Progress: (20/20) | 12.80 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 9.76/ 12.00 GFLOPS | Progress: (4/20) | 3.72 s
-[Task 7/25] Current/Best: 18.88/ 19.35 GFLOPS | Progress: (8/20) | 5.29 s
-[Task 7/25] Current/Best: 16.01/ 19.52 GFLOPS | Progress: (12/20) | 7.24 s
-[Task 7/25] Current/Best: 12.12/ 19.53 GFLOPS | Progress: (16/20) | 9.35 s
-[Task 7/25] Current/Best: 6.10/ 20.38 GFLOPS | Progress: (20/20) | 11.88 s Done.
+[Task 7/25] Current/Best: 9.77/ 12.12 GFLOPS | Progress: (4/20) | 3.74 s
+[Task 7/25] Current/Best: 19.30/ 20.09 GFLOPS | Progress: (8/20) | 5.29 s
+[Task 7/25] Current/Best: 16.00/ 20.09 GFLOPS | Progress: (12/20) | 7.23 s
+[Task 7/25] Current/Best: 12.18/ 20.09 GFLOPS | Progress: (16/20) | 9.32 s
+[Task 7/25] Current/Best: 6.13/ 20.23 GFLOPS | Progress: (20/20) | 11.83 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 10.15/ 13.94 GFLOPS | Progress: (4/20) | 2.98 s
-[Task 8/25] Current/Best: 9.02/ 13.94 GFLOPS | Progress: (8/20) | 8.34 s
-[Task 8/25] Current/Best: 12.81/ 13.94 GFLOPS | Progress: (12/20) | 15.01 s
-[Task 8/25] Current/Best: 19.13/ 19.13 GFLOPS | Progress: (16/20) | 17.19 s
-[Task 8/25] Current/Best: 18.58/ 19.13 GFLOPS | Progress: (20/20) | 24.55 s Done.
+[Task 8/25] Current/Best: 10.50/ 14.10 GFLOPS | Progress: (4/20) | 2.91 s
+[Task 8/25] Current/Best: 9.58/ 14.10 GFLOPS | Progress: (8/20) | 8.05 s
+[Task 8/25] Current/Best: 13.20/ 14.10 GFLOPS | Progress: (12/20) | 14.66 s
+[Task 8/25] Current/Best: 19.09/ 19.09 GFLOPS | Progress: (16/20) | 16.78 s
+[Task 8/25] Current/Best: 19.22/ 19.22 GFLOPS | Progress: (20/20) | 23.88 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.28/ 14.28 GFLOPS | Progress: (4/20) | 12.03 s
-[Task 9/25] Current/Best: 22.36/ 22.36 GFLOPS | Progress: (8/20) | 13.87 s
-[Task 9/25] Current/Best: 7.97/ 22.36 GFLOPS | Progress: (12/20) | 16.49 s
-[Task 9/25] Current/Best: 17.69/ 22.36 GFLOPS | Progress: (16/20) | 19.29 s
-[Task 9/25] Current/Best: 8.95/ 22.36 GFLOPS | Progress: (20/20) | 28.22 s
+[Task 9/25] Current/Best: 14.39/ 14.39 GFLOPS | Progress: (4/20) | 11.98 s
+[Task 9/25] Current/Best: 23.08/ 23.08 GFLOPS | Progress: (8/20) | 13.80 s
+[Task 9/25] Current/Best: 7.81/ 23.08 GFLOPS | Progress: (12/20) | 16.39 s
+[Task 9/25] Current/Best: 17.83/ 23.08 GFLOPS | Progress: (16/20) | 19.27 s
+[Task 9/25] Current/Best: 8.95/ 23.08 GFLOPS | Progress: (20/20) | 28.04 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.15/ 18.15 GFLOPS | Progress: (4/20) | 2.65 s
-[Task 10/25] Current/Best: 15.73/ 18.15 GFLOPS | Progress: (8/20) | 4.33 s
-[Task 10/25] Current/Best: 11.40/ 18.81 GFLOPS | Progress: (12/20) | 5.92 s
-[Task 10/25] Current/Best: 19.01/ 20.07 GFLOPS | Progress: (16/20) | 7.05 s
-[Task 10/25] Current/Best: 8.44/ 20.07 GFLOPS | Progress: (20/20) | 8.61 s Done.
+[Task 10/25] Current/Best: 18.25/ 18.25 GFLOPS | Progress: (4/20) | 2.60 s
+[Task 10/25] Current/Best: 15.33/ 18.25 GFLOPS | Progress: (8/20) | 4.25 s
+[Task 10/25] Current/Best: 11.54/ 18.87 GFLOPS | Progress: (12/20) | 5.82 s
+[Task 10/25] Current/Best: 19.02/ 20.31 GFLOPS | Progress: (16/20) | 6.92 s
+[Task 10/25] Current/Best: 8.62/ 20.31 GFLOPS | Progress: (20/20) | 8.46 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 10.84/ 18.07 GFLOPS | Progress: (4/20) | 3.54 s
-[Task 11/25] Current/Best: 14.22/ 18.07 GFLOPS | Progress: (8/20) | 6.42 s
-[Task 11/25] Current/Best: 15.93/ 18.07 GFLOPS | Progress: (12/20) | 8.57 s
-[Task 11/25] Current/Best: 11.80/ 20.63 GFLOPS | Progress: (16/20) | 11.52 s
-[Task 11/25] Current/Best: 18.07/ 20.63 GFLOPS | Progress: (20/20) | 13.71 s Done.
+[Task 11/25] Current/Best: 10.89/ 18.15 GFLOPS | Progress: (4/20) | 3.48 s
+[Task 11/25] Current/Best: 14.78/ 18.15 GFLOPS | Progress: (8/20) | 6.34 s
+[Task 11/25] Current/Best: 15.90/ 18.15 GFLOPS | Progress: (12/20) | 8.44 s
+[Task 11/25] Current/Best: 11.86/ 20.62 GFLOPS | Progress: (16/20) | 11.45 s
+[Task 11/25] Current/Best: 17.93/ 20.62 GFLOPS | Progress: (20/20) | 13.58 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.77/ 18.11 GFLOPS | Progress: (4/20) | 5.91 s
-[Task 12/25] Current/Best: 4.96/ 18.11 GFLOPS | Progress: (8/20) | 9.95 s
-[Task 12/25] Current/Best: 19.05/ 19.05 GFLOPS | Progress: (12/20) | 12.00 s
-[Task 12/25] Current/Best: 14.57/ 19.05 GFLOPS | Progress: (16/20) | 14.99 s
-[Task 12/25] Current/Best: 15.16/ 19.05 GFLOPS | Progress: (20/20) | 16.99 s Done.
+[Task 12/25] Current/Best: 7.80/ 17.89 GFLOPS | Progress: (4/20) | 5.75 s
+[Task 12/25] Current/Best: 5.13/ 17.89 GFLOPS | Progress: (8/20) | 9.72 s
+[Task 12/25] Current/Best: 18.79/ 18.79 GFLOPS | Progress: (12/20) | 11.72 s
+[Task 12/25] Current/Best: 15.17/ 18.79 GFLOPS | Progress: (16/20) | 14.70 s
+[Task 12/25] Current/Best: 15.06/ 18.79 GFLOPS | Progress: (20/20) | 16.69 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.61/ 17.27 GFLOPS | Progress: (4/20) | 3.87 s
-[Task 13/25] Current/Best: 15.52/ 20.59 GFLOPS | Progress: (8/20) | 6.52 s
-[Task 13/25] Current/Best: 18.65/ 21.20 GFLOPS | Progress: (12/20) | 9.60 s
-[Task 13/25] Current/Best: 12.15/ 21.20 GFLOPS | Progress: (16/20) | 13.09 s
-[Task 13/25] Current/Best: 17.71/ 21.20 GFLOPS | Progress: (20/20) | 15.51 s Done.
+[Task 13/25] Current/Best: 8.39/ 17.23 GFLOPS | Progress: (4/20) | 3.85 s
+[Task 13/25] Current/Best: 15.14/ 20.66 GFLOPS | Progress: (8/20) | 6.49 s
+[Task 13/25] Current/Best: 18.64/ 21.70 GFLOPS | Progress: (12/20) | 9.53 s
+[Task 13/25] Current/Best: 12.27/ 21.70 GFLOPS | Progress: (16/20) | 12.99 s
+[Task 13/25] Current/Best: 17.66/ 21.70 GFLOPS | Progress: (20/20) | 15.35 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 12.12/ 13.07 GFLOPS | Progress: (4/20) | 3.51 s
-[Task 14/25] Current/Best: 6.07/ 13.11 GFLOPS | Progress: (8/20) | 5.77 s
-[Task 14/25] Current/Best: 19.21/ 19.21 GFLOPS | Progress: (12/20) | 8.50 s
-[Task 14/25] Current/Best: 15.63/ 19.21 GFLOPS | Progress: (16/20) | 10.21 s Done.
+[Task 14/25] Current/Best: 12.08/ 13.33 GFLOPS | Progress: (4/20) | 3.45 s
+[Task 14/25] Current/Best: 6.10/ 13.33 GFLOPS | Progress: (8/20) | 5.63 s
+[Task 14/25] Current/Best: 19.60/ 19.60 GFLOPS | Progress: (12/20) | 8.31 s
+[Task 14/25] Current/Best: 16.28/ 19.60 GFLOPS | Progress: (16/20) | 9.99 s Done.
-[Task 14/25] Current/Best: 17.02/ 19.21 GFLOPS | Progress: (20/20) | 11.98 s
+[Task 14/25] Current/Best: 16.91/ 19.60 GFLOPS | Progress: (20/20) | 11.75 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 14.78/ 16.95 GFLOPS | Progress: (4/20) | 2.82 s
-[Task 15/25] Current/Best: 12.56/ 17.80 GFLOPS | Progress: (8/20) | 4.15 s
-[Task 15/25] Current/Best: 9.67/ 20.61 GFLOPS | Progress: (12/20) | 6.45 s
-[Task 15/25] Current/Best: 19.69/ 20.61 GFLOPS | Progress: (16/20) | 9.64 s
-[Task 15/25] Current/Best: 9.25/ 20.61 GFLOPS | Progress: (20/20) | 10.68 s
+[Task 15/25] Current/Best: 15.61/ 17.10 GFLOPS | Progress: (4/20) | 2.76 s
+[Task 15/25] Current/Best: 12.66/ 17.72 GFLOPS | Progress: (8/20) | 4.09 s
+[Task 15/25] Current/Best: 9.96/ 20.73 GFLOPS | Progress: (12/20) | 6.37 s
+[Task 15/25] Current/Best: 20.02/ 20.73 GFLOPS | Progress: (16/20) | 9.82 s
+[Task 15/25] Current/Best: 9.49/ 20.73 GFLOPS | Progress: (20/20) | 10.85 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 17.70/ 17.70 GFLOPS | Progress: (4/20) | 3.07 s
-[Task 16/25] Current/Best: 3.03/ 17.70 GFLOPS | Progress: (8/20) | 4.70 s
-[Task 16/25] Current/Best: 18.52/ 19.40 GFLOPS | Progress: (12/20) | 5.94 s
-[Task 16/25] Current/Best: 17.60/ 19.40 GFLOPS | Progress: (16/20) | 7.35 s
-[Task 16/25] Current/Best: 9.93/ 19.76 GFLOPS | Progress: (20/20) | 9.55 s Done.
+[Task 16/25] Current/Best: 19.25/ 19.25 GFLOPS | Progress: (4/20) | 3.09 s
+[Task 16/25] Current/Best: 3.02/ 19.25 GFLOPS | Progress: (8/20) | 4.73 s
+[Task 16/25] Current/Best: 18.36/ 19.25 GFLOPS | Progress: (12/20) | 5.95 s
+[Task 16/25] Current/Best: 18.48/ 19.25 GFLOPS | Progress: (16/20) | 7.34 s
+[Task 16/25] Current/Best: 9.96/ 21.18 GFLOPS | Progress: (20/20) | 9.50 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 12.40/ 16.11 GFLOPS | Progress: (4/20) | 4.93 s
-[Task 17/25] Current/Best: 12.76/ 22.73 GFLOPS | Progress: (8/20) | 7.78 s
-[Task 17/25] Current/Best: 16.39/ 22.73 GFLOPS | Progress: (12/20) | 9.90 s
-[Task 17/25] Current/Best: 16.45/ 22.73 GFLOPS | Progress: (16/20) | 12.16 s
-[Task 17/25] Current/Best: 9.97/ 22.73 GFLOPS | Progress: (20/20) | 14.37 s Done.
+[Task 17/25] Current/Best: 12.95/ 16.14 GFLOPS | Progress: (4/20) | 4.87 s
+[Task 17/25] Current/Best: 12.73/ 22.86 GFLOPS | Progress: (8/20) | 7.80 s
+[Task 17/25] Current/Best: 16.51/ 22.86 GFLOPS | Progress: (12/20) | 9.91 s
+[Task 17/25] Current/Best: 16.44/ 22.86 GFLOPS | Progress: (16/20) | 12.14 s
+[Task 17/25] Current/Best: 9.96/ 22.86 GFLOPS | Progress: (20/20) | 14.32 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 10.33/ 17.24 GFLOPS | Progress: (4/20) | 3.93 s
-[Task 18/25] Current/Best: 10.60/ 18.46 GFLOPS | Progress: (8/20) | 7.71 s
-[Task 18/25] Current/Best: 18.61/ 18.61 GFLOPS | Progress: (12/20) | 9.69 s
-[Task 18/25] Current/Best: 10.04/ 18.61 GFLOPS | Progress: (16/20) | 13.63 s
-[Task 18/25] Current/Best: 20.48/ 20.48 GFLOPS | Progress: (20/20) | 15.18 s Done.
+[Task 18/25] Current/Best: 10.19/ 16.04 GFLOPS | Progress: (4/20) | 3.90 s
+[Task 18/25] Current/Best: 10.57/ 18.55 GFLOPS | Progress: (8/20) | 7.63 s
+[Task 18/25] Current/Best: 18.87/ 18.87 GFLOPS | Progress: (12/20) | 9.61 s
+[Task 18/25] Current/Best: 10.04/ 18.87 GFLOPS | Progress: (16/20) | 13.54 s
+[Task 18/25] Current/Best: 20.34/ 20.34 GFLOPS | Progress: (20/20) | 15.11 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 7.12/ 19.61 GFLOPS | Progress: (4/20) | 6.33 s
-[Task 19/25] Current/Best: 2.69/ 19.61 GFLOPS | Progress: (8/20) | 9.67 s
-[Task 19/25] Current/Best: 18.10/ 20.22 GFLOPS | Progress: (12/20) | 12.70 s
-[Task 19/25] Current/Best: 13.39/ 20.74 GFLOPS | Progress: (16/20) | 15.73 s
-[Task 19/25] Current/Best: 2.69/ 21.94 GFLOPS | Progress: (20/20) | 18.59 s Done.
+[Task 19/25] Current/Best: 7.08/ 19.47 GFLOPS | Progress: (4/20) | 6.15 s
+[Task 19/25] Current/Best: 2.69/ 19.47 GFLOPS | Progress: (8/20) | 9.46 s
+[Task 19/25] Current/Best: 17.82/ 20.64 GFLOPS | Progress: (12/20) | 12.44 s
+[Task 19/25] Current/Best: 13.48/ 20.64 GFLOPS | Progress: (16/20) | 15.50 s
+[Task 19/25] Current/Best: 2.69/ 21.90 GFLOPS | Progress: (20/20) | 18.32 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 8.96/ 14.97 GFLOPS | Progress: (4/20) | 3.43 s Done.
+[Task 20/25] Current/Best: 9.01/ 15.28 GFLOPS | Progress: (4/20) | 3.37 s Done.
Done.
-[Task 20/25] Current/Best: 9.72/ 14.97 GFLOPS | Progress: (8/20) | 6.87 s
-[Task 20/25] Current/Best: 2.32/ 14.97 GFLOPS | Progress: (12/20) | 10.88 s
-[Task 20/25] Current/Best: 10.87/ 14.97 GFLOPS | Progress: (16/20) | 14.86 s
-[Task 20/25] Current/Best: 11.53/ 21.52 GFLOPS | Progress: (20/20) | 17.02 s
+[Task 20/25] Current/Best: 9.83/ 15.28 GFLOPS | Progress: (8/20) | 6.96 s
+[Task 20/25] Current/Best: 2.32/ 15.28 GFLOPS | Progress: (12/20) | 10.98 s
+[Task 20/25] Current/Best: 11.14/ 15.28 GFLOPS | Progress: (16/20) | 14.92 s
+[Task 20/25] Current/Best: 11.49/ 21.40 GFLOPS | Progress: (20/20) | 17.08 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.31/ 17.58 GFLOPS | Progress: (4/20) | 3.36 s
-[Task 21/25] Current/Best: 14.52/ 17.58 GFLOPS | Progress: (8/20) | 5.01 s
-[Task 21/25] Current/Best: 1.61/ 17.58 GFLOPS | Progress: (12/20) | 7.21 s
-[Task 21/25] Current/Best: 15.82/ 17.58 GFLOPS | Progress: (16/20) | 10.82 s
-[Task 21/25] Current/Best: 4.44/ 17.58 GFLOPS | Progress: (20/20) | 18.29 s
+[Task 21/25] Current/Best: 6.31/ 17.52 GFLOPS | Progress: (4/20) | 3.34 s
+[Task 21/25] Current/Best: 14.53/ 17.52 GFLOPS | Progress: (8/20) | 4.99 s
+[Task 21/25] Current/Best: 1.61/ 17.52 GFLOPS | Progress: (12/20) | 7.18 s
+[Task 21/25] Current/Best: 16.06/ 17.52 GFLOPS | Progress: (16/20) | 10.76 s
+[Task 21/25] Current/Best: 4.44/ 17.52 GFLOPS | Progress: (20/20) | 18.16 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 2.70/ 16.62 GFLOPS | Progress: (4/20) | 2.79 s
-[Task 22/25] Current/Best: 9.22/ 20.76 GFLOPS | Progress: (8/20) | 4.84 s
-[Task 22/25] Current/Best: 19.81/ 20.76 GFLOPS | Progress: (12/20) | 7.28 s
-[Task 22/25] Current/Best: 15.18/ 20.76 GFLOPS | Progress: (16/20) | 9.47 s
-[Task 22/25] Current/Best: 13.26/ 20.76 GFLOPS | Progress: (20/20) | 11.24 s Done.
+[Task 22/25] Current/Best: 2.70/ 16.78 GFLOPS | Progress: (4/20) | 2.72 s
+[Task 22/25] Current/Best: 8.93/ 20.99 GFLOPS | Progress: (8/20) | 4.69 s
+[Task 22/25] Current/Best: 19.77/ 20.99 GFLOPS | Progress: (12/20) | 7.09 s
+[Task 22/25] Current/Best: 15.29/ 20.99 GFLOPS | Progress: (16/20) | 9.23 s
+[Task 22/25] Current/Best: 12.96/ 20.99 GFLOPS | Progress: (20/20) | 10.99 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 16.50/ 19.44 GFLOPS | Progress: (4/20) | 3.34 s
-[Task 23/25] Current/Best: 14.05/ 19.79 GFLOPS | Progress: (8/20) | 6.80 s
-[Task 23/25] Current/Best: 20.30/ 21.28 GFLOPS | Progress: (12/20) | 8.71 s
-[Task 23/25] Current/Best: 6.30/ 21.28 GFLOPS | Progress: (16/20) | 15.85 s
-[Task 23/25] Current/Best: 7.29/ 21.28 GFLOPS | Progress: (20/20) | 20.15 s Done.
+[Task 23/25] Current/Best: 15.58/ 19.64 GFLOPS | Progress: (4/20) | 3.35 s
+[Task 23/25] Current/Best: 13.75/ 19.82 GFLOPS | Progress: (8/20) | 6.66 s
+[Task 23/25] Current/Best: 20.37/ 21.50 GFLOPS | Progress: (12/20) | 8.54 s
+[Task 23/25] Current/Best: 6.47/ 21.50 GFLOPS | Progress: (16/20) | 15.65 s
+[Task 23/25] Current/Best: 7.57/ 21.50 GFLOPS | Progress: (20/20) | 19.92 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.09/ 8.09 GFLOPS | Progress: (4/20) | 11.88 s
-[Task 24/25] Current/Best: 1.85/ 8.09 GFLOPS | Progress: (8/20) | 23.00 s
-[Task 24/25] Current/Best: 3.56/ 8.09 GFLOPS | Progress: (12/20) | 34.59 s Done.
+[Task 24/25] Current/Best: 8.50/ 8.50 GFLOPS | Progress: (4/20) | 11.81 s
+[Task 24/25] Current/Best: 1.96/ 8.50 GFLOPS | Progress: (8/20) | 22.88 s
+[Task 24/25] Current/Best: 4.04/ 8.50 GFLOPS | Progress: (12/20) | 34.46 s Done.
-[Task 24/25] Current/Best: 6.19/ 8.62 GFLOPS | Progress: (16/20) | 40.36 s
-[Task 24/25] Current/Best: 2.89/ 8.62 GFLOPS | Progress: (20/20) | 46.48 s Done.
+[Task 24/25] Current/Best: 6.06/ 8.50 GFLOPS | Progress: (16/20) | 40.15 s
+[Task 24/25] Current/Best: 2.95/ 8.50 GFLOPS | Progress: (20/20) | 46.11 s Done.
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 1.55/ 2.85 GFLOPS | Progress: (4/20) | 11.64 s
-[Task 25/25] Current/Best: 5.36/ 7.50 GFLOPS | Progress: (8/20) | 22.93 s
-[Task 25/25] Current/Best: 5.85/ 7.50 GFLOPS | Progress: (12/20) | 34.28 s
-[Task 25/25] Current/Best: 5.77/ 9.10 GFLOPS | Progress: (16/20) | 36.18 s
-[Task 25/25] Current/Best: 2.86/ 9.10 GFLOPS | Progress: (20/20) | 46.91 s
+[Task 25/25] Current/Best: 1.55/ 2.88 GFLOPS | Progress: (4/20) | 11.63 s
+[Task 25/25] Current/Best: 5.84/ 7.66 GFLOPS | Progress: (8/20) | 22.91 s
+[Task 25/25] Current/Best: 5.89/ 7.66 GFLOPS | Progress: (12/20) | 34.41 s
+[Task 25/25] Current/Best: 5.68/ 9.20 GFLOPS | Progress: (16/20) | 36.16 s
+[Task 25/25] Current/Best: 2.84/ 9.20 GFLOPS | Progress: (20/20) | 46.89 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -972,8 +972,8 @@ 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': 411.1838606100173, 'median': 411.4897552000457, 'std': 1.000769137550157}
-unoptimized: {'mean': 518.1210708800063, 'median': 517.8918785499718, 'std': 2.360912984889522}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 410.4343596400008, 'median': 410.54452120000633, 'std': 0.7799474279614487}
+unoptimized: {'mean': 509.63054053000286, 'median': 510.2050166499964, 'std': 1.692568446876928}
</pre></div>
</div>
</div>
@@ -987,7 +987,7 @@ 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 38.588 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 30.264 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 f588cffaa3..83194f1f34 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>1.245e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.304e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 5edd8430ba..2b4a595631 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, 0x166b8150)), stage(b, placeholder(b, 0x1fcf2f90)), 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=[ [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x7560f10)), stage(b, placeholder(b, 0xca9f5b0)), 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=[it [...]
</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 512ab74e06..aada00a19f 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>13:50.077</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:40.694</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,54 +336,54 @@
</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>10:38.588</p></td>
+<td><p>10:30.264</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>01:09.998</p></td>
+<td><p>01:12.891</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:03.301</p></td>
+<td><p>00:59.116</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>00:32.041</p></td>
+<td><p>00:32.418</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>00:24.496</p></td>
+<td><p>00:23.836</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>00:00.759</p></td>
+<td><p>00:01.291</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>00:00.723</p></td>
+<td><p>00:00.713</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>00:00.163</p></td>
+<td><p>00:00.156</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>00:00.004</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="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="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-even"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
+<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>
<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 652a21725a..5d009ca2e8 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -538,7 +538,7 @@ helper function to run a profile of the TVM generated code.</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
naive: 0.000007
</pre></div>
</div>
@@ -627,7 +627,7 @@ factor to be the number of threads on your CPU.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000024
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>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"),
@@ -660,10 +660,10 @@ factor to be the number of threads on your CPU.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 8.40468000205874e-06 1.0
- naive 6.772499999999999e-06 0.8058010535012712
-parallel 7.1025e-06 0.8450648922100819
- vector 2.44631e-05 2.9106521597500112
+ numpy 7.419700000355078e-06 1.0
+ naive 6.662500000000001e-06 0.8979473563191449
+parallel 6.951400000000001e-06 0.9368842405578842
+ vector 2.4550700000000002e-05 3.30885345752862
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -979,7 +979,7 @@ 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: 0.018998
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019511
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1020,7 +1020,7 @@ optimizations.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.554445
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.257721
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1085,7 +1085,7 @@ schedule.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.318267
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.303514
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1144,7 +1144,7 @@ already cache friendly from our previous optimizations.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.343458
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.347067
@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], []),
@@ -1199,7 +1199,7 @@ more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.126368
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.117817
@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 @@ optimized schedule.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.110780
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.108332
@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], []),
@@ -1349,7 +1349,7 @@ to `C</cite> when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.111568
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110473
@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], []),
@@ -1416,7 +1416,7 @@ of thread-level parallelization.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.147295
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.144252
@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], []),
@@ -1478,13 +1478,13 @@ 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 3.5544454010999997 1.0
- blocking 0.3182670935 0.0895405773855762
- vectorization 0.34345757870000004 0.09662761414022837
-loop permutation 0.12636830540000002 0.03555218638634669
- array packing 0.11078039839999998 0.031166718263759684
- block caching 0.1115676855 0.031388211917806635
- parallelization 0.1472945234 0.041439523407622615
+ none 3.2577210449999994 1.0
+ blocking 0.3035144557 0.09316772415668884
+ vectorization 0.34706732529999995 0.10653684600548725
+loop permutation 0.1178172596 0.03616554578263469
+ array packing 0.108331731 0.03325383895784116
+ block caching 0.11047277930000002 0.03391106168207844
+ parallelization 0.144251878 0.044279996969476564
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1516,7 +1516,6 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.301 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>