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 2022/12/16 01:00:01 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@cdb4eea138789f7021dfc10e124bfd3127241e60)
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 a9bce207ec deploying docs (apache/tvm@cdb4eea138789f7021dfc10e124bfd3127241e60)
a9bce207ec is described below
commit a9bce207ec0199ba8e1c8cef00a5c72ab034fac8
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri Dec 16 00:59:55 2022 +0000
deploying docs (apache/tvm@cdb4eea138789f7021dfc10e124bfd3127241e60)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 329141 -> 298414 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 22792 -> 21680 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 44 +-
.../deploy_models/deploy_model_on_adreno.rst.txt | 4 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 4 +-
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 1045 ++++++++++++--------
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 468 ++++-----
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 4 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 60 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 24 +-
.../tutorial/tensor_expr_get_started.rst.txt | 49 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 15 +-
docs/how_to/compile_models/from_pytorch.html | 10 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 24 +-
.../deploy_models/deploy_model_on_adreno.html | 4 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 38 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 36 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 1045 ++++++++++++--------
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 468 ++++-----
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 5 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 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 | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 4 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 274 +++--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 24 +-
docs/tutorial/tensor_expr_get_started.html | 45 +-
129 files changed, 2492 insertions(+), 2182 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 9c86215278..b0585eecfd 100644
Binary files a/docs/_images/sphx_glr_micro_train_001.png and b/docs/_images/sphx_glr_micro_train_001.png differ
diff --git a/docs/_images/sphx_glr_micro_train_thumb.png b/docs/_images/sphx_glr_micro_train_thumb.png
index 839a4f5975..9b391c104b 100644
Binary files a/docs/_images/sphx_glr_micro_train_thumb.png and b/docs/_images/sphx_glr_micro_train_thumb.png differ
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index 370023b1a1..bcfc60a6f8 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 9.753 seconds)
+ **Total running time of the script:** ( 1 minutes 10.318 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 d84df4a264..b011a12040 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 960ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 948ms/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 5586671bfb..0a9f123b4a 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.zip27499e08-8655-4630-ac33-88bfae0ee171 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipf4f236f0-5498-4417-86df-dda928cf54a8 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 1da475d940..07e9b5fff9 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]
19%|#9 | 7.99M/41.5M [00:00<00:00, 58.0MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 58.9MB/s]
48%|####8 | 20.0M/41.5M [00:00<00:00, 55.3MB/s]
61%|###### | 25.2M/41.5M [00:00<00:00, 43.0MB/s]
82%|########2 | 34.1M/41.5M [00:00<00:00, 45.9MB/s]
95%|#########5| 39.5M/41.5M [00:00<00:00, 48.7MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 49.0MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 42.7MB/s]
32%|###1 | 13.2M/41.5M [00:00<00:00, 56.9MB/s]
46%|####5 | 19.0M/41.5M [00:00<00:00, 36.1MB/s]
56%|#####5 | 23.1M/41.5M [00:00<00:00, 31.4MB/s]
65%|######4 | 26.9M/41.5M [00:00<00:00, 33.2MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 38.2MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 38.5MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 38.3MB/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 f4ed7298e1..21e679fb8e 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -98,7 +98,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#8 | 8.07M/44.7M [00:00<00:00, 84.6MB/s]
36%|###6 | 16.1M/44.7M [00:00<00:00, 66.1MB/s]
62%|######2 | 27.8M/44.7M [00:00<00:00, 88.5MB/s]
82%|########2 | 36.7M/44.7M [00:00<00:00, 74.5MB/s]
99%|#########9| 44.3M/44.7M [00:00<00:00, 70.3MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 73.7MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
29%|##9 | 13.0M/44.7M [00:00<00:00, 136MB/s]
58%|#####8 | 26.0M/44.7M [00:00<00:00, 110MB/s]
82%|########2 | 36.8M/44.7M [00:00<00:00, 110MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 99.7MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
index 834027f376..d531a79ac5 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -416,7 +416,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 12.164 seconds)
+ **Total running time of the script:** ( 1 minutes 11.994 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 a5789dbe00..ae7c611903 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
=================
-**05:45.433** total execution time for **how_to_compile_models** files:
+**05:44.598** total execution time for **how_to_compile_models** files:
-+-----------------------------------------------------------------------------------+------------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:12.164 | 0.0 MB |
-+-----------------------------------------------------------------------------------+------------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:09.753 | 0.0 MB |
-+-----------------------------------------------------------------------------------+------------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:47.125 | 0.0 MB |
-+-----------------------------------------------------------------------------------+------------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.188 | 0.0 MB |
-+-----------------------------------------------------------------------------------+------------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:28.1000 | 0.0 MB |
-+-----------------------------------------------------------------------------------+------------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.363 | 0.0 MB |
-+-----------------------------------------------------------------------------------+------------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.696 | 0.0 MB |
-+-----------------------------------------------------------------------------------+------------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:23.142 | 0.0 MB |
-+-----------------------------------------------------------------------------------+------------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.572 | 0.0 MB |
-+-----------------------------------------------------------------------------------+------------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.428 | 0.0 MB |
-+-----------------------------------------------------------------------------------+------------+--------+
++-----------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.994 | 0.0 MB |
++-----------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:10.318 | 0.0 MB |
++-----------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.832 | 0.0 MB |
++-----------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.224 | 0.0 MB |
++-----------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:28.728 | 0.0 MB |
++-----------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.196 | 0.0 MB |
++-----------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.797 | 0.0 MB |
++-----------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.512 | 0.0 MB |
++-----------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.613 | 0.0 MB |
++-----------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.383 | 0.0 MB |
++-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
index 2e274804a3..fbdf54114f 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -723,7 +723,7 @@ well as provides information about the model's performance
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 3338.9692 3337.3748 3355.3211 3333.9448 5.8164
+ 3337.3420 3336.8833 3340.1602 3335.5198 1.5800
@@ -732,7 +732,7 @@ well as provides information about the model's performance
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.868 seconds)
+ **Total running time of the script:** ( 1 minutes 0.706 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_model_on_adreno.py:
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 b05830da62..cb9c3b6780 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
@@ -433,7 +433,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.9070 15.8293 16.4198 15.7309 0.1954
+ 15.5254 15.5108 15.7035 15.4388 0.0776
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 a2b3882e36..4579944b3b 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -127,7 +127,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.99M/170M [00:00<00:03, 46.0MB/s]
9%|9 | 16.0M/170M [00:00<00:03, 43.9MB/s]
14%|#4 | 24.0M/170M [00:00<00:03, 49.0MB/s]
19%|#8 | 32.0M/170M [00:00<00:02, 52.5MB/s]
25%|##4 | 42.1M/170M [00:00<00:02, 59.6MB/s]
28%|##8 | 47.9M/170M [00:00<00:02, 60.1MB/s]
33%|###2 | 56.0M/170M [00:01<00:02, 56.5MB/s]
38%|###7 | 64.0M/170M [00:01<00:01, 55.9MB/s]
42%|####2 | 72.0M/170M [00:01<00:01, 58.7MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 55.0MB/s]
52%|#####1 | 88.0M/170M [00:01<00:01, 53.7MB/s]
57%|#####6 | 96.0M/170M [00:01<00:01, 51.1MB/s]
61%|######1 | 104M/170M [00:02<00:01, 50.0MB/s]
66%|######5 | 112M/170M [00:02<00:01, 54.8MB/s]
71%|####### | 120M/170M [00:02<00:00, 54.8MB/s]
75%|#######5 | 128M/170M [00:02<00:00, 56.2MB/s]
79%|#######9 | 134M/170M [00:02<00:00, 50.2MB/s]
85%|########4 | 144M/170M [00:02<00:00, 54.4MB/s]
89%|########9 | 152M/170M [00:02<00:00, 51.0MB/s]
94%|#########4| 160M/170M [00:03<00:00, 50.7MB/s]
100%|##########| 170M/170M [00:03<00:00, 54.8MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
8%|8 | 14.3M/170M [00:00<00:01, 136MB/s]
16%|#6 | 27.3M/170M [00:00<00:01, 126MB/s]
23%|##3 | 39.3M/170M [00:00<00:01, 97.9MB/s]
29%|##8 | 49.1M/170M [00:00<00:01, 89.8MB/s]
34%|###4 | 58.0M/170M [00:00<00:01, 88.4MB/s]
39%|###9 | 66.6M/170M [00:00<00:01, 75.7MB/s]
47%|####7 | 80.0M/170M [00:00<00:01, 87.0MB/s]
57%|#####6 | 96.0M/170M [00:01<00:00, 102MB/s]
66%|######5 | 112M/170M [00:01<00:00, 115MB/s]
75%|#######5 | 128M/170M [00:01<00:00, 128MB/s]
83%|########2 | 140M/170M [00:01<00:00, 92.0MB/s]
89%|########8 | 151M/170M [00:01<00:00, 83.0MB/s]
94%|#########4| 160M/170M [00:01<00:00, 64.5MB/s]
98%|#########8| 167M/170M [00:02<00:00, 63.6MB/s]
100%|##########| 170M/170M [00:02<00:00, 85.4MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -296,7 +296,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 13.543 seconds)
+ **Total running time of the script:** ( 3 minutes 9.497 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 c70016faec..0d2373903f 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -236,7 +236,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 39.9MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 46.4MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
89%|########9 | 12.1M/13.6M [00:00<00:00, 127MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 135MB/s]
@@ -418,7 +418,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.2110 90.1254 93.0441 90.0141 0.3496
+ 90.2606 90.1680 95.5233 89.9181 0.5807
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.624 seconds)
+ **Total running time of the script:** ( 1 minutes 5.052 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 c0f800bedd..6f94a0426b 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)
- 120.1219 120.0064 123.9565 118.8562 0.6350
+ 117.1102 116.8850 120.9418 115.5038 0.9601
@@ -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 30.884 seconds)
+ **Total running time of the script:** ( 2 minutes 26.290 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 833636d08f..25ce1b6d20 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 39.571 seconds)
+ **Total running time of the script:** ( 1 minutes 39.742 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 982fb19bef..916be65ae9 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -166,7 +166,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
5%|5 | 7026/132723 [00:00<00:01, 70254.37KB/s]
12%|#1 | 15717/132723 [00:00<00:01, 80045.35KB/s]
18%|#8 | 24410/132723 [00:00<00:01, 83176.20KB/s]
25%|##4 | 33135/132723 [00:00<00:01, 84782.48KB/s]
31%|###1 | 41765/132723 [00:00<00:01, 85326.02KB/s]
38%|###7 | 50425/132723 [00:00<00:00, 85754.30KB/s]
45%|####4 | 59138/132723 [00:00<00:00, 86196.50KB/s]
51%|#####1 | 67758/132723 [00:00<00:00, 81682.71KB/s]
58%|#####7 | 76396/132723 [00:00<00:00, 83093.90KB/s]
64%|######3 | 84743/132723 [00:01<00:00, 67789.27KB/s]
70%|####### | 93508/132723 [00:01<00:00, 72934.75KB/s]
76%|#######6 | 101212/132723 [00:01<00:00, 60069.40KB/s]
83%|########2 | 109789/132723 [00:01<00:00, 66195.98KB/s]
88%|########8 | 117002/132723 [00:01<00:00, 55507.73KB/s]
95%|#########4| 125700/132723 [00:01<00:00, 62725.89KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 71843.93KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6320/132723 [00:00<00:02, 63184.39KB/s]
11%|#1 | 15095/132723 [00:00<00:01, 77630.93KB/s]
17%|#7 | 22859/132723 [00:00<00:01, 77112.39KB/s]
23%|##3 | 30571/132723 [00:00<00:01, 76850.67KB/s]
29%|##8 | 38257/132723 [00:00<00:01, 67400.60KB/s]
35%|###5 | 46982/132723 [00:00<00:01, 73553.58KB/s]
42%|####1 | 55733/132723 [00:00<00:00, 77836.78KB/s]
49%|####8 | 64487/132723 [00:00<00:00, 80793.24KB/s]
55%|#####5 | 73302/132723 [00:00<00:00, 83018.54KB/s]
62%|######1 | 81686/132723 [00:01<00:01, 47678.40KB/s]
66%|######6 | 88228/132723 [00:01<00:01, 43203.23KB/s]
73%|#######2 | 96605/132723 [00:01<00:00, 51028.42KB/s]
78%|#######7 | 103033/132723 [00:01<00:00, 53508.11KB/s]
82%|########2 | 109399/132723 [00:01<00:00, 49759.07KB/s]
89%|########8 | 117853/132723 [00:01<00:00, 57749.66KB/s]
94%|########
#3| 124386/132723 [00:02<00:00, 55145.11KB/s]
98%|#########8| 130433/132723 [00:02<00:00, 49949.21KB/s]
100%|##########| 132723/132723 [00:02<00:00, 58741.14KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 5.471 seconds)
+ **Total running time of the script:** ( 3 minutes 3.902 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 ce08ea30e6..53d814e3d9 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**14:01.600** total execution time for **how_to_deploy_models** files:
+**13:50.011** 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``) | 03:13.543 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:09.497 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:05.471 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:03.902 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:30.884 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:26.290 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:39.571 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:39.742 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:05.624 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:05.052 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 01:00.868 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 01:00.706 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.122 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:34.892 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.617 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.085 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.894 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.839 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 11453534e9..32a204c8e5 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.zip0b305b85-bd6a-4462-90d2-08239da3d3a7 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip80ce96e4-f644-419c-987f-b43b502f6572 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 50cb52a724..660f284e2f 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:47.138** total execution time for **how_to_extend_tvm** files:
+**00:45.487** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:43.686 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:42.195 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.412 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.302 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.033 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.983 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index c8977ff5ae..f5a9e98820 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: 7271us [7271us] (46.51%; 46.51%)
- FoldScaleAxis: 8363us [7us] (53.49%; 53.49%)
- FoldConstant: 8357us [1723us] (53.45%; 99.92%)
- InferType: 6634us [6634us] (42.43%; 79.38%)
+ InferType: 7045us [7045us] (46.33%; 46.33%)
+ FoldScaleAxis: 8162us [6us] (53.67%; 53.67%)
+ FoldConstant: 8156us [1654us] (53.63%; 99.92%)
+ InferType: 6502us [6502us] (42.76%; 79.72%)
@@ -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: 8771us [8771us] (51.34%; 51.34%)
- FoldScaleAxis: 8313us [5us] (48.66%; 48.66%)
- FoldConstant: 8308us [1674us] (48.63%; 99.94%)
- InferType: 6633us [6633us] (38.83%; 79.84%)
+ InferType: 6556us [6556us] (45.13%; 45.13%)
+ FoldScaleAxis: 7970us [5us] (54.87%; 54.87%)
+ FoldConstant: 7966us [1624us] (54.84%; 99.94%)
+ InferType: 6341us [6341us] (43.65%; 79.61%)
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 c514547bc0..a62c035162 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: 54.162593 ms
+ Convolution: 39.299934 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 bd5a541639..757961c6a8 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
@@ -657,7 +657,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 12.816998 ms
+ conv2d with tensor core: 13.359076 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 d1188918ca..22c0c21d55 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: 0.019354
- Baseline: 3.425807
+ Numpy running time: 0.017908
+ Baseline: 3.432259
@@ -238,7 +238,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.311341
+ Opt1: 0.292593
@@ -340,7 +340,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.348581
+ Opt2: 0.329119
@@ -435,7 +435,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.121133
+ Opt3: 0.113844
@@ -559,7 +559,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110501
+ Opt4: 0.109142
@@ -680,7 +680,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111509
+ Opt5: 0.110419
@@ -804,7 +804,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.145770
+ Opt6: 0.146566
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 964b783537..4e7ccf29c8 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
=================
-**00:35.150** total execution time for **how_to_optimize_operators** files:
+**00:34.654** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.571 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.050 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.514 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.542 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.065 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.062 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
index 79ed658ae7..e9cd62fa14 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**09:00.134** total execution time for **how_to_tune_with_autoscheduler** files:
+**08:52.036** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:35.884 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:28.370 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:31.099 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:30.783 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:01.529 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:01.162 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:28.697 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:28.948 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.851 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.813 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.074 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:10.960 | 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 a3aae58fc2..12bba4c56b 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
@@ -770,7 +770,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.355 ms
+ Execution time of this operator: 0.362 ms
@@ -1377,7 +1377,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 35.884 seconds)
+ **Total running time of the script:** ( 5 minutes 28.370 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 86cfe5ac68..a4ef4a2581 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)
- 7.8996 7.8936 7.9132 7.8920 0.0097
+ 7.8646 7.8648 7.8668 7.8620 0.0020
@@ -671,7 +671,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.529 seconds)
+ **Total running time of the script:** ( 1 minutes 1.162 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
index 6dc9ae1911..fb24a03b8d 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)
- 755.4898 756.1591 757.0488 753.2613 1.6171
+ 742.9161 742.6435 743.6482 742.4567 0.5233
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 31.099 seconds)
+ **Total running time of the script:** ( 1 minutes 30.783 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 025d9007c1..a166b6d86f 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -386,408 +386,657 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [256]), storage_scope = global {
- for (nb_j.inner: int32, 0, 2) {
- let cse_var_2: int32 = (nb_j.inner*16)
- let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 16) {
+ let cse_var_1: int32 = (i.outer.inner*128)
{
- compute_4: Buffer(compute_3, float32, [256], [])[cse_var_2] = 0f32
- compute_4[(cse_var_2 + 1)] = 0f32
- compute_4[(cse_var_2 + 2)] = 0f32
- compute_4[(cse_var_2 + 3)] = 0f32
- compute_4[(cse_var_2 + 4)] = 0f32
- compute_4[(cse_var_2 + 5)] = 0f32
- compute_4[(cse_var_2 + 6)] = 0f32
- compute_4[(cse_var_2 + 7)] = 0f32
- compute_4[(cse_var_2 + 8)] = 0f32
- compute_4[(cse_var_2 + 9)] = 0f32
- compute_4[(cse_var_2 + 10)] = 0f32
- compute_4[(cse_var_2 + 11)] = 0f32
- compute_4[(cse_var_2 + 12)] = 0f32
- compute_4[(cse_var_2 + 13)] = 0f32
- compute_4[(cse_var_2 + 14)] = 0f32
- compute_4[(cse_var_2 + 15)] = 0f32
- compute_4[(cse_var_2 + 32)] = 0f32
- compute_4[(cse_var_2 + 33)] = 0f32
- compute_4[(cse_var_2 + 34)] = 0f32
- compute_4[(cse_var_2 + 35)] = 0f32
- compute_4[(cse_var_2 + 36)] = 0f32
- compute_4[(cse_var_2 + 37)] = 0f32
- compute_4[(cse_var_2 + 38)] = 0f32
- compute_4[(cse_var_2 + 39)] = 0f32
- compute_4[(cse_var_2 + 40)] = 0f32
- compute_4[(cse_var_2 + 41)] = 0f32
- compute_4[(cse_var_2 + 42)] = 0f32
- compute_4[(cse_var_2 + 43)] = 0f32
- compute_4[(cse_var_2 + 44)] = 0f32
- compute_4[(cse_var_2 + 45)] = 0f32
- compute_4[(cse_var_2 + 46)] = 0f32
- compute_4[(cse_var_2 + 47)] = 0f32
- compute_4[(cse_var_2 + 64)] = 0f32
- compute_4[(cse_var_2 + 65)] = 0f32
- compute_4[(cse_var_2 + 66)] = 0f32
- compute_4[(cse_var_2 + 67)] = 0f32
- compute_4[(cse_var_2 + 68)] = 0f32
- compute_4[(cse_var_2 + 69)] = 0f32
- compute_4[(cse_var_2 + 70)] = 0f32
- compute_4[(cse_var_2 + 71)] = 0f32
- compute_4[(cse_var_2 + 72)] = 0f32
- compute_4[(cse_var_2 + 73)] = 0f32
- compute_4[(cse_var_2 + 74)] = 0f32
- compute_4[(cse_var_2 + 75)] = 0f32
- compute_4[(cse_var_2 + 76)] = 0f32
- compute_4[(cse_var_2 + 77)] = 0f32
- compute_4[(cse_var_2 + 78)] = 0f32
- compute_4[(cse_var_2 + 79)] = 0f32
- compute_4[(cse_var_2 + 96)] = 0f32
- compute_4[(cse_var_2 + 97)] = 0f32
- compute_4[(cse_var_2 + 98)] = 0f32
- compute_4[(cse_var_2 + 99)] = 0f32
- compute_4[(cse_var_2 + 100)] = 0f32
- compute_4[(cse_var_2 + 101)] = 0f32
- compute_4[(cse_var_2 + 102)] = 0f32
- compute_4[(cse_var_2 + 103)] = 0f32
- compute_4[(cse_var_2 + 104)] = 0f32
- compute_4[(cse_var_2 + 105)] = 0f32
- compute_4[(cse_var_2 + 106)] = 0f32
- compute_4[(cse_var_2 + 107)] = 0f32
- compute_4[(cse_var_2 + 108)] = 0f32
- compute_4[(cse_var_2 + 109)] = 0f32
- compute_4[(cse_var_2 + 110)] = 0f32
- compute_4[(cse_var_2 + 111)] = 0f32
- compute_4[(cse_var_2 + 128)] = 0f32
- compute_4[(cse_var_2 + 129)] = 0f32
- compute_4[(cse_var_2 + 130)] = 0f32
- compute_4[(cse_var_2 + 131)] = 0f32
- compute_4[(cse_var_2 + 132)] = 0f32
- compute_4[(cse_var_2 + 133)] = 0f32
- compute_4[(cse_var_2 + 134)] = 0f32
- compute_4[(cse_var_2 + 135)] = 0f32
- compute_4[(cse_var_2 + 136)] = 0f32
- compute_4[(cse_var_2 + 137)] = 0f32
- compute_4[(cse_var_2 + 138)] = 0f32
- compute_4[(cse_var_2 + 139)] = 0f32
- compute_4[(cse_var_2 + 140)] = 0f32
- compute_4[(cse_var_2 + 141)] = 0f32
- compute_4[(cse_var_2 + 142)] = 0f32
- compute_4[(cse_var_2 + 143)] = 0f32
- compute_4[(cse_var_2 + 160)] = 0f32
- compute_4[(cse_var_2 + 161)] = 0f32
- compute_4[(cse_var_2 + 162)] = 0f32
- compute_4[(cse_var_2 + 163)] = 0f32
- compute_4[(cse_var_2 + 164)] = 0f32
- compute_4[(cse_var_2 + 165)] = 0f32
- compute_4[(cse_var_2 + 166)] = 0f32
- compute_4[(cse_var_2 + 167)] = 0f32
- compute_4[(cse_var_2 + 168)] = 0f32
- compute_4[(cse_var_2 + 169)] = 0f32
- compute_4[(cse_var_2 + 170)] = 0f32
- compute_4[(cse_var_2 + 171)] = 0f32
- compute_4[(cse_var_2 + 172)] = 0f32
- compute_4[(cse_var_2 + 173)] = 0f32
- compute_4[(cse_var_2 + 174)] = 0f32
- compute_4[(cse_var_2 + 175)] = 0f32
- compute_4[(cse_var_2 + 192)] = 0f32
- compute_4[(cse_var_2 + 193)] = 0f32
- compute_4[(cse_var_2 + 194)] = 0f32
- compute_4[(cse_var_2 + 195)] = 0f32
- compute_4[(cse_var_2 + 196)] = 0f32
- compute_4[(cse_var_2 + 197)] = 0f32
- compute_4[(cse_var_2 + 198)] = 0f32
- compute_4[(cse_var_2 + 199)] = 0f32
- compute_4[(cse_var_2 + 200)] = 0f32
- compute_4[(cse_var_2 + 201)] = 0f32
- compute_4[(cse_var_2 + 202)] = 0f32
- compute_4[(cse_var_2 + 203)] = 0f32
- compute_4[(cse_var_2 + 204)] = 0f32
- compute_4[(cse_var_2 + 205)] = 0f32
- compute_4[(cse_var_2 + 206)] = 0f32
- compute_4[(cse_var_2 + 207)] = 0f32
- compute_4[(cse_var_2 + 224)] = 0f32
- compute_4[(cse_var_2 + 225)] = 0f32
- compute_4[(cse_var_2 + 226)] = 0f32
- compute_4[(cse_var_2 + 227)] = 0f32
- compute_4[(cse_var_2 + 228)] = 0f32
- compute_4[(cse_var_2 + 229)] = 0f32
- compute_4[(cse_var_2 + 230)] = 0f32
- compute_4[(cse_var_2 + 231)] = 0f32
- compute_4[(cse_var_2 + 232)] = 0f32
- compute_4[(cse_var_2 + 233)] = 0f32
- compute_4[(cse_var_2 + 234)] = 0f32
- compute_4[(cse_var_2 + 235)] = 0f32
- compute_4[(cse_var_2 + 236)] = 0f32
- compute_4[(cse_var_2 + 237)] = 0f32
- compute_4[(cse_var_2 + 238)] = 0f32
- compute_4[(cse_var_2 + 239)] = 0f32
- for (elem_idx: int32, 0, (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
- let cse_var_131: int32 = (elem_idx*16)
- let cse_var_130: int32 = (cse_var_2 + 99)
- let cse_var_129: int32 = (cse_var_2 + 98)
- let cse_var_128: int32 = (cse_var_2 + 97)
- let cse_var_127: int32 = (cse_var_2 + 96)
- let cse_var_126: int32 = (cse_var_2 + 9)
- let cse_var_125: int32 = (cse_var_2 + 8)
- let cse_var_124: int32 = (cse_var_2 + 79)
- let cse_var_123: int32 = (cse_var_2 + 78)
- let cse_var_122: int32 = (cse_var_2 + 77)
- let cse_var_121: int32 = (cse_var_2 + 76)
- let cse_var_120: int32 = (cse_var_2 + 75)
- let cse_var_119: int32 = (cse_var_2 + 74)
- let cse_var_118: int32 = (cse_var_2 + 73)
- let cse_var_117: int32 = (cse_var_2 + 72)
- let cse_var_116: int32 = (cse_var_2 + 71)
- let cse_var_115: int32 = (cse_var_2 + 70)
- let cse_var_114: int32 = (cse_var_2 + 7)
- let cse_var_113: int32 = (cse_var_2 + 69)
- let cse_var_112: int32 = (cse_var_2 + 68)
- let cse_var_111: int32 = (cse_var_2 + 67)
- let cse_var_110: int32 = (cse_var_2 + 66)
- let cse_var_109: int32 = (cse_var_2 + 65)
- let cse_var_108: int32 = (cse_var_2 + 64)
- let cse_var_107: int32 = (cse_var_2 + 6)
- let cse_var_106: int32 = (cse_var_2 + 5)
- let cse_var_105: int32 = (cse_var_2 + 47)
- let cse_var_104: int32 = (cse_var_2 + 46)
- let cse_var_103: int32 = (cse_var_2 + 45)
- let cse_var_102: int32 = (cse_var_2 + 44)
- let cse_var_101: int32 = (cse_var_2 + 43)
- let cse_var_100: int32 = (cse_var_2 + 42)
- let cse_var_99: int32 = (cse_var_2 + 41)
- let cse_var_98: int32 = (cse_var_2 + 40)
- let cse_var_97: int32 = (cse_var_2 + 4)
- let cse_var_96: int32 = (cse_var_2 + 39)
- let cse_var_95: int32 = (cse_var_2 + 38)
- let cse_var_94: int32 = (cse_var_2 + 37)
- let cse_var_93: int32 = (cse_var_2 + 36)
- let cse_var_92: int32 = (cse_var_2 + 35)
- let cse_var_91: int32 = (cse_var_2 + 34)
- let cse_var_90: int32 = (cse_var_2 + 33)
- let cse_var_89: int32 = (cse_var_2 + 32)
- let cse_var_88: int32 = (cse_var_2 + 3)
- let cse_var_87: int32 = (cse_var_2 + 239)
- let cse_var_86: int32 = (cse_var_2 + 238)
- let cse_var_85: int32 = (cse_var_2 + 237)
- let cse_var_84: int32 = (cse_var_2 + 236)
- let cse_var_83: int32 = (cse_var_2 + 235)
- let cse_var_82: int32 = (cse_var_2 + 234)
- let cse_var_81: int32 = (cse_var_2 + 233)
- let cse_var_80: int32 = (cse_var_2 + 232)
- let cse_var_79: int32 = (cse_var_2 + 231)
- let cse_var_78: int32 = (cse_var_2 + 230)
- let cse_var_77: int32 = (cse_var_2 + 229)
- let cse_var_76: int32 = (cse_var_2 + 228)
- let cse_var_75: int32 = (cse_var_2 + 227)
- let cse_var_74: int32 = (cse_var_2 + 226)
- let cse_var_73: int32 = (cse_var_2 + 225)
- let cse_var_72: int32 = (cse_var_2 + 224)
- let cse_var_71: int32 = (cse_var_2 + 207)
- let cse_var_70: int32 = (cse_var_2 + 206)
- let cse_var_69: int32 = (cse_var_2 + 205)
- let cse_var_68: int32 = (cse_var_2 + 204)
- let cse_var_67: int32 = (cse_var_2 + 203)
- let cse_var_66: int32 = (cse_var_2 + 202)
- let cse_var_65: int32 = (cse_var_2 + 201)
- let cse_var_64: int32 = (cse_var_2 + 200)
- let cse_var_63: int32 = (cse_var_2 + 2)
- let cse_var_62: int32 = (cse_var_2 + 199)
- let cse_var_61: int32 = (cse_var_2 + 198)
- let cse_var_60: int32 = (cse_var_2 + 197)
- let cse_var_59: int32 = (cse_var_2 + 196)
- let cse_var_58: int32 = (cse_var_2 + 195)
- let cse_var_57: int32 = (cse_var_2 + 194)
- let cse_var_56: int32 = (cse_var_2 + 193)
- let cse_var_55: int32 = (cse_var_2 + 192)
- let cse_var_54: int32 = (cse_var_2 + 175)
- let cse_var_53: int32 = (cse_var_2 + 174)
- let cse_var_52: int32 = (cse_var_2 + 173)
- let cse_var_51: int32 = (cse_var_2 + 172)
- let cse_var_50: int32 = (cse_var_2 + 171)
- let cse_var_49: int32 = (cse_var_2 + 170)
- let cse_var_48: int32 = (cse_var_2 + 169)
- let cse_var_47: int32 = (cse_var_2 + 168)
- let cse_var_46: int32 = (cse_var_2 + 167)
- let cse_var_45: int32 = (cse_var_2 + 166)
- let cse_var_44: int32 = (cse_var_2 + 165)
- let cse_var_43: int32 = (cse_var_2 + 164)
- let cse_var_42: int32 = (cse_var_2 + 163)
- let cse_var_41: int32 = (cse_var_2 + 162)
- let cse_var_40: int32 = (cse_var_2 + 161)
- let cse_var_39: int32 = (cse_var_2 + 160)
- let cse_var_38: int32 = (cse_var_2 + 15)
- let cse_var_37: int32 = (cse_var_2 + 143)
- let cse_var_36: int32 = (cse_var_2 + 142)
- let cse_var_35: int32 = (cse_var_2 + 141)
- let cse_var_34: int32 = (cse_var_2 + 140)
- let cse_var_33: int32 = (cse_var_2 + 14)
- let cse_var_32: int32 = (cse_var_2 + 139)
- let cse_var_31: int32 = (cse_var_2 + 138)
- let cse_var_30: int32 = (cse_var_2 + 137)
- let cse_var_29: int32 = (cse_var_2 + 136)
- let cse_var_28: int32 = (cse_var_2 + 135)
- let cse_var_27: int32 = (cse_var_2 + 134)
- let cse_var_26: int32 = (cse_var_2 + 133)
- let cse_var_25: int32 = (cse_var_2 + 132)
- let cse_var_24: int32 = (cse_var_2 + 131)
- let cse_var_23: int32 = (cse_var_2 + 130)
- let cse_var_22: int32 = (cse_var_2 + 13)
- let cse_var_21: int32 = (cse_var_2 + 129)
- let cse_var_20: int32 = (cse_var_2 + 128)
- let cse_var_19: int32 = (cse_var_2 + 12)
- let cse_var_18: int32 = (cse_var_2 + 111)
- let cse_var_17: int32 = (cse_var_2 + 110)
- let cse_var_16: int32 = (cse_var_2 + 11)
- let cse_var_15: int32 = (cse_var_2 + 109)
- let cse_var_14: int32 = (cse_var_2 + 108)
- let cse_var_13: int32 = (cse_var_2 + 107)
- let cse_var_12: int32 = (cse_var_2 + 106)
- let cse_var_11: int32 = (cse_var_2 + 105)
- let cse_var_10: int32 = (cse_var_2 + 104)
- let cse_var_9: int32 = (cse_var_2 + 103)
- let cse_var_8: int32 = (cse_var_2 + 102)
- let cse_var_7: int32 = (cse_var_2 + 101)
- let cse_var_6: int32 = (cse_var_2 + 100)
- let cse_var_5: int32 = (cse_var_2 + 10)
- let cse_var_4: int32 = (cse_var_2 + 1)
- let cse_var_3: int32 = (floordiv(i0.outer.i1.outer.fused, 16)*2048)
- {
- compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_3 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_63] = (compute_4[cse_var_63] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_88] = (compute_4[cse_var_88] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_97] = (compute_4[cse_var_97] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_106] = (compute_4[cse_var_106] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_107] = (compute_4[cse_var_107] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_114] = (compute_4[cse_var_114] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_125] = (compute_4[cse_var_125] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_126] = (compute_4[cse_var_126] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_22] = (compute_4[cse_var_22] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_33] = (compute_4[cse_var_33] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_38] = (compute_4[cse_var_38] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_89] = (compute_4[cse_var_89] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_90] = (compute_4[cse_var_90] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_91] = (compute_4[cse_var_91] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_92] = (compute_4[cse_var_92] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_93] = (compute_4[cse_var_93] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_94] = (compute_4[cse_var_94] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_95] = (compute_4[cse_var_95] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_96] = (compute_4[cse_var_96] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_98] = (compute_4[cse_var_98] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_99] = (compute_4[cse_var_99] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_100] = (compute_4[cse_var_100] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_101] = (compute_4[cse_var_101] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_102] = (compute_4[cse_var_102] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_103] = (compute_4[cse_var_103] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_104] = (compute_4[cse_var_104] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_105] = (compute_4[cse_var_105] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_108] = (compute_4[cse_var_108] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_109] = (compute_4[cse_var_109] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_110] = (compute_4[cse_var_110] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_111] = (compute_4[cse_var_111] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_112] = (compute_4[cse_var_112] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_113] = (compute_4[cse_var_113] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_115] = (compute_4[cse_var_115] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_116] = (compute_4[cse_var_116] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_117] = (compute_4[cse_var_117] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_118] = (compute_4[cse_var_118] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_119] = (compute_4[cse_var_119] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_120] = (compute_4[cse_var_120] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_121] = (compute_4[cse_var_121] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_122] = (compute_4[cse_var_122] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_123] = (compute_4[cse_var_123] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_124] = (compute_4[cse_var_124] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_127] = (compute_4[cse_var_127] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_128] = (compute_4[cse_var_128] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_129] = (compute_4[cse_var_129] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_130] = (compute_4[cse_var_130] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_20] = (compute_4[cse_var_20] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_21] = (compute_4[cse_var_21] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_23] = (compute_4[cse_var_23] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_24] = (compute_4[cse_var_24] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_25] = (compute_4[cse_var_25] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_26] = (compute_4[cse_var_26] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_27] = (compute_4[cse_var_27] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_28] = (compute_4[cse_var_28] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_29] = (compute_4[cse_var_29] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_30] = (compute_4[cse_var_30] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_31] = (compute_4[cse_var_31] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_32] = (compute_4[cse_var_32] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_34] = (compute_4[cse_var_34] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_35] = (compute_4[cse_var_35] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_36] = (compute_4[cse_var_36] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_37] = (compute_4[cse_var_37] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_39] = (compute_4[cse_var_39] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_40] = (compute_4[cse_var_40] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_41] = (compute_4[cse_var_41] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_42] = (compute_4[cse_var_42] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_43] = (compute_4[cse_var_43] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_44] = (compute_4[cse_var_44] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_45] = (compute_4[cse_var_45] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_46] = (compute_4[cse_var_46] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_47] = (compute_4[cse_var_47] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_48] = (compute_4[cse_var_48] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_49] = (compute_4[cse_var_49] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_50] = (compute_4[cse_var_50] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_51] = (compute_4[cse_var_51] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_52] = (compute_4[cse_var_52] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_53] = (compute_4[cse_var_53] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_54] = (compute_4[cse_var_54] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_55] = (compute_4[cse_var_55] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_56] = (compute_4[cse_var_56] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_57] = (compute_4[cse_var_57] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_58] = (compute_4[cse_var_58] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_59] = (compute_4[cse_var_59] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_60] = (compute_4[cse_var_60] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_61] = (compute_4[cse_var_61] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_62] = (compute_4[cse_var_62] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_64] = (compute_4[cse_var_64] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_65] = (compute_4[cse_var_65] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_66] = (compute_4[cse_var_66] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_67] = (compute_4[cse_var_67] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_68] = (compute_4[cse_var_68] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_69] = (compute_4[cse_var_69] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_70] = (compute_4[cse_var_70] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_71] = (compute_4[cse_var_71] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_72] = (compute_4[cse_var_72] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_73] = (compute_4[cse_var_73] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_74] = (compute_4[cse_var_74] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_75] = (compute_4[cse_var_75] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_76] = (compute_4[cse_var_76] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_77] = (compute_4[cse_var_77] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_78] = (compute_4[cse_var_78] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_79] = (compute_4[cse_var_79] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_80] = (compute_4[cse_var_80] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_81] = (compute_4[cse_var_81] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_82] = (compute_4[cse_var_82] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_83] = (compute_4[cse_var_83] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_84] = (compute_4[cse_var_84] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_85] = (compute_4[cse_var_85] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_86] = (compute_4[cse_var_86] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_87] = (compute_4[cse_var_87] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4: Buffer(compute_3, float32, [2048], [])[cse_var_1] = 0f32
+ compute_4[(cse_var_1 + 1)] = 0f32
+ compute_4[(cse_var_1 + 2)] = 0f32
+ compute_4[(cse_var_1 + 3)] = 0f32
+ compute_4[(cse_var_1 + 4)] = 0f32
+ compute_4[(cse_var_1 + 5)] = 0f32
+ compute_4[(cse_var_1 + 6)] = 0f32
+ compute_4[(cse_var_1 + 7)] = 0f32
+ compute_4[(cse_var_1 + 8)] = 0f32
+ compute_4[(cse_var_1 + 9)] = 0f32
+ compute_4[(cse_var_1 + 10)] = 0f32
+ compute_4[(cse_var_1 + 11)] = 0f32
+ compute_4[(cse_var_1 + 12)] = 0f32
+ compute_4[(cse_var_1 + 13)] = 0f32
+ compute_4[(cse_var_1 + 14)] = 0f32
+ compute_4[(cse_var_1 + 15)] = 0f32
+ compute_4[(cse_var_1 + 16)] = 0f32
+ compute_4[(cse_var_1 + 17)] = 0f32
+ compute_4[(cse_var_1 + 18)] = 0f32
+ compute_4[(cse_var_1 + 19)] = 0f32
+ compute_4[(cse_var_1 + 20)] = 0f32
+ compute_4[(cse_var_1 + 21)] = 0f32
+ compute_4[(cse_var_1 + 22)] = 0f32
+ compute_4[(cse_var_1 + 23)] = 0f32
+ compute_4[(cse_var_1 + 24)] = 0f32
+ compute_4[(cse_var_1 + 25)] = 0f32
+ compute_4[(cse_var_1 + 26)] = 0f32
+ compute_4[(cse_var_1 + 27)] = 0f32
+ compute_4[(cse_var_1 + 28)] = 0f32
+ compute_4[(cse_var_1 + 29)] = 0f32
+ compute_4[(cse_var_1 + 30)] = 0f32
+ compute_4[(cse_var_1 + 31)] = 0f32
+ compute_4[(cse_var_1 + 32)] = 0f32
+ compute_4[(cse_var_1 + 33)] = 0f32
+ compute_4[(cse_var_1 + 34)] = 0f32
+ compute_4[(cse_var_1 + 35)] = 0f32
+ compute_4[(cse_var_1 + 36)] = 0f32
+ compute_4[(cse_var_1 + 37)] = 0f32
+ compute_4[(cse_var_1 + 38)] = 0f32
+ compute_4[(cse_var_1 + 39)] = 0f32
+ compute_4[(cse_var_1 + 40)] = 0f32
+ compute_4[(cse_var_1 + 41)] = 0f32
+ compute_4[(cse_var_1 + 42)] = 0f32
+ compute_4[(cse_var_1 + 43)] = 0f32
+ compute_4[(cse_var_1 + 44)] = 0f32
+ compute_4[(cse_var_1 + 45)] = 0f32
+ compute_4[(cse_var_1 + 46)] = 0f32
+ compute_4[(cse_var_1 + 47)] = 0f32
+ compute_4[(cse_var_1 + 48)] = 0f32
+ compute_4[(cse_var_1 + 49)] = 0f32
+ compute_4[(cse_var_1 + 50)] = 0f32
+ compute_4[(cse_var_1 + 51)] = 0f32
+ compute_4[(cse_var_1 + 52)] = 0f32
+ compute_4[(cse_var_1 + 53)] = 0f32
+ compute_4[(cse_var_1 + 54)] = 0f32
+ compute_4[(cse_var_1 + 55)] = 0f32
+ compute_4[(cse_var_1 + 56)] = 0f32
+ compute_4[(cse_var_1 + 57)] = 0f32
+ compute_4[(cse_var_1 + 58)] = 0f32
+ compute_4[(cse_var_1 + 59)] = 0f32
+ compute_4[(cse_var_1 + 60)] = 0f32
+ compute_4[(cse_var_1 + 61)] = 0f32
+ compute_4[(cse_var_1 + 62)] = 0f32
+ compute_4[(cse_var_1 + 63)] = 0f32
+ compute_4[(cse_var_1 + 64)] = 0f32
+ compute_4[(cse_var_1 + 65)] = 0f32
+ compute_4[(cse_var_1 + 66)] = 0f32
+ compute_4[(cse_var_1 + 67)] = 0f32
+ compute_4[(cse_var_1 + 68)] = 0f32
+ compute_4[(cse_var_1 + 69)] = 0f32
+ compute_4[(cse_var_1 + 70)] = 0f32
+ compute_4[(cse_var_1 + 71)] = 0f32
+ compute_4[(cse_var_1 + 72)] = 0f32
+ compute_4[(cse_var_1 + 73)] = 0f32
+ compute_4[(cse_var_1 + 74)] = 0f32
+ compute_4[(cse_var_1 + 75)] = 0f32
+ compute_4[(cse_var_1 + 76)] = 0f32
+ compute_4[(cse_var_1 + 77)] = 0f32
+ compute_4[(cse_var_1 + 78)] = 0f32
+ compute_4[(cse_var_1 + 79)] = 0f32
+ compute_4[(cse_var_1 + 80)] = 0f32
+ compute_4[(cse_var_1 + 81)] = 0f32
+ compute_4[(cse_var_1 + 82)] = 0f32
+ compute_4[(cse_var_1 + 83)] = 0f32
+ compute_4[(cse_var_1 + 84)] = 0f32
+ compute_4[(cse_var_1 + 85)] = 0f32
+ compute_4[(cse_var_1 + 86)] = 0f32
+ compute_4[(cse_var_1 + 87)] = 0f32
+ compute_4[(cse_var_1 + 88)] = 0f32
+ compute_4[(cse_var_1 + 89)] = 0f32
+ compute_4[(cse_var_1 + 90)] = 0f32
+ compute_4[(cse_var_1 + 91)] = 0f32
+ compute_4[(cse_var_1 + 92)] = 0f32
+ compute_4[(cse_var_1 + 93)] = 0f32
+ compute_4[(cse_var_1 + 94)] = 0f32
+ compute_4[(cse_var_1 + 95)] = 0f32
+ compute_4[(cse_var_1 + 96)] = 0f32
+ compute_4[(cse_var_1 + 97)] = 0f32
+ compute_4[(cse_var_1 + 98)] = 0f32
+ compute_4[(cse_var_1 + 99)] = 0f32
+ compute_4[(cse_var_1 + 100)] = 0f32
+ compute_4[(cse_var_1 + 101)] = 0f32
+ compute_4[(cse_var_1 + 102)] = 0f32
+ compute_4[(cse_var_1 + 103)] = 0f32
+ compute_4[(cse_var_1 + 104)] = 0f32
+ compute_4[(cse_var_1 + 105)] = 0f32
+ compute_4[(cse_var_1 + 106)] = 0f32
+ compute_4[(cse_var_1 + 107)] = 0f32
+ compute_4[(cse_var_1 + 108)] = 0f32
+ compute_4[(cse_var_1 + 109)] = 0f32
+ compute_4[(cse_var_1 + 110)] = 0f32
+ compute_4[(cse_var_1 + 111)] = 0f32
+ compute_4[(cse_var_1 + 112)] = 0f32
+ compute_4[(cse_var_1 + 113)] = 0f32
+ compute_4[(cse_var_1 + 114)] = 0f32
+ compute_4[(cse_var_1 + 115)] = 0f32
+ compute_4[(cse_var_1 + 116)] = 0f32
+ compute_4[(cse_var_1 + 117)] = 0f32
+ compute_4[(cse_var_1 + 118)] = 0f32
+ compute_4[(cse_var_1 + 119)] = 0f32
+ compute_4[(cse_var_1 + 120)] = 0f32
+ compute_4[(cse_var_1 + 121)] = 0f32
+ compute_4[(cse_var_1 + 122)] = 0f32
+ compute_4[(cse_var_1 + 123)] = 0f32
+ compute_4[(cse_var_1 + 124)] = 0f32
+ compute_4[(cse_var_1 + 125)] = 0f32
+ compute_4[(cse_var_1 + 126)] = 0f32
+ compute_4[(cse_var_1 + 127)] = 0f32
+ for (elem_idx: int32, 0, (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])) {
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ compute_4[cse_var_1] = (compute_4[cse_var_1] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((i.outer.inner*2048) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_2: int32 = (cse_var_1 + 1)
+ compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_3: int32 = (cse_var_1 + 2)
+ compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_4: int32 = (cse_var_1 + 3)
+ compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_5: int32 = (cse_var_1 + 4)
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_6: int32 = (cse_var_1 + 5)
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_7: int32 = (cse_var_1 + 6)
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_8: int32 = (cse_var_1 + 7)
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_9: int32 = (cse_var_1 + 8)
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_10: int32 = (cse_var_1 + 9)
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_11: int32 = (cse_var_1 + 10)
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_12: int32 = (cse_var_1 + 11)
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_13: int32 = (cse_var_1 + 12)
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_14: int32 = (cse_var_1 + 13)
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_15: int32 = (cse_var_1 + 14)
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_16: int32 = (cse_var_1 + 15)
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_17: int32 = (cse_var_1 + 16)
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_18: int32 = (cse_var_1 + 17)
+ compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_19: int32 = (cse_var_1 + 18)
+ compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_20: int32 = (cse_var_1 + 19)
+ compute_4[cse_var_20] = (compute_4[cse_var_20] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_21: int32 = (cse_var_1 + 20)
+ compute_4[cse_var_21] = (compute_4[cse_var_21] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_22: int32 = (cse_var_1 + 21)
+ compute_4[cse_var_22] = (compute_4[cse_var_22] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_23: int32 = (cse_var_1 + 22)
+ compute_4[cse_var_23] = (compute_4[cse_var_23] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_24: int32 = (cse_var_1 + 23)
+ compute_4[cse_var_24] = (compute_4[cse_var_24] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_25: int32 = (cse_var_1 + 24)
+ compute_4[cse_var_25] = (compute_4[cse_var_25] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_26: int32 = (cse_var_1 + 25)
+ compute_4[cse_var_26] = (compute_4[cse_var_26] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_27: int32 = (cse_var_1 + 26)
+ compute_4[cse_var_27] = (compute_4[cse_var_27] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_28: int32 = (cse_var_1 + 27)
+ compute_4[cse_var_28] = (compute_4[cse_var_28] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_29: int32 = (cse_var_1 + 28)
+ compute_4[cse_var_29] = (compute_4[cse_var_29] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_30: int32 = (cse_var_1 + 29)
+ compute_4[cse_var_30] = (compute_4[cse_var_30] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_31: int32 = (cse_var_1 + 30)
+ compute_4[cse_var_31] = (compute_4[cse_var_31] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_32: int32 = (cse_var_1 + 31)
+ compute_4[cse_var_32] = (compute_4[cse_var_32] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_33: int32 = (cse_var_1 + 32)
+ compute_4[cse_var_33] = (compute_4[cse_var_33] + (placeholder_16[((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_34: int32 = (cse_var_1 + 33)
+ compute_4[cse_var_34] = (compute_4[cse_var_34] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_35: int32 = (cse_var_1 + 34)
+ compute_4[cse_var_35] = (compute_4[cse_var_35] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_36: int32 = (cse_var_1 + 35)
+ compute_4[cse_var_36] = (compute_4[cse_var_36] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_37: int32 = (cse_var_1 + 36)
+ compute_4[cse_var_37] = (compute_4[cse_var_37] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_38: int32 = (cse_var_1 + 37)
+ compute_4[cse_var_38] = (compute_4[cse_var_38] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_39: int32 = (cse_var_1 + 38)
+ compute_4[cse_var_39] = (compute_4[cse_var_39] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_40: int32 = (cse_var_1 + 39)
+ compute_4[cse_var_40] = (compute_4[cse_var_40] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_41: int32 = (cse_var_1 + 40)
+ compute_4[cse_var_41] = (compute_4[cse_var_41] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_42: int32 = (cse_var_1 + 41)
+ compute_4[cse_var_42] = (compute_4[cse_var_42] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_43: int32 = (cse_var_1 + 42)
+ compute_4[cse_var_43] = (compute_4[cse_var_43] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_44: int32 = (cse_var_1 + 43)
+ compute_4[cse_var_44] = (compute_4[cse_var_44] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_45: int32 = (cse_var_1 + 44)
+ compute_4[cse_var_45] = (compute_4[cse_var_45] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_46: int32 = (cse_var_1 + 45)
+ compute_4[cse_var_46] = (compute_4[cse_var_46] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_47: int32 = (cse_var_1 + 46)
+ compute_4[cse_var_47] = (compute_4[cse_var_47] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_48: int32 = (cse_var_1 + 47)
+ compute_4[cse_var_48] = (compute_4[cse_var_48] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_49: int32 = (cse_var_1 + 48)
+ compute_4[cse_var_49] = (compute_4[cse_var_49] + (placeholder_16[((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_50: int32 = (cse_var_1 + 49)
+ compute_4[cse_var_50] = (compute_4[cse_var_50] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_51: int32 = (cse_var_1 + 50)
+ compute_4[cse_var_51] = (compute_4[cse_var_51] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_52: int32 = (cse_var_1 + 51)
+ compute_4[cse_var_52] = (compute_4[cse_var_52] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_53: int32 = (cse_var_1 + 52)
+ compute_4[cse_var_53] = (compute_4[cse_var_53] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_54: int32 = (cse_var_1 + 53)
+ compute_4[cse_var_54] = (compute_4[cse_var_54] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_55: int32 = (cse_var_1 + 54)
+ compute_4[cse_var_55] = (compute_4[cse_var_55] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_56: int32 = (cse_var_1 + 55)
+ compute_4[cse_var_56] = (compute_4[cse_var_56] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_57: int32 = (cse_var_1 + 56)
+ compute_4[cse_var_57] = (compute_4[cse_var_57] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_58: int32 = (cse_var_1 + 57)
+ compute_4[cse_var_58] = (compute_4[cse_var_58] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_59: int32 = (cse_var_1 + 58)
+ compute_4[cse_var_59] = (compute_4[cse_var_59] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_60: int32 = (cse_var_1 + 59)
+ compute_4[cse_var_60] = (compute_4[cse_var_60] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_61: int32 = (cse_var_1 + 60)
+ compute_4[cse_var_61] = (compute_4[cse_var_61] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_62: int32 = (cse_var_1 + 61)
+ compute_4[cse_var_62] = (compute_4[cse_var_62] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_63: int32 = (cse_var_1 + 62)
+ compute_4[cse_var_63] = (compute_4[cse_var_63] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_64: int32 = (cse_var_1 + 63)
+ compute_4[cse_var_64] = (compute_4[cse_var_64] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_65: int32 = (cse_var_1 + 64)
+ compute_4[cse_var_65] = (compute_4[cse_var_65] + (placeholder_16[((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_66: int32 = (cse_var_1 + 65)
+ compute_4[cse_var_66] = (compute_4[cse_var_66] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_67: int32 = (cse_var_1 + 66)
+ compute_4[cse_var_67] = (compute_4[cse_var_67] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_68: int32 = (cse_var_1 + 67)
+ compute_4[cse_var_68] = (compute_4[cse_var_68] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_69: int32 = (cse_var_1 + 68)
+ compute_4[cse_var_69] = (compute_4[cse_var_69] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_70: int32 = (cse_var_1 + 69)
+ compute_4[cse_var_70] = (compute_4[cse_var_70] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_71: int32 = (cse_var_1 + 70)
+ compute_4[cse_var_71] = (compute_4[cse_var_71] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_72: int32 = (cse_var_1 + 71)
+ compute_4[cse_var_72] = (compute_4[cse_var_72] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_73: int32 = (cse_var_1 + 72)
+ compute_4[cse_var_73] = (compute_4[cse_var_73] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_74: int32 = (cse_var_1 + 73)
+ compute_4[cse_var_74] = (compute_4[cse_var_74] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_75: int32 = (cse_var_1 + 74)
+ compute_4[cse_var_75] = (compute_4[cse_var_75] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_76: int32 = (cse_var_1 + 75)
+ compute_4[cse_var_76] = (compute_4[cse_var_76] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_77: int32 = (cse_var_1 + 76)
+ compute_4[cse_var_77] = (compute_4[cse_var_77] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_78: int32 = (cse_var_1 + 77)
+ compute_4[cse_var_78] = (compute_4[cse_var_78] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_79: int32 = (cse_var_1 + 78)
+ compute_4[cse_var_79] = (compute_4[cse_var_79] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_80: int32 = (cse_var_1 + 79)
+ compute_4[cse_var_80] = (compute_4[cse_var_80] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_81: int32 = (cse_var_1 + 80)
+ compute_4[cse_var_81] = (compute_4[cse_var_81] + (placeholder_16[((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_82: int32 = (cse_var_1 + 81)
+ compute_4[cse_var_82] = (compute_4[cse_var_82] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_83: int32 = (cse_var_1 + 82)
+ compute_4[cse_var_83] = (compute_4[cse_var_83] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_84: int32 = (cse_var_1 + 83)
+ compute_4[cse_var_84] = (compute_4[cse_var_84] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_85: int32 = (cse_var_1 + 84)
+ compute_4[cse_var_85] = (compute_4[cse_var_85] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_86: int32 = (cse_var_1 + 85)
+ compute_4[cse_var_86] = (compute_4[cse_var_86] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_87: int32 = (cse_var_1 + 86)
+ compute_4[cse_var_87] = (compute_4[cse_var_87] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_88: int32 = (cse_var_1 + 87)
+ compute_4[cse_var_88] = (compute_4[cse_var_88] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_89: int32 = (cse_var_1 + 88)
+ compute_4[cse_var_89] = (compute_4[cse_var_89] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_90: int32 = (cse_var_1 + 89)
+ compute_4[cse_var_90] = (compute_4[cse_var_90] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_91: int32 = (cse_var_1 + 90)
+ compute_4[cse_var_91] = (compute_4[cse_var_91] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_92: int32 = (cse_var_1 + 91)
+ compute_4[cse_var_92] = (compute_4[cse_var_92] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_93: int32 = (cse_var_1 + 92)
+ compute_4[cse_var_93] = (compute_4[cse_var_93] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_94: int32 = (cse_var_1 + 93)
+ compute_4[cse_var_94] = (compute_4[cse_var_94] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_95: int32 = (cse_var_1 + 94)
+ compute_4[cse_var_95] = (compute_4[cse_var_95] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_96: int32 = (cse_var_1 + 95)
+ compute_4[cse_var_96] = (compute_4[cse_var_96] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_97: int32 = (cse_var_1 + 96)
+ compute_4[cse_var_97] = (compute_4[cse_var_97] + (placeholder_16[((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_98: int32 = (cse_var_1 + 97)
+ compute_4[cse_var_98] = (compute_4[cse_var_98] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_99: int32 = (cse_var_1 + 98)
+ compute_4[cse_var_99] = (compute_4[cse_var_99] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_100: int32 = (cse_var_1 + 99)
+ compute_4[cse_var_100] = (compute_4[cse_var_100] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_101: int32 = (cse_var_1 + 100)
+ compute_4[cse_var_101] = (compute_4[cse_var_101] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_102: int32 = (cse_var_1 + 101)
+ compute_4[cse_var_102] = (compute_4[cse_var_102] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_103: int32 = (cse_var_1 + 102)
+ compute_4[cse_var_103] = (compute_4[cse_var_103] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_104: int32 = (cse_var_1 + 103)
+ compute_4[cse_var_104] = (compute_4[cse_var_104] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_105: int32 = (cse_var_1 + 104)
+ compute_4[cse_var_105] = (compute_4[cse_var_105] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_106: int32 = (cse_var_1 + 105)
+ compute_4[cse_var_106] = (compute_4[cse_var_106] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_107: int32 = (cse_var_1 + 106)
+ compute_4[cse_var_107] = (compute_4[cse_var_107] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_108: int32 = (cse_var_1 + 107)
+ compute_4[cse_var_108] = (compute_4[cse_var_108] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_109: int32 = (cse_var_1 + 108)
+ compute_4[cse_var_109] = (compute_4[cse_var_109] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_110: int32 = (cse_var_1 + 109)
+ compute_4[cse_var_110] = (compute_4[cse_var_110] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_111: int32 = (cse_var_1 + 110)
+ compute_4[cse_var_111] = (compute_4[cse_var_111] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_112: int32 = (cse_var_1 + 111)
+ compute_4[cse_var_112] = (compute_4[cse_var_112] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_113: int32 = (cse_var_1 + 112)
+ compute_4[cse_var_113] = (compute_4[cse_var_113] + (placeholder_16[((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_114: int32 = (cse_var_1 + 113)
+ compute_4[cse_var_114] = (compute_4[cse_var_114] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_115: int32 = (cse_var_1 + 114)
+ compute_4[cse_var_115] = (compute_4[cse_var_115] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_116: int32 = (cse_var_1 + 115)
+ compute_4[cse_var_116] = (compute_4[cse_var_116] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_117: int32 = (cse_var_1 + 116)
+ compute_4[cse_var_117] = (compute_4[cse_var_117] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_118: int32 = (cse_var_1 + 117)
+ compute_4[cse_var_118] = (compute_4[cse_var_118] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_119: int32 = (cse_var_1 + 118)
+ compute_4[cse_var_119] = (compute_4[cse_var_119] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_120: int32 = (cse_var_1 + 119)
+ compute_4[cse_var_120] = (compute_4[cse_var_120] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_121: int32 = (cse_var_1 + 120)
+ compute_4[cse_var_121] = (compute_4[cse_var_121] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_122: int32 = (cse_var_1 + 121)
+ compute_4[cse_var_122] = (compute_4[cse_var_122] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_123: int32 = (cse_var_1 + 122)
+ compute_4[cse_var_123] = (compute_4[cse_var_123] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_124: int32 = (cse_var_1 + 123)
+ compute_4[cse_var_124] = (compute_4[cse_var_124] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_125: int32 = (cse_var_1 + 124)
+ compute_4[cse_var_125] = (compute_4[cse_var_125] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_126: int32 = (cse_var_1 + 125)
+ compute_4[cse_var_126] = (compute_4[cse_var_126] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_127: int32 = (cse_var_1 + 126)
+ compute_4[cse_var_127] = (compute_4[cse_var_127] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_128: int32 = (cse_var_1 + 127)
+ compute_4[cse_var_128] = (compute_4[cse_var_128] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 8) {
- for (i1.inner: int32, 0, 32) {
- let cse_var_132: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
- compute_5: Buffer(compute_2, float32, [65536], [])[cse_var_132] = max((compute_4[((i0.inner*32) + i1.inner)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[cse_var_132]), 0f32)
- }
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_129: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*16))
+ compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_129, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_129, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -843,7 +1092,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 2.713 ms
+ Execution time of this operator: 2.712 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 ee57628343..ec3a6bf4bd 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
=================
-**00:40.913** total execution time for **how_to_tune_with_autotvm** files:
+**00:53.282** 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``) | 00:40.875 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:53.247 | 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_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 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 3d8c129206..a80ec71bd6 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -265,8 +265,7 @@ for this template
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 20.64/20.64 result: MeasureResult(costs=(0.011214620777777776,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8706092834472656, timestamp=1671134424.2356322) [('tile_f', [-1, 16, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,600394
- No: 2 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+ No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -388,8 +387,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1280805
- No: 3 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2244356
+ No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -511,272 +510,161 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4819687
- No: 4 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1601396
+ No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
+ yield remote, remote.load_module(os.path.split(build_result.filename)[1])
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
+ costs = time_f(*args).results
+ File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
+ blob = feval(*args)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
+ 4: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1730
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 13: operator()
- at ../src/driver/driver_api.cc:388
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1749
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1693
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1617
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+ 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../src/runtime/rpc/rpc_module.cc:129
+ 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1012
+ 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
+ at ../src/runtime/rpc/rpc_endpoint.cc:804
+ File "../src/runtime/rpc/rpc_endpoint.cc", line 804
+ TVMError:
+ ---------------------------------------------------------------
+ An error occurred during the execution of TVM.
+ For more information, please see: https://tvm.apache.org/docs/errors.html
+ ---------------------------------------------------------------
+ Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
+
+ During handling of the above exception, another exception occurred:
Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1730
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 13: operator()
- at ../src/driver/driver_api.cc:388
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1749
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1693
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1617
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,743342
- No: 5 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
+ costs = time_f(*args).results
+ File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
+ self.gen.throw(type, value, traceback)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
+ remote.remove(build_result.filename)
+ File "/workspace/python/tvm/rpc/client.py", line 144, in remove
+ self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
+ File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
+ return self._sess.get_function(name)
+ File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
+ self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
+ File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
+ raise get_last_ffi_error()
tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1730
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 13: operator()
- at ../src/driver/driver_api.cc:388
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1749
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1693
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ 52: 0xffffffffffffffff
+ 51: _start
+ 50: __libc_start_main
+ 49: _Py_UnixMain
+ 48: 0x0000000000650da0
+ 47: 0x0000000000650afa
+ 46: _PyFunction_FastCallDict
+ 45: _PyEval_EvalCodeWithName
+ 44: _PyEval_EvalFrameDefault
+ 43: _PyFunction_FastCallKeywords
+ 42: _PyEval_EvalCodeWithName
+ 41: _PyEval_EvalFrameDefault
+ 40: _PyMethodDef_RawFastCallKeywords
+ 39: 0x0000000000546369
+ 38: _PyEval_EvalCodeWithName
+ 37: _PyEval_EvalFrameDefault
+ 36: _PyFunction_FastCallKeywords
+ 35: _PyEval_EvalCodeWithName
+ 34: _PyEval_EvalFrameDefault
+ 33: _PyFunction_FastCallDict
+ 32: _PyEval_EvalCodeWithName
+ 31: _PyEval_EvalFrameDefault
+ 30: _PyObject_FastCallDict
+ 29: 0x00000000004c06e1
+ 28: _PyFunction_FastCallDict
+ 27: _PyEval_EvalFrameDefault
+ 26: _PyMethodDescr_FastCallKeywords
+ 25: 0x00000000005dcb58
+ 24: 0x00000000005dc83f
+ 23: 0x00000000004ba127
+ 22: _PyEval_EvalFrameDefault
+ 21: _PyFunction_FastCallKeywords
+ 20: _PyEval_EvalFrameDefault
+ 19: _PyFunction_FastCallKeywords
+ 18: _PyEval_EvalFrameDefault
+ 17: _PyFunction_FastCallKeywords
+ 16: _PyEval_EvalCodeWithName
+ 15: _PyEval_EvalFrameDefault
+ 14: 0x0000000000537c30
+ 13: _PyObject_FastCallKeywords
+ 12: 0x00007f8167708fa2
+ 11: _ctypes_callproc
+ 10: ffi_call
+ 9: ffi_call_unix64
+ 8: TVMModGetFunction
+ at ../src/runtime/c_runtime_api.cc:408
+ 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
+ at ../src/runtime/module.cc:66
+ 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
+ at ../src/runtime/rpc/rpc_module.cc:185
+ 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1007
+ 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.h:223
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
at ../include/tvm/runtime/packed_func.h:1617
2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
1: Call
at ../include/tvm/runtime/packed_func.h:1213
0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+ at ../src/runtime/rpc/rpc_endpoint.cc:684
+ File "../src/runtime/rpc/rpc_endpoint.cc", line 684
+ TVMError:
+ ---------------------------------------------------------------
+ An error occurred during the execution of TVM.
+ For more information, please see: https://tvm.apache.org/docs/errors.html
+ ---------------------------------------------------------------
+ Check failed: (code == RPCCode::kReturn) is false: code=1
Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1730
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 13: operator()
- at ../src/driver/driver_api.cc:388
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1749
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1693
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1617
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7934948
- No: 6 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
- res = future.result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
- return self.__get_result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
- raise self._exception
- File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
- result = self.fn(*self.args, **self.kwargs)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
- worker = lambda *args: self._worker_run(*args)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
- return proc.recv()
- File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
- raise TimeoutError()
- TimeoutError
-
- [('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4701736
- No: 7 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+ 52: 0xffffffffffffffff
+ 51: _start
+ 50: __libc_start_main
+ 49: _Py_UnixMain
+ 48: 0x0000000000650da0
+ 47: 0x0000000000650afa
+ 46: _PyFunction_FastCallDict
+ 45: _PyEval_EvalCodeWithName
+ 44: _PyEval_EvalFrameDefault
+ 43: _PyFunction_FastCallKeywords
+ 42: _PyEval_EvalCodeWithName
+ 41: _PyEval_EvalFrameDefault
+ 40: _PyMethodDef_RawFastCallKeywords
+ 39: 0x0000000000546369
+ 38: _PyEval_EvalCodeWithName
+ 37: _PyEval_EvalFrameDefault
+ 36: _PyFunction_FastCallKeywords
+ 35: _PyEval_EvalCodeWithName
+ 34: _PyEval_EvalFrameDefault
+ 33: _PyFunction_FastCallDict
+ 32: _PyEval_EvalCodeWithName
+ 31: _PyEval_EvalFrameDefault
+ 30: _PyObject_FastCallDict
+ 29: 0x00000000004c06e1
+ 28: _PyFunction_FastCallDict
+ 27: _PyEval_EvalFrameDefault
+ 26: _PyMethodDescr_FastCallKeywords
+ 25: 0x00000000005dcb58
+ 24: 0x00000000005dc83f
+ 23: 0x00000000004ba127
+ 22: _PyEval_EvalFrameDefault
+ 21: _PyFunction_FastCallKeywords
+ 20: _PyEval_EvalFrameDefault
+ 19: _PyFunction_FastCall [('tile_f', [-1, 4, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7096202
+ No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -898,8 +786,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9621138
- No: 8 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,422669
+ No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1021,8 +909,26 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 128]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9797251
- No: 9 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7791711
+ No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+ TimeoutError
+
+ [('tile_f', [-1, 32, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8178075
+ No: 7 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1144,8 +1050,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5319969
- No: 10 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4596761
+ No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1267,8 +1173,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1920700
- No: 11 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1953322
+ No: 9 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1390,8 +1296,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9238852
- No: 12 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 256, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8950973
+ No: 10 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1513,8 +1419,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6910795
- No: 13 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8518019
+ No: 11 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1636,8 +1542,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6661236
- No: 14 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8316157
+ No: 12 GFLOPS: 2.06/2.06 result: MeasureResult(costs=(0.1121591415,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.885895013809204, timestamp=1671150812.0305164) [('tile_f', [-1, 32, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6493580
+ No: 13 GFLOPS: 0.00/2.06 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1759,8 +1666,10 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1342482
- No: 15 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2431251
+ No: 14 GFLOPS: 2.24/2.24 result: MeasureResult(costs=(0.10351821124999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.995007276535034, timestamp=1671150816.201508) [('tile_f', [-1, 2, 4, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8200708
+ No: 15 GFLOPS: 36.88/36.88 result: MeasureResult(costs=(0.0062773861875,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.57865571975708, timestamp=1671150816.9564357) [('tile_f', [-1, 2, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5543275
+ No: 16 GFLOPS: 0.00/36.88 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1882,9 +1791,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2505094
- No: 16 GFLOPS: 3.72/20.64 result: MeasureResult(costs=(0.0622214735,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.070925235748291, timestamp=1671134443.9414694) [('tile_f', [-1, 1, 1, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7310324
- No: 17 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6237617
+ No: 17 GFLOPS: 0.00/36.88 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2006,8 +1914,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7492083
- No: 18 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7409293
+ No: 18 GFLOPS: 63.89/63.89 result: MeasureResult(costs=(0.0036235520357142856,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6129930019378662, timestamp=1671150818.7755003) [('tile_f', [-1, 64, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8330545
+ No: 19 GFLOPS: 0.00/63.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2129,9 +2038,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9712757
- No: 19 GFLOPS: 58.33/58.33 result: MeasureResult(costs=(0.003968929269230769,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3788962364196777, timestamp=1671134445.5341394) [('tile_f', [-1, 4, 64, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3502056
- No: 20 GFLOPS: 2.20/58.33 result: MeasureResult(costs=(0.10519447325,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.414799451828003, timestamp=1671134447.3109863) [('tile_f', [-1, 8, 1, 16]), ('tile_y', [-1, 1, 1, 7]), ('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', 0)],None,842107
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4184767
+ No: 20 GFLOPS: 22.83/63.89 result: MeasureResult(costs=(0.010139647600000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2491390705108643, timestamp=1671150819.5261936) [('tile_f', [-1, 1, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,483015
@@ -2186,9 +2094,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 4, 64, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3502056
+ [('tile_f', [-1, 64, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8330545
Finish loading 20 records
- Time cost of this operator: 0.004350
+ Time cost of this operator: 0.004044
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 c2e59542e1..105a1c90b1 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -329,10 +329,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.3 98.726 (1, 2, 10, 10, 3) 2 1 [309.3]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.964 (1, 6, 10, 10) 1 1 [3.021]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.309 (1, 1, 10, 10, 3) 1 1 [0.969]
- Total_time - 313.29 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.8 98.725 (1, 2, 10, 10, 3) 2 1 [312.8]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.063 0.967 (1, 6, 10, 10) 1 1 [3.063]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.978 0.309 (1, 1, 10, 10, 3) 1 1 [0.978]
+ Total_time - 316.84 - - - - -
@@ -397,10 +397,10 @@ 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 136.9 97.997 (1, 6, 10, 10, 1) 2 1 [136.9]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.835 1.313 (1, 6, 10, 10) 1 1 [1.835]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.964 0.69 (1, 1, 10, 10, 3) 1 1 [0.964]
- Total_time - 139.698 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 104.9 97.502 (1, 6, 10, 10, 1) 2 1 [104.9]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.773 1.648 (1, 6, 10, 10) 1 1 [1.773]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.914 0.85 (1, 3, 10, 10, 1) 1 1 [0.914]
+ Total_time - 107.588 - - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index c8ba51b026..c4758bd457 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -109,7 +109,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
61%|###### | 2.09M/3.42M [00:00<00:00, 14.0MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 21.7MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 93.9MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -314,7 +314,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.907 seconds)
+ **Total running time of the script:** ( 1 minutes 1.986 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index 47d49f2ef9..d5c3e48923 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/tmpfzal6q_o/images/random'
+ '/tmp/tmpfa7d9238/images/random'
@@ -316,7 +316,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]
+ :alt: [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpfzal6q_o/images/target contains 8144 images
- /tmp/tmpfzal6q_o/images/random contains 5000 images
+ /tmp/tmpfa7d9238/images/target contains 8144 images
+ /tmp/tmpfa7d9238/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: 0.2115 - accuracy: 0.9251 - val_loss: 0.1319 - val_accuracy: 0.9569 - 47s/epoch - 143ms/step
+ 328/328 - 44s - loss: 0.2389 - accuracy: 0.9189 - val_loss: 0.1032 - val_accuracy: 0.9630 - 44s/epoch - 134ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.0981 - accuracy: 0.9643 - val_loss: 0.1193 - val_accuracy: 0.9615 - 43s/epoch - 132ms/step
+ 328/328 - 40s - loss: 0.1080 - accuracy: 0.9593 - val_loss: 0.0938 - val_accuracy: 0.9671 - 40s/epoch - 123ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0727 - accuracy: 0.9723 - val_loss: 0.1170 - val_accuracy: 0.9626 - 43s/epoch - 132ms/step
+ 328/328 - 40s - loss: 0.0698 - accuracy: 0.9728 - val_loss: 0.1001 - val_accuracy: 0.9671 - 40s/epoch - 122ms/step
- <keras.callbacks.History object at 0x7f0a580e6ad0>
+ <keras.callbacks.History object at 0x7efeb1d117d0>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 42.924 seconds)
+ **Total running time of the script:** ( 4 minutes 50.743 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 4c842776ca..a45496cdfb 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**06:47.777** total execution time for **how_to_work_with_microtvm** files:
+**06:54.746** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:42.924 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:50.743 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:01.907 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:01.986 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:51.188 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:50.699 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.915 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.595 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.840 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.722 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index deb66a65cf..68322de688 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:44.815** total execution time for **how_to_work_with_relay** files:
+**00:44.041** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.650 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.318 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.542 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.183 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.617 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.533 | 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 8ef033634f..3df2c1b534 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 0x7f0a534879e0>
+ <function my_cuda_math_rule at 0x7efeb1f0da70>
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 faca306950..0c8c00cca0 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
@@ -5,20 +5,20 @@
Computation times
=================
-**00:06.962** total execution time for **how_to_work_with_schedules** files:
+**00:07.495** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.379 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.960 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.206 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.183 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.589 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.576 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.566 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.556 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.117 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.118 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.051 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.050 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.029 | 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 a267f332d6..c27277260a 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -343,7 +343,7 @@ The importing needs to happen before the tensorized GEMV being executed.
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpphos1fye/input0.cc'\nsource_filename = \"/tmp/tmpphos1fye/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/tmpdniot803/input0.cc'\nsource_filename = \"/tmp/tmpdniot803/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 ba24661daa..2fae60302a 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:26.086** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:25.201** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.079 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:25.195 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index fdd43242df..0b7aa76f32 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 28.99s!
+ resnet18_v1 inference graph built in 27.57s!
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 4e82dda886..59b113938e 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -333,7 +333,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 19.51s!
+ yolov3-tiny inference graph built in 18.83s!
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 72a2b01389..b395c55b79 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**01:40.516** total execution time for **topic_vta_tutorials_frontend** files:
+**01:37.181** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.588 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:50.130 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.928 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:47.051 | 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 e4d93b8008..8e817f502f 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:03.170** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.173** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.705 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.720 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.465 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.454 | 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 b5ccb1e590..1050fd76e1 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
=================
-**00:00.828** total execution time for **topic_vta_tutorials** files:
+**00:00.803** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.437 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.427 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.391 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.376 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index c0965c91a0..83903c1ffb 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -325,7 +325,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 95.950 ms
+ Execution time of this operator: 92.876 ms
@@ -443,7 +443,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 13.490 seconds)
+ **Total running time of the script:** ( 1 minutes 16.354 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 1c79304d84..055aff3aa4 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -450,16 +450,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 2.54/2.54 result: MeasureResult(costs=(0.1057228566,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9456357955932617, timestamp=1671132993.9879565) [('tile_y', [-1, 8]), ('tile_x', [-1, 4])],None,23
- No: 2 GFLOPS: 12.22/12.22 result: MeasureResult(costs=(0.021961225600000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6002020835876465, timestamp=1671132994.5979462) [('tile_y', [-1, 256]), ('tile_x', [-1, 256])],None,88
- No: 3 GFLOPS: 8.75/12.22 result: MeasureResult(costs=(0.030663131,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7832496166229248, timestamp=1671132996.109403) [('tile_y', [-1, 512]), ('tile_x', [-1, 64])],None,69
- No: 4 GFLOPS: 11.78/12.22 result: MeasureResult(costs=(0.0227864714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6155939102172852, timestamp=1671132997.502146) [('tile_y', [-1, 32]), ('tile_x', [-1, 256])],None,85
- No: 5 GFLOPS: 12.79/12.79 result: MeasureResult(costs=(0.020993404200000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5696730613708496, timestamp=1671132998.200661) [('tile_y', [-1, 128]), ('tile_x', [-1, 512])],None,97
- No: 6 GFLOPS: 3.13/12.79 result: MeasureResult(costs=(0.0856952252,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6118481159210205, timestamp=1671133000.6068947) [('tile_y', [-1, 2]), ('tile_x', [-1, 8])],None,31
- No: 7 GFLOPS: 0.51/12.79 result: MeasureResult(costs=(0.5270117990000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.669428586959839, timestamp=1671133009.2976425) [('tile_y', [-1, 128]), ('tile_x', [-1, 1])],None,7
- No: 8 GFLOPS: 1.73/12.79 result: MeasureResult(costs=(0.1547205766,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.695625066757202, timestamp=1671133012.0230503) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 9 GFLOPS: 14.60/14.60 result: MeasureResult(costs=(0.018383960600000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.815500020980835, timestamp=1671133012.9544334) [('tile_y', [-1, 64]), ('tile_x', [-1, 64])],None,66
- No: 10 GFLOPS: 13.72/14.60 result: MeasureResult(costs=(0.0195635744,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.560798168182373, timestamp=1671133013.5176134) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
+ No: 1 GFLOPS: 12.84/12.84 result: MeasureResult(costs=(0.020908782199999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5888190269470215, timestamp=1671149365.2509778) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
+ No: 2 GFLOPS: 10.55/12.84 result: MeasureResult(costs=(0.0254483944,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6654369831085205, timestamp=1671149365.908091) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 3 GFLOPS: 2.11/12.84 result: MeasureResult(costs=(0.12707509,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.277238130569458, timestamp=1671149368.9420745) [('tile_y', [-1, 128]), ('tile_x', [-1, 4])],None,27
+ No: 4 GFLOPS: 3.06/12.84 result: MeasureResult(costs=(0.087751631,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.649143934249878, timestamp=1671149371.3521419) [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
+ No: 5 GFLOPS: 13.01/13.01 result: MeasureResult(costs=(0.0206402432,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5729818344116211, timestamp=1671149372.04685) [('tile_y', [-1, 128]), ('tile_x', [-1, 512])],None,97
+ No: 6 GFLOPS: 1.75/13.01 result: MeasureResult(costs=(0.1538126638,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6816587448120117, timestamp=1671149374.7573478) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 8.82/13.01 result: MeasureResult(costs=(0.030418642799999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.717548131942749, timestamp=1671149376.2418528) [('tile_y', [-1, 2]), ('tile_x', [-1, 32])],None,51
+ No: 8 GFLOPS: 0.90/13.01 result: MeasureResult(costs=(0.298880578,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.0075554847717285, timestamp=1671149381.271068) [('tile_y', [-1, 64]), ('tile_x', [-1, 2])],None,16
+ No: 9 GFLOPS: 2.30/13.01 result: MeasureResult(costs=(0.1166373722,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.086557388305664, timestamp=1671149383.4721088) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 10 GFLOPS: 1.63/13.01 result: MeasureResult(costs=(0.1645712018,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.840363025665283, timestamp=1671149386.3538458) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 274150e303..73de7edde2 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': 515.405821380001, 'median': 515.0413227499996, 'std': 3.0268202307209173}
+ {'mean': 508.923503159998, 'median': 509.0428255500001, 'std': 1.7475491963004322}
@@ -554,31 +554,29 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 10.62/ 13.06 GFLOPS | Progress: (4/20) | 8.31 s
[Task 1/25] Current/Best: 3.45/ 16.74 GFLOPS | Progress: (8/20) | 12.25 s
[Task 1/25] Current/Best: 17.88/ 17.88 GFLOPS | Progress: (12/20) | 15.87 s
[Task 1/25] Current/Best: 7.02/ 22.63 GFLOPS | Progress: (16/20) | 21.73 s
[Task 1/25] Current/Best: 9.29/ 22.63 GFLOPS | Progress: (20/20) | 24.21 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 4.91/ 17.37 GFLOPS | Progress: (4/20) | 3.53 s
[Task 2/25] Current/Best: 13.21/ 17.55 GFLOPS | Progress: (8/20) | 5.13 s
[Task 2/25] Current/Best: 14.06/ 17.55 GFLOPS | Progress: (12/20) | 7.08 s
[Task 2/25] Current/Best: 11.13/ 17.55 GFLOPS | Progress: (16/20) | 8.66 s
[Task 2/25] Current/Best: 9.98/ 17.55 GFLOPS | Progress: (20/20) | 10.40 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 3.06/ 14.99 GFLOPS | Progress: (4/20) | 4.78 s
[Task 3/25] Current/Best: 11.36/ 20.00 GFLOPS | Progress: (8/20) | 6.94 s
[Task 3/25] Current/Best: 13.74/ 20.00 GFLOPS | Progress: (12/20) | 9.49 s
[Task 3/25] Current/Best: 13.58/ 20.00 GFLOPS | Progress: (16/20) | 12.18 s
[Task 3/25] Current/Best: 9.21/ 20.00 GFLOPS | Progress: (20/20) | 14.79 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.27/ 12.00 GFLOPS | Progress: (4/20) | 4.94 s
[Task 4/25] Current/Best: 13.50/ 16.09 GFLOPS | Progress: (8/20) | 6.75 s
[Task 4/25] Current/Best: 10.12/ 16.39 GFLOPS | Progress: (12/20) | 12.76 s
[Task 4/25] Current/Best: 12.06/ 16.39 GFLOPS | Progress: (16/20) | 14.64 s
[Task 4/25] Current/Best: 13.60/ 16.39 GFLOPS | Progress: (20/20) | 17.66 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 15.77/ 15.77 GFLOPS | Progress: (4/20) | 4.11 s
[Task 5/25] Current/Best: 9.83/ 15.77 GFLOPS | Progress: (8/20) | 7.66 s
[Task 5/25] Current/Best: 23.08/ 23.08 GFLOPS | Progress: (12/20) | 9.28 s
[Task 5/25] Current/Best: 17.41/ 23.08 GFLOPS | Progress: (16/20) | 11.38 s
[Task 5/25] Current/Best: 7.96/ 23.08 GFLOPS | Progress: (20/20) | 13.49 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 15.97/ 17.46 GFLOPS | Progress: (4/20) | 5.50 s
[Task 6/25] Current/Best: 12.17/ 17.56 GFLOPS | Progress: (8/20) | 7.97 s
[Task 6/25] Current/Best: 5.74/ 17.56 GFLOPS | Progress: (12/20) | 12.49 s
[Task 6/25] Current/Best: 5.05/ 23.30 GFLOPS | Progress: (16/20) | 14.89 s
[Task 6/25] Current/Best: 20.82/ 23.30 GFLOPS | Progress: (20/20) | 18.23 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 12.16/ 12.16 GFLOPS | Progress: (4/20) | 4.83 s
[Task 7/25] Current/Best: 21.78/ 21.78 GFLOPS | Progress: (8/20) | 7.74 s
[Task 7/25] Current/Best: 19.24/ 21.78 GFLOPS | Progress: (12/20) | 10.15 s
[Task 7/25] Current/Best: 7.40/ 21.78 GFLOPS | Progress: (16/20) | 13.00 s
[Task 7/25] Current/Best: 20.28/ 21.78 GFLOPS | Progress: (20/20) | 15.74 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.22/ 14.39 GFLOPS | Progress: (4/20) | 10.56 s
[Task 8/25] Current/Best: 5.19/ 14.39 GFLOPS | Progress: (8/20) | 17.31 s
[Task 8/25] Current/Best: 7.90/ 14.39 GFLOPS | Progress: (12/20) | 20.58 s
[Task 8/25] Current/Best: 13.95/ 14.39 GFLOPS | Progress: (16/20) | 24.36 s
[Task 8/25] Current/Best: 2.85/ 14.39 GFLOPS | Progress: (20/20) | 28.40 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 15.89/ 22.54 GFLOPS | Progress: (4/20) | 7.54 s
[Task 9/25] Current/Best: 14.83/ 23.32 GFLOPS | Progress: (8/20) | 11.49 s
[Task 9/25] Current/Best: 7.47/ 23.32 GFLOPS | Progress: (12/20) | 13.30 s
[Task 9/25] Current/Best: 18.76/ 23.33 GFLOPS | Progress: (16/20) | 24.29 s
[Task 9/25] Current/Best: 12.15/ 23.33 GFLOPS | Progress: (20/20) | 28.31 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 14.21/ 16.73 GFLOPS | Progress: (4/20) | 4.00 s
[Task 10/25] Current/Best: 4.47/ 17.85 GFLOPS | Progress: (8/20) | 5.93 s
[Task 10/25] Current/Best: 11.31/ 18.32 GFLOPS | Progress: (12/20) | 7.97 s
[Task 10/25] Current/Best: 14.42/ 22.00 GFLOPS | Progress: (16/20) | 9.61 s
[Task 10/25] Current/Best: 4.54/ 22.00 GFLOPS | Progress: (20/20)
| 12.08 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 11.06/ 15.82 GFLOPS | Progress: (4/20) | 4.64 s
[Task 11/25] Current/Best: 17.47/ 18.78 GFLOPS | Progress: (8/20) | 6.87 s
[Task 11/25] Current/Best: 11.09/ 21.18 GFLOPS | Progress: (12/20) | 9.34 s
[Task 11/25] Current/Best: 10.94/ 23.86 GFLOPS | Progress: (16/20) | 12.43 s
[Task 11/25] Current/Best: 17.92/ 23.86 GFLOPS | Progress: (20/20) | 14.92 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 10.62/ 16.76 GFLOPS | Progress: (4/20) | 5.67 s
[Task 12/25] Current/Best: 14.52/ 20.72 GFLOPS | Progress: (8/20) | 7.59 s
[Task 12/25] Current/Best: 12.41/ 20.72 GFLOPS | Progress: (12/20) | 13.37 s
[Task 12/25] Current/Best: 11.04/ 20.72 GFLOPS | Progress: (16/20) | 19.24 s
[Task 12/25] Current/Best: 12.78/ 20.72 GFLOPS | Progress: (20/20) | 22.56 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 12.08/ 20.43 GFLOPS | Progress: (4/20) | 4.99 s
[Task 13/25] Current/Best: 12.97/ 20.43 GFLOPS | Progress: (8/20) | 8.34 s
[Task 13/25] Current/Best: 21.18/ 21.18 GFLOPS | Progress: (12/20) | 10.84 s
[Task 13/25] Current/Best: 5.83/ 21.18 GFLOPS | Progress: (16/20) | 14.57 s
[Task 13/25] Current/Best: 16.94/ 21.18 GFLOPS | Progress: (20/20) | 17.77 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 8.97/ 16.75 GFLOPS | Progress: (4/20) | 4.04 s
[Task 14/25] Current/Best: 15.04/ 18.10 GFLOPS | Progress: (8/20) | 6.48 s
[Task 14/25] Current/Best: 11.54/ 18.26 GFLOPS | Progress: (12/20) | 8.97 s
[Task 14/25] Current/Best: 18.86/ 18.86 GFLOPS | Progress: (16/20) | 11.20 s Done.
-
[Task 14/25] Current/Best: 9.00/ 18.86 GFLOPS | Progress: (20/20) | 14.67 s Done.
-
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 14.10/ 21.43 GFLOPS | Progress: (4/20) | 3.60 s
[Task 15/25] Current/Best: 18.48/ 21.43 GFLOPS | Progress: (8/20) | 5.23 s
[Task 15/25] Current/Best: 9.20/ 23.31 GFLOPS | Progress: (12/20) | 6.82 s
[Task 15/25] Current/Best: 13.96/ 23.31 GFLOPS | Progress: (16/20) | 10.99 s
[Task 15/25] Current/Best: 11.02/ 23.31 GFLOPS | Progress: (20/20) | 14.83 s Done.
-
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 16.04/ 16.04 GFLOPS | Progress: (4/20) | 5.69 s
[Task 16/25] Current/Best: 12.63/ 16.28 GFLOPS | Progress: (8/20) | 8.17 s
[Task 16/25] Current/Best: 13.81/ 16.28 GFLOPS | Progress: (12/20) | 11.18 s
[Task 16/25] Current/Best: 13.15/ 16.28 GFLOPS | Progress: (16/20) | 14.58 s
[Task 16/25] Current/Best: 14.86/ 18.16 GFLOPS | Progress: (20/20) | 16.55 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 11.89/ 11.89 GFLOPS | Progress: (4/20) | 5.35 s
[Task 17/25] Current/Best: 9.74/ 11.89 GFLOPS | Progress: (8/20) | 8.59 s
[Task 17/25] Current/Best: 13.97/ 17.79 GFLOPS | Progress: (12/20) | 10.79 s
[Task 17/25] Current/Best: 6.11/ 20.37 GFLOPS | Progress: (16/20) | 14.57 s
[Task 17/25] Current/Best: 21.38/ 21.38 GFLOPS | Progress: (20/20) | 19.96 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 5.11/ 17.87 GFLOPS | Progress: (4/20) | 8.01 s
[Task 18/25] Current/Best: 13.15/ 19.42 GFLOPS | Progress: (8/20) | 10.46 s
[Task 18/25] Current/Best: 5.62/ 20.94 GFLOPS | Progress: (12/20) | 12.64 s
[Task 18/25] Current/Best: 20.44/ 20.94 GFLOPS | Progress: (16/20) | 16.33 s
[Task 18/25] Current/Best: 19.43/ 20.94 GFLOPS | Progress: (20/20) | 20.35 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 18.16/ 18.16 GFLOPS | Progress: (4/20) | 6.76 s
[Task 19/25] Current/Best: 6.16/ 18.94 GFLOPS | Progress: (8/20) | 11.69 s
[Task 19/25] Current/Best: 18.06/ 21.54 GFLOPS | Progress: (12/20) | 14.67 s
[Task 19/25] Current/Best: 21.70/ 21.70 GFLOPS | Progress: (16/20) | 17.09 s
[Task 19/25] Current/Best: 4.32/ 21.70 GFLOPS | Progress: (20/20) | 21.65 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 10.17/ 10.70 GFLOPS | Progress: (4/20) | 5.37 s
[Task 20/25] Current/Best: 10.74/ 18.20 GFLOPS | Progress: (8/20) | 8.91 s
[Task 20/25] Current/Best: 13.61/ 18.20 GFLOPS | Progress: (12/20) | 10.74 s
[Task 20/25] Current/Best: 12.99/ 18.20 GFLOPS | Progress: (16/20) | 16.37 s
[Task 20/25] Current/Best: 8.26/ 18.20 GFLOPS | Progress: (20/20) | 18.83 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 8.49/ 13.47 GFLOPS | Progress: (4/20) | 4.71 s
[Task 21/25] Current/Best: 7.59/ 16.62 GFLOPS | Progress: (8/20) | 7.16 s
[Task 21/25] Current/Best: 14.55/ 16.62 GFLOPS | Progress: (12/20) | 9.51 s Done.
-
[Task 21/25] Current/Best: 11.87/ 16.62 GFLOPS | Progress: (16/20) | 12.55 s
[Task 21/25] Current/Best: 11.43/ 19.95 GFLOPS | Progress: (20/20) | 14.72 s Done.
-
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 10.63/ 20.95 GFLOPS | Progress: (4/20) | 4.89 s
[Task 22/25] Current/Best: 13.77/ 20.95 GFLOPS | Progress: (8/20) | 6.47 s
[Task 22/25] Current/Best: 14.42/ 20.95 GFLOPS | Progress: (12/20) | 8.74 s
[Task 22/25] Current/Best: 6.67/ 20.95 GFLOPS | Progress: (16/20) | 11.57 s
[Task 22/25] Current/Best: 20.76/ 20.95 GFLOPS | Progress: (20/20) | 14.61 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 8.16/ 19.85 GFLOPS | Progress: (4/20) | 4.99 s
[Task 23/25] Current/Best: 18.95/ 19.85 GFLOPS | Progress: (8/20) | 7.75 s
[Task 23/25] Current/Best: 18.74/ 20.60 GFLOPS | Progress: (12/20) | 10.56 s
[Task 23/25] Current/Best: 12.90/ 20.60 GFLOPS | Progress: (16/20) | 14.54 s
[Task 23/25] Current/Best: 10.99/ 21.53 GFLOPS | Progress: (20/20) | 19.45 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 1.78/ 9.68 GFLOPS | Progress: (4/20) | 3.59 s
[Task 24/25] Current/Best: 5.16/ 9.68 GFLOPS | Progress: (8/20) | 9.65 s
[Task 24/25] Current/Best: 3.72/ 9.68 GFLOPS | Progress: (12/20) | 20.82 s
[Task 24/25] Current/Best: 9.21/ 9.68 GFLOPS | Progress: (16/20) | 32.93 s
[Task 24/25] Current/Best: 1.83/ 9.68 GFLOPS | Progress: (20/20) | 43.86 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 25/25] Current/Best: 1.54/ 8.74 GFLOPS | Progress: (4/20) | 4.13 s
[Task 25/25] Current/Best: 7.81/ 8.74 GFLOPS | Progress: (8/20) | 8.89 s
[Task 25/25] Current/Best: 3.50/ 8.74 GFLOPS | Progress: (12/20) | 19.83 s
[Task 25/25] Current/Best: 8.96/ 8.96 GFLOPS | Progress: (16/20) | 31.31 s
[Task 25/25] Current/Best: 7.20/ 9.47 GFLOPS | Progress: (20/20) | 43.17 s
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 13.59/ 17.55 GFLOPS | Progress: (4/20) | 8.95 s
[Task 1/25] Current/Best: 22.85/ 22.85 GFLOPS | Progress: (8/20) | 11.80 s
[Task 1/25] Current/Best: 18.39/ 22.85 GFLOPS | Progress: (12/20) | 14.28 s
[Task 1/25] Current/Best: 19.17/ 22.85 GFLOPS | Progress: (16/20) | 16.27 s
[Task 1/25] Current/Best: 15.85/ 22.85 GFLOPS | Progress: (20/20) | 20.62 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.47/ 15.74 GFLOPS | Progress: (4/20) | 3.51 s
[Task 2/25] Current/Best: 14.82/ 17.28 GFLOPS | Progress: (8/20) | 5.08 s
[Task 2/25] Current/Best: 15.28/ 17.28 GFLOPS | Progress: (12/20) | 6.93 s
[Task 2/25] Current/Best: 17.87/ 17.87 GFLOPS | Progress: (16/20) | 9.85 s
[Task 2/25] Current/Best: 8.54/ 17.87 GFLOPS | Progress: (20/20) | 11.47 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 12.26/ 14.66 GFLOPS | Progress: (4/20) | 3.98 s
[Task 3/25] Current/Best: 8.98/ 14.66 GFLOPS | Progress: (8/20) | 7.38 s
[Task 3/25] Current/Best: 6.76/ 14.66 GFLOPS | Progress: (12/20) | 9.84 s
[Task 3/25] Current/Best: 13.07/ 18.33 GFLOPS | Progress: (16/20) | 12.26 s
[Task 3/25] Current/Best: 14.68/ 18.33 GFLOPS | Progress: (20/20) | 14.48 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 11.19/ 21.36 GFLOPS | Progress: (4/20) | 3.89 s
[Task 4/25] Current/Best: 13.13/ 21.36 GFLOPS | Progress: (8/20) | 6.06 s
[Task 4/25] Current/Best: 11.84/ 21.36 GFLOPS | Progress: (12/20) | 11.56 s
[Task 4/25] Current/Best: 12.79/ 21.36 GFLOPS | Progress: (16/20) | 13.30 s
[Task 4/25] Current/Best: 10.03/ 21.36 GFLOPS | Progress: (20/20) | 15.96 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 17.80/ 17.81 GFLOPS | Progress: (4/20) | 4.24 s
[Task 5/25] Current/Best: 20.72/ 21.56 GFLOPS | Progress: (8/20) | 5.99 s
[Task 5/25] Current/Best: 12.21/ 21.56 GFLOPS | Progress: (12/20) | 8.40 s
[Task 5/25] Current/Best: 5.81/ 21.56 GFLOPS | Progress: (16/20) | 10.18 s
[Task 5/25] Current/Best: 6.87/ 21.56 GFLOPS | Progress: (20/20) | 12.69 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 11.35/ 21.97 GFLOPS | Progress: (4/20) | 6.84 s
[Task 6/25] Current/Best: 13.16/ 21.97 GFLOPS | Progress: (8/20) | 9.55 s
[Task 6/25] Current/Best: 14.42/ 21.97 GFLOPS | Progress: (12/20) | 13.48 s
[Task 6/25] Current/Best: 8.71/ 21.97 GFLOPS | Progress: (16/20) | 16.39 s
[Task 6/25] Current/Best: 11.11/ 21.97 GFLOPS | Progress: (20/20) | 18.64 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 16.22/ 16.22 GFLOPS | Progress: (4/20) | 4.13 s
[Task 7/25] Current/Best: 5.73/ 16.22 GFLOPS | Progress: (8/20) | 7.00 s
[Task 7/25] Current/Best: 7.18/ 21.08 GFLOPS | Progress: (12/20) | 9.43 s
[Task 7/25] Current/Best: 14.97/ 21.08 GFLOPS | Progress: (16/20) | 11.70 s
[Task 7/25] Current/Best: 9.87/ 21.08 GFLOPS | Progress: (20/20) | 14.13 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.69/ 17.87 GFLOPS | Progress: (4/20) | 6.17 s
[Task 8/25] Current/Best: 11.92/ 17.87 GFLOPS | Progress: (8/20) | 8.91 s
[Task 8/25] Current/Best: 2.86/ 17.87 GFLOPS | Progress: (12/20) | 13.48 s
[Task 8/25] Current/Best: 13.77/ 17.87 GFLOPS | Progress: (16/20) | 18.74 s
[Task 8/25] Current/Best: 13.65/ 17.87 GFLOPS | Progress: (20/20) | 21.57 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 13.95/ 20.29 GFLOPS | Progress: (4/20) | 3.38 s
[Task 9/25] Current/Best: 17.77/ 20.29 GFLOPS | Progress: (8/20) | 5.95 s
[Task 9/25] Current/Best: 19.16/ 20.29 GFLOPS | Progress: (12/20) | 15.47 s
[Task 9/25] Current/Best: 12.85/ 20.29 GFLOPS | Progress: (16/20) | 24.23 s
[Task 9/25] Current/Best: 22.71/ 22.71 GFLOPS | Progress: (20/20) | 29.39 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 19.02/ 19.02 GFLOPS | Progress: (4/20) | 3.53 s
[Task 10/25] Current/Best: 17.51/ 21.95 GFLOPS | Progress: (8/20) | 5.12 s
[Task 10/25] Current/Best: 13.07/ 21.95 GFLOPS | Progress: (12/20) | 7.32 s
[Task 10/25] Current/Best: 10.99/ 21.95 GFLOPS | Progress: (16/20) | 9.24 s
[Task 10/25] Current/Best: 7.95/ 21.95 GFLOPS | Progress: (20/20) | 11.15 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 6.20/ 13.44 GFLOPS | Progress: (4/20) | 4.40 s
[Task 11/25] Current/Best: 6.29/ 21.15 GFLOPS | Progress: (8/20) | 7.09 s
[Task 11/25] Current/Best: 14.30/ 21.15 GFLOPS | Progress: (12/20) | 10.06 s
[Task 11/25] Current/Best: 8.01/ 21.15 GFLOPS | Progress: (16/20) | 12.28 s
[Task 11/25] Current/Best: 7.00/ 21.15 GFLOPS | Progress: (20/20) | 15.23 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 13.40/ 13.40 GFLOPS | Progress: (4/20) | 6.86 s
[Task 12/25] Current/Best: 12.67/ 13.40 GFLOPS | Progress: (8/20) | 10.76 s
[Task 12/25] Current/Best: 10.32/ 21.06 GFLOPS | Progress: (12/20) | 15.79 s
[Task 12/25] Current/Best: 8.33/ 21.06 GFLOPS | Progress: (16/20) | 19.78 s
[Task 12/25] Current/Best: 10.10/ 21.06 GFLOPS | Progress: (20/20) | 23.35 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 14.26/ 19.38 GFLOPS | Progress: (4/20) | 5.61 s
[Task 13/25] Current/Best: 9.82/ 19.85 GFLOPS | Progress: (8/20) | 8.17 s
[Task 13/25] Current/Best: 10.94/ 21.26 GFLOPS | Progress: (12/20) | 11.38 s
[Task 13/25] Current/Best: 11.51/ 21.26 GFLOPS | Progress: (16/20) | 14.54 s
[Task 13/25] Current/Best: 17.17/ 21.26 GFLOPS | Progress: (20/20) | 17.75 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 4.50/ 14.10 GFLOPS | Progress: (4/20) | 4.86 s
[Task 14/25] Current/Best: 5.11/ 14.10 GFLOPS | Progress: (8/20) | 12.41 s
[Task 14/25] Current/Best: 5.96/ 14.10 GFLOPS | Progress: (12/20) | 17.37 s
[Task 14/25] Current/Best: 7.48/ 17.86 GFLOPS | Progress: (16/20) | 21.00 s
[Task 14/25] Current/Best: 15.63/ 17.86 GFLOPS | Progress: (20/20) | 28.02 s Done.
+
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.69/ 16.69 GFLOPS | Progress: (4/20) | 6.65 s
[Task 15/25] Current/Best: 15.44/ 16.69 GFLOPS | Progress: (8/20) | 8.81 s
[Task 15/25] Current/Best: 11.59/ 16.81 GFLOPS | Progress: (12/20) | 10.78 s
[Task 15/25] Current/Best: 14.12/ 16.81 GFLOPS | Progress: (16/20) | 17.19 s
[Task 15/25] Current/Best: 6.57/ 16.81 GFLOPS | Progress: (20/20) | 23.95 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 11.88/ 11.88 GFLOPS | Progress: (4/20) | 5.21 s
[Task 16/25] Current/Best: 10.22/ 15.48 GFLOPS | Progress: (8/20) | 7.05 s
[Task 16/25] Current/Best: 7.90/ 15.48 GFLOPS | Progress: (12/20) | 9.53 s
[Task 16/25] Current/Best: 15.31/ 18.18 GFLOPS | Progress: (16/20) | 11.07 s
[Task 16/25] Current/Best: 9.67/ 18.18 GFLOPS | Progress: (20/20)
| 12.57 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 19.05/ 19.05 GFLOPS | Progress: (4/20) | 4.19 s
[Task 17/25] Current/Best: 19.84/ 21.73 GFLOPS | Progress: (8/20) | 6.56 s
[Task 17/25] Current/Best: 15.91/ 21.73 GFLOPS | Progress: (12/20) | 9.54 s
[Task 17/25] Current/Best: 9.61/ 21.73 GFLOPS | Progress: (16/20) | 12.02 s
[Task 17/25] Current/Best: 9.69/ 21.73 GFLOPS | Progress: (20/20) | 15.33 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 2.98/ 15.20 GFLOPS | Progress: (4/20) | 5.79 s
[Task 18/25] Current/Best: 4.87/ 17.94 GFLOPS | Progress: (8/20) | 8.32 s
[Task 18/25] Current/Best: 15.81/ 17.94 GFLOPS | Progress: (12/20) | 10.26 s
[Task 18/25] Current/Best: 4.33/ 19.04 GFLOPS | Progress: (16/20) | 13.78 s
[Task 18/25] Current/Best: 8.72/ 19.04 GFLOPS | Progress: (20/20) | 22.25 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 19.94/ 19.94 GFLOPS | Progress: (4/20) | 4.45 s
[Task 19/25] Current/Best: 13.60/ 19.94 GFLOPS | Progress: (8/20) | 7.54 s
[Task 19/25] Current/Best: 19.27/ 19.94 GFLOPS | Progress: (12/20) | 10.86 s
[Task 19/25] Current/Best: 10.54/ 22.39 GFLOPS | Progress: (16/20) | 13.86 s
[Task 19/25] Current/Best: 10.28/ 22.39 GFLOPS | Progress: (20/20) | 19.68 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 12.23/ 15.43 GFLOPS | Progress: (4/20) | 4.58 s
[Task 20/25] Current/Best: 13.30/ 15.65 GFLOPS | Progress: (8/20) | 6.50 s
[Task 20/25] Current/Best: 11.48/ 16.27 GFLOPS | Progress: (12/20) | 14.49 s
[Task 20/25] Current/Best: 10.50/ 16.27 GFLOPS | Progress: (16/20) | 17.56 s
[Task 20/25] Current/Best: 20.47/ 20.47 GFLOPS | Progress: (20/20) | 21.94 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+ Done.
+
[Task 21/25] Current/Best: 15.53/ 15.53 GFLOPS | Progress: (4/20) | 4.57 s
[Task 21/25] Current/Best: 11.37/ 17.13 GFLOPS | Progress: (8/20) | 6.95 s
[Task 21/25] Current/Best: 10.69/ 17.13 GFLOPS | Progress: (12/20) | 9.05 s
[Task 21/25] Current/Best: 9.75/ 17.13 GFLOPS | Progress: (16/20) | 11.28 s
[Task 21/25] Current/Best: 1.62/ 18.87 GFLOPS | Progress: (20/20) | 13.94 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 5.27/ 17.94 GFLOPS | Progress: (4/20) | 4.20 s
[Task 22/25] Current/Best: 9.16/ 17.94 GFLOPS | Progress: (8/20) | 7.68 s
[Task 22/25] Current/Best: 6.88/ 18.22 GFLOPS | Progress: (12/20) | 11.53 s
[Task 22/25] Current/Best: 16.61/ 18.22 GFLOPS | Progress: (16/20) | 13.88 s
[Task 22/25] Current/Best: 20.22/ 20.22 GFLOPS | Progress: (20/20) | 15.46 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 4.46/ 11.08 GFLOPS | Progress: (4/20) | 5.80 s
[Task 23/25] Current/Best: 12.95/ 20.71 GFLOPS | Progress: (8/20) | 9.98 s
[Task 23/25] Current/Best: 10.74/ 20.71 GFLOPS | Progress: (12/20) | 13.26 s
[Task 23/25] Current/Best: 18.35/ 20.71 GFLOPS | Progress: (16/20) | 16.15 s
[Task 23/25] Current/Best: 22.00/ 22.00 GFLOPS | Progress: (20/20) | 18.54 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 3.01/ 7.78 GFLOPS | Progress: (4/20) | 12.71 s
[Task 24/25] Current/Best: 8.58/ 8.58 GFLOPS | Progress: (8/20) | 23.65 s
[Task 24/25] Current/Best: 9.74/ 9.74 GFLOPS | Progress: (12/20) | 34.59 s
[Task 24/25] Current/Best: 1.86/ 9.74 GFLOPS | Progress: (16/20) | 45.51 s
[Task 24/25] Current/Best: 3.04/ 9.74 GFLOPS | Progress: (20/20) | 52.56 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 2.97/ 7.13 GFLOPS | Progress: (4/20) | 12.77 s
[Task 25/25] Current/Best: 1.55/ 7.13 GFLOPS | Progress: (8/20) | 14.89 s
[Task 25/25] Current/Best: 2.51/ 7.13 GFLOPS | Progress: (12/20) | 25.87 s
[Task 25/25] Current/Best: 8.37/ 8.37 GFLOPS | Progress: (16/20) | 29.11 s
[Task 25/25] Current/Best: 5.24/ 8.37 GFLOPS | Progress: (2
0/20) | 40.04 s
@@ -674,8 +672,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621105
- class='n02123159 tiger cat' with probability=0.356377
+ class='n02123045 tabby, tabby cat' with probability=0.621103
+ class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -732,8 +730,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 420.40497239999695, 'median': 420.71705995001594, 'std': 2.3541167080824197}
- unoptimized: {'mean': 515.405821380001, 'median': 515.0413227499996, 'std': 3.0268202307209173}
+ optimized: {'mean': 424.66174119000243, 'median': 423.78276120000464, 'std': 2.1590939253187806}
+ unoptimized: {'mean': 508.923503159998, 'median': 509.0428255500001, 'std': 1.7475491963004322}
@@ -756,7 +754,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 11 minutes 51.785 seconds)
+ **Total running time of the script:** ( 11 minutes 59.039 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 7e6f88edbc..304ec1c3c1 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -270,7 +270,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.257e-07 secs/op
+ 1.288e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 090c767186..02c3e4191e 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -260,7 +260,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x85cd340)), stage(b, placeholder(b, 0x211c7910)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
+ [stage(a, placeholder(a, 0x1a99e260)), stage(b, placeholder(b, 0xa0132b0)), 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 94b7673787..16165eb6a1 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
=================
-**15:06.528** total execution time for **tutorial** files:
+**15:17.980** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:51.785 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:59.039 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:13.490 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:16.354 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.134 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.063 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.625 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.475 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:26.028 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:25.846 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.471 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.207 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.825 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.159 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.160 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.002 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index b5272fed43..8ca0f9295c 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -294,8 +294,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
- naive: 0.000007
+ Numpy running time: 0.000006
+ naive: 0.000008
@@ -393,7 +393,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000008
+ parallel: 0.000007
@@ -499,10 +499,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.505199998831813e-06 1.0
- naive 6.7013000000000005e-06 0.8928875980710786
- parallel 8.189200000000001e-06 1.091136811980314
- vector 2.4592800000000003e-05 3.276768107955535
+ numpy 6.244270000479446e-06 1.0
+ naive 7.9129e-06 1.267225792509362
+ parallel 6.997299999999999e-06 1.1205953617416822
+ vector 2.46278e-05 3.9440639174970067
@@ -923,7 +923,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.017862
+ Numpy running time: 0.017793
@@ -981,7 +981,7 @@ optimizations.
.. code-block:: none
- none: 3.253786
+ none: 3.440954
@@ -1083,7 +1083,7 @@ schedule.
.. code-block:: none
- blocking: 0.310376
+ blocking: 0.289748
@@ -1178,7 +1178,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.349501
+ vectorization: 0.329821
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1251,7 +1251,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.116475
+ loop permutation: 0.116800
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1349,7 +1349,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.108511
+ array packing: 0.109298
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1441,7 +1441,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110442
+ block caching: 0.110138
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1526,7 +1526,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.143344
+ parallelization: 0.145736
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1606,13 +1606,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.2537857751 1.0
- blocking 0.3103759217 0.0953891691564916
- vectorization 0.3495007787 0.10741358001334882
- loop permutation 0.11647482649999999 0.03579671021716859
- array packing 0.1085111202 0.033349190051291895
- block caching 0.11044218000000001 0.033942670978886355
- parallelization 0.1433438763 0.04405449104761501
+ none 3.4409538483 1.0
+ blocking 0.2897479329 0.084205701579854
+ vectorization 0.3298209069 0.09585159273872496
+ loop permutation 0.1167999963 0.03394407523300696
+ array packing 0.1092977568 0.031763796208425885
+ block caching 0.11013792169999999 0.03200796248819598
+ parallelization 0.14573564519999999 0.04235326936221494
@@ -1652,6 +1652,11 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 1.063 seconds)
+
+
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 415dd7276e..8de0c6f681 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-ce97138ebeb2cf2b5a5a3e916841a884e604d61d
+cdb4eea138789f7021dfc10e124bfd3127241e60
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 6dfd054e27..0a1077bc92 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -585,7 +585,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.753 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.318 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 44c51db793..202f6c5fd1 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ pip install -U tensorflow --user
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 960ms/step
+1/1 [==============================] - 1s 948ms/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 a27de842d2..0c36f6d57b 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -440,7 +440,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip27499e08-8655-4630-ac33-88bfae0ee171 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.zipf4f236f0-5498-4417-86df-dda928cf54a8 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 22e38886d4..6dbe38015a 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,13 +448,14 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 58.0MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:00, 58.9MB/s]
- 48%|####8 | 20.0M/41.5M [00:00<00:00, 55.3MB/s]
- 61%|###### | 25.2M/41.5M [00:00<00:00, 43.0MB/s]
- 82%|########2 | 34.1M/41.5M [00:00<00:00, 45.9MB/s]
- 95%|#########5| 39.5M/41.5M [00:00<00:00, 48.7MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 49.0MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 42.7MB/s]
+ 32%|###1 | 13.2M/41.5M [00:00<00:00, 56.9MB/s]
+ 46%|####5 | 19.0M/41.5M [00:00<00:00, 36.1MB/s]
+ 56%|#####5 | 23.1M/41.5M [00:00<00:00, 31.4MB/s]
+ 65%|######4 | 26.9M/41.5M [00:00<00:00, 33.2MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 38.2MB/s]
+ 92%|#########2| 38.3M/41.5M [00:01<00:00, 38.5MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 38.3MB/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 800656b9a8..dcc7218f29 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,12 +431,10 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 18%|#8 | 8.07M/44.7M [00:00<00:00, 84.6MB/s]
- 36%|###6 | 16.1M/44.7M [00:00<00:00, 66.1MB/s]
- 62%|######2 | 27.8M/44.7M [00:00<00:00, 88.5MB/s]
- 82%|########2 | 36.7M/44.7M [00:00<00:00, 74.5MB/s]
- 99%|#########9| 44.3M/44.7M [00:00<00:00, 70.3MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 73.7MB/s]
+ 29%|##9 | 13.0M/44.7M [00:00<00:00, 136MB/s]
+ 58%|#####8 | 26.0M/44.7M [00:00<00:00, 110MB/s]
+ 82%|########2 | 36.8M/44.7M [00:00<00:00, 110MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 99.7MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_tensorflow.html b/docs/how_to/compile_models/from_tensorflow.html
index 381dedfa02..7d6b5668b2 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -645,7 +645,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 12.164 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.994 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 04ddbdb725..69a70ef6af 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,52 +340,52 @@
<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>05:45.433</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:44.598</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
-<col style="width: 12%" />
+<col style="width: 11%" />
<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>01:12.164</p></td>
+<td><p>01:11.994</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:09.753</p></td>
+<td><p>01:10.318</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:47.125</p></td>
+<td><p>00:46.832</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:32.188</p></td>
+<td><p>00:32.224</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:28.1000</p></td>
+<td><p>00:28.728</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:26.363</p></td>
+<td><p>00:26.196</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:25.696</p></td>
+<td><p>00:25.797</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>00:23.142</p></td>
+<td><p>00:22.512</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:17.572</p></td>
+<td><p>00:17.613</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></td>
-<td><p>00:02.428</p></td>
+<td><p>00:02.383</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno.html b/docs/how_to/deploy_models/deploy_model_on_adreno.html
index 163d60c659..ec1bfb9444 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -919,10 +919,10 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 3338.9692 3337.3748 3355.3211 3333.9448 5.8164
+ 3337.3420 3336.8833 3340.1602 3335.5198 1.5800
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.868 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.706 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/2387d8448da213eb625e6b3d916327d4/deploy_model_on_adreno.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_model_on_adreno.py</span></code></a></p>
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 7974023912..474e8e951b 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -661,7 +661,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.9070 15.8293 16.4198 15.7309 0.1954
+ 15.5254 15.5108 15.7035 15.4388 0.0776
</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 91f853f4a3..52485bfe8f 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,27 +453,21 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 5%|4 | 7.99M/170M [00:00<00:03, 46.0MB/s]
- 9%|9 | 16.0M/170M [00:00<00:03, 43.9MB/s]
- 14%|#4 | 24.0M/170M [00:00<00:03, 49.0MB/s]
- 19%|#8 | 32.0M/170M [00:00<00:02, 52.5MB/s]
- 25%|##4 | 42.1M/170M [00:00<00:02, 59.6MB/s]
- 28%|##8 | 47.9M/170M [00:00<00:02, 60.1MB/s]
- 33%|###2 | 56.0M/170M [00:01<00:02, 56.5MB/s]
- 38%|###7 | 64.0M/170M [00:01<00:01, 55.9MB/s]
- 42%|####2 | 72.0M/170M [00:01<00:01, 58.7MB/s]
- 47%|####7 | 80.0M/170M [00:01<00:01, 55.0MB/s]
- 52%|#####1 | 88.0M/170M [00:01<00:01, 53.7MB/s]
- 57%|#####6 | 96.0M/170M [00:01<00:01, 51.1MB/s]
- 61%|######1 | 104M/170M [00:02<00:01, 50.0MB/s]
- 66%|######5 | 112M/170M [00:02<00:01, 54.8MB/s]
- 71%|####### | 120M/170M [00:02<00:00, 54.8MB/s]
- 75%|#######5 | 128M/170M [00:02<00:00, 56.2MB/s]
- 79%|#######9 | 134M/170M [00:02<00:00, 50.2MB/s]
- 85%|########4 | 144M/170M [00:02<00:00, 54.4MB/s]
- 89%|########9 | 152M/170M [00:02<00:00, 51.0MB/s]
- 94%|#########4| 160M/170M [00:03<00:00, 50.7MB/s]
-100%|##########| 170M/170M [00:03<00:00, 54.8MB/s]
+ 8%|8 | 14.3M/170M [00:00<00:01, 136MB/s]
+ 16%|#6 | 27.3M/170M [00:00<00:01, 126MB/s]
+ 23%|##3 | 39.3M/170M [00:00<00:01, 97.9MB/s]
+ 29%|##8 | 49.1M/170M [00:00<00:01, 89.8MB/s]
+ 34%|###4 | 58.0M/170M [00:00<00:01, 88.4MB/s]
+ 39%|###9 | 66.6M/170M [00:00<00:01, 75.7MB/s]
+ 47%|####7 | 80.0M/170M [00:00<00:01, 87.0MB/s]
+ 57%|#####6 | 96.0M/170M [00:01<00:00, 102MB/s]
+ 66%|######5 | 112M/170M [00:01<00:00, 115MB/s]
+ 75%|#######5 | 128M/170M [00:01<00:00, 128MB/s]
+ 83%|########2 | 140M/170M [00:01<00:00, 92.0MB/s]
+ 89%|########8 | 151M/170M [00:01<00:00, 83.0MB/s]
+ 94%|#########4| 160M/170M [00:01<00:00, 64.5MB/s]
+ 98%|#########8| 167M/170M [00:02<00:00, 63.6MB/s]
+100%|##########| 170M/170M [00:02<00:00, 85.4MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode=& [...]
@@ -571,7 +565,7 @@ 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 13.543 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 9.497 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 e165256ccc..3b63f24164 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -497,8 +497,8 @@ training. Other models require a full post training calibration.</p>
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 59%|#####8 | 7.99M/13.6M [00:00<00:00, 39.9MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 46.4MB/s]
+ 89%|########9 | 12.1M/13.6M [00:00<00:00, 127MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 135MB/s]
</pre></div>
</div>
</div>
@@ -589,7 +589,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.2110 90.1254 93.0441 90.0141 0.3496
+ 90.2606 90.1680 95.5233 89.9181 0.5807
</pre></div>
</div>
<div class="admonition note">
@@ -628,7 +628,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.624 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.052 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 d7c4692dc6..b149af37a8 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -582,7 +582,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.1219 120.0064 123.9565 118.8562 0.6350
+ 117.1102 116.8850 120.9418 115.5038 0.9601
</pre></div>
</div>
<div class="admonition note">
@@ -610,7 +610,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 30.884 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 26.290 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 76f74568d5..30ee42fd6b 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -520,7 +520,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 39.571 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 39.742 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 1112837e09..d1d6c56cb6 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -462,22 +462,24 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|5 | 7026/132723 [00:00<00:01, 70254.37KB/s]
- 12%|#1 | 15717/132723 [00:00<00:01, 80045.35KB/s]
- 18%|#8 | 24410/132723 [00:00<00:01, 83176.20KB/s]
- 25%|##4 | 33135/132723 [00:00<00:01, 84782.48KB/s]
- 31%|###1 | 41765/132723 [00:00<00:01, 85326.02KB/s]
- 38%|###7 | 50425/132723 [00:00<00:00, 85754.30KB/s]
- 45%|####4 | 59138/132723 [00:00<00:00, 86196.50KB/s]
- 51%|#####1 | 67758/132723 [00:00<00:00, 81682.71KB/s]
- 58%|#####7 | 76396/132723 [00:00<00:00, 83093.90KB/s]
- 64%|######3 | 84743/132723 [00:01<00:00, 67789.27KB/s]
- 70%|####### | 93508/132723 [00:01<00:00, 72934.75KB/s]
- 76%|#######6 | 101212/132723 [00:01<00:00, 60069.40KB/s]
- 83%|########2 | 109789/132723 [00:01<00:00, 66195.98KB/s]
- 88%|########8 | 117002/132723 [00:01<00:00, 55507.73KB/s]
- 95%|#########4| 125700/132723 [00:01<00:00, 62725.89KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 71843.93KB/s]
+ 5%|4 | 6320/132723 [00:00<00:02, 63184.39KB/s]
+ 11%|#1 | 15095/132723 [00:00<00:01, 77630.93KB/s]
+ 17%|#7 | 22859/132723 [00:00<00:01, 77112.39KB/s]
+ 23%|##3 | 30571/132723 [00:00<00:01, 76850.67KB/s]
+ 29%|##8 | 38257/132723 [00:00<00:01, 67400.60KB/s]
+ 35%|###5 | 46982/132723 [00:00<00:01, 73553.58KB/s]
+ 42%|####1 | 55733/132723 [00:00<00:00, 77836.78KB/s]
+ 49%|####8 | 64487/132723 [00:00<00:00, 80793.24KB/s]
+ 55%|#####5 | 73302/132723 [00:00<00:00, 83018.54KB/s]
+ 62%|######1 | 81686/132723 [00:01<00:01, 47678.40KB/s]
+ 66%|######6 | 88228/132723 [00:01<00:01, 43203.23KB/s]
+ 73%|#######2 | 96605/132723 [00:01<00:00, 51028.42KB/s]
+ 78%|#######7 | 103033/132723 [00:01<00:00, 53508.11KB/s]
+ 82%|########2 | 109399/132723 [00:01<00:00, 49759.07KB/s]
+ 89%|########8 | 117853/132723 [00:01<00:00, 57749.66KB/s]
+ 94%|#########3| 124386/132723 [00:02<00:00, 55145.11KB/s]
+ 98%|#########8| 130433/132723 [00:02<00:00, 49949.21KB/s]
+100%|##########| 132723/132723 [00:02<00:00, 58741.14KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -516,7 +518,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 5.471 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 3.902 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 0534248e82..c63217b1c6 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>14:01.600</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>13:50.011</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,39 +349,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:13.543</p></td>
+<td><p>03:09.497</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>03:05.471</p></td>
+<td><p>03:03.902</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>02:30.884</p></td>
+<td><p>02:26.290</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>01:39.571</p></td>
+<td><p>01:39.742</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:05.624</p></td>
+<td><p>01:05.052</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_adreno.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno.py</span></code>)</p></td>
-<td><p>01:00.868</p></td>
+<td><p>01:00.706</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:35.122</p></td>
+<td><p>00:34.892</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:25.617</p></td>
+<td><p>00:25.085</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:24.894</p></td>
+<td><p>00:24.839</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
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 9efd195272..b88fcfdc58 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -621,7 +621,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip0b305b85-bd6a-4462-90d2-08239da3d3a7 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.zip80ce96e4-f644-419c-987f-b43b502f6572 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 0370908afd..ce668c23b6 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:47.138</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:45.487</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:43.686</p></td>
+<td><p>00:42.195</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>00:02.412</p></td>
+<td><p>00:02.302</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:01.033</p></td>
+<td><p>00:00.983</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index cb45871e03..7a445bf65e 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -525,10 +525,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 7271us [7271us] (46.51%; 46.51%)
-FoldScaleAxis: 8363us [7us] (53.49%; 53.49%)
- FoldConstant: 8357us [1723us] (53.45%; 99.92%)
- InferType: 6634us [6634us] (42.43%; 79.38%)
+InferType: 7045us [7045us] (46.33%; 46.33%)
+FoldScaleAxis: 8162us [6us] (53.67%; 53.67%)
+ FoldConstant: 8156us [1654us] (53.63%; 99.92%)
+ InferType: 6502us [6502us] (42.76%; 79.72%)
</pre></div>
</div>
</div>
@@ -550,10 +550,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 8771us [8771us] (51.34%; 51.34%)
-FoldScaleAxis: 8313us [5us] (48.66%; 48.66%)
- FoldConstant: 8308us [1674us] (48.63%; 99.94%)
- InferType: 6633us [6633us] (38.83%; 79.84%)
+InferType: 6556us [6556us] (45.13%; 45.13%)
+FoldScaleAxis: 7970us [5us] (54.87%; 54.87%)
+ FoldConstant: 7966us [1624us] (54.84%; 99.94%)
+ InferType: 6341us [6341us] (43.65%; 79.61%)
</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 0ba844d82f..1fd502f899 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -577,7 +577,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.162593 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 39.299934 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 bcf9f5d763..81badfae77 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -914,7 +914,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.816998 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.359076 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 49b6e04e00..4afcccae09 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -474,8 +474,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019354
-Baseline: 3.425807
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017908
+Baseline: 3.432259
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -534,7 +534,7 @@ 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: 0.311341
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.292593
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -600,7 +600,7 @@ 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: 0.348581
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.329119
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -660,7 +660,7 @@ 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: 0.121133
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.113844
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -742,7 +742,7 @@ 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: 0.110501
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109142
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -827,7 +827,7 @@ 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: 0.111509
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110419
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -916,7 +916,7 @@ 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: 0.145770
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146566
</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 1db5c9c0f4..754f39fa3a 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.150</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.654</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.571</p></td>
+<td><p>00:32.050</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>00:01.514</p></td>
+<td><p>00:01.542</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></td>
-<td><p>00:01.065</p></td>
+<td><p>00:01.062</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
index d31497b07f..6828a1a106 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>09:00.134</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>08:52.036</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -349,27 +349,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>05:35.884</p></td>
+<td><p>05:28.370</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:31.099</p></td>
+<td><p>01:30.783</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>01:01.529</p></td>
+<td><p>01:01.162</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>00:28.697</p></td>
+<td><p>00:28.948</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:11.851</p></td>
+<td><p>00:11.813</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:11.074</p></td>
+<td><p>00:10.960</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 7a5b3a1ae2..622acb8c17 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
@@ -1016,7 +1016,7 @@ 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: 0.355 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.362 ms
</pre></div>
</div>
</div>
@@ -1579,7 +1579,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 35.884 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 28.370 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 b058c1fccf..2fecee4137 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -915,7 +915,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.8996 7.8936 7.9132 7.8920 0.0097
+ 7.8646 7.8648 7.8668 7.8620 0.0020
</pre></div>
</div>
</div>
@@ -937,7 +937,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.529 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.162 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/eafe360d52540634c9eea0fa89e804bd/tune_network_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index e15143af55..ebbf5b54a6 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -934,7 +934,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 755.4898 756.1591 757.0488 753.2613 1.6171
+ 742.9161 742.6435 743.6482 742.4567 0.5233
</pre></div>
</div>
</div>
@@ -956,7 +956,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 31.099 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 30.783 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 12396ca1f1..8c513a11bc 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,408 +632,657 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [256]), storage_scope = global {
- for (nb_j.inner: int32, 0, 2) {
- let cse_var_2: int32 = (nb_j.inner*16)
- let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 16) {
+ let cse_var_1: int32 = (i.outer.inner*128)
{
- compute_4: Buffer(compute_3, float32, [256], [])[cse_var_2] = 0f32
- compute_4[(cse_var_2 + 1)] = 0f32
- compute_4[(cse_var_2 + 2)] = 0f32
- compute_4[(cse_var_2 + 3)] = 0f32
- compute_4[(cse_var_2 + 4)] = 0f32
- compute_4[(cse_var_2 + 5)] = 0f32
- compute_4[(cse_var_2 + 6)] = 0f32
- compute_4[(cse_var_2 + 7)] = 0f32
- compute_4[(cse_var_2 + 8)] = 0f32
- compute_4[(cse_var_2 + 9)] = 0f32
- compute_4[(cse_var_2 + 10)] = 0f32
- compute_4[(cse_var_2 + 11)] = 0f32
- compute_4[(cse_var_2 + 12)] = 0f32
- compute_4[(cse_var_2 + 13)] = 0f32
- compute_4[(cse_var_2 + 14)] = 0f32
- compute_4[(cse_var_2 + 15)] = 0f32
- compute_4[(cse_var_2 + 32)] = 0f32
- compute_4[(cse_var_2 + 33)] = 0f32
- compute_4[(cse_var_2 + 34)] = 0f32
- compute_4[(cse_var_2 + 35)] = 0f32
- compute_4[(cse_var_2 + 36)] = 0f32
- compute_4[(cse_var_2 + 37)] = 0f32
- compute_4[(cse_var_2 + 38)] = 0f32
- compute_4[(cse_var_2 + 39)] = 0f32
- compute_4[(cse_var_2 + 40)] = 0f32
- compute_4[(cse_var_2 + 41)] = 0f32
- compute_4[(cse_var_2 + 42)] = 0f32
- compute_4[(cse_var_2 + 43)] = 0f32
- compute_4[(cse_var_2 + 44)] = 0f32
- compute_4[(cse_var_2 + 45)] = 0f32
- compute_4[(cse_var_2 + 46)] = 0f32
- compute_4[(cse_var_2 + 47)] = 0f32
- compute_4[(cse_var_2 + 64)] = 0f32
- compute_4[(cse_var_2 + 65)] = 0f32
- compute_4[(cse_var_2 + 66)] = 0f32
- compute_4[(cse_var_2 + 67)] = 0f32
- compute_4[(cse_var_2 + 68)] = 0f32
- compute_4[(cse_var_2 + 69)] = 0f32
- compute_4[(cse_var_2 + 70)] = 0f32
- compute_4[(cse_var_2 + 71)] = 0f32
- compute_4[(cse_var_2 + 72)] = 0f32
- compute_4[(cse_var_2 + 73)] = 0f32
- compute_4[(cse_var_2 + 74)] = 0f32
- compute_4[(cse_var_2 + 75)] = 0f32
- compute_4[(cse_var_2 + 76)] = 0f32
- compute_4[(cse_var_2 + 77)] = 0f32
- compute_4[(cse_var_2 + 78)] = 0f32
- compute_4[(cse_var_2 + 79)] = 0f32
- compute_4[(cse_var_2 + 96)] = 0f32
- compute_4[(cse_var_2 + 97)] = 0f32
- compute_4[(cse_var_2 + 98)] = 0f32
- compute_4[(cse_var_2 + 99)] = 0f32
- compute_4[(cse_var_2 + 100)] = 0f32
- compute_4[(cse_var_2 + 101)] = 0f32
- compute_4[(cse_var_2 + 102)] = 0f32
- compute_4[(cse_var_2 + 103)] = 0f32
- compute_4[(cse_var_2 + 104)] = 0f32
- compute_4[(cse_var_2 + 105)] = 0f32
- compute_4[(cse_var_2 + 106)] = 0f32
- compute_4[(cse_var_2 + 107)] = 0f32
- compute_4[(cse_var_2 + 108)] = 0f32
- compute_4[(cse_var_2 + 109)] = 0f32
- compute_4[(cse_var_2 + 110)] = 0f32
- compute_4[(cse_var_2 + 111)] = 0f32
- compute_4[(cse_var_2 + 128)] = 0f32
- compute_4[(cse_var_2 + 129)] = 0f32
- compute_4[(cse_var_2 + 130)] = 0f32
- compute_4[(cse_var_2 + 131)] = 0f32
- compute_4[(cse_var_2 + 132)] = 0f32
- compute_4[(cse_var_2 + 133)] = 0f32
- compute_4[(cse_var_2 + 134)] = 0f32
- compute_4[(cse_var_2 + 135)] = 0f32
- compute_4[(cse_var_2 + 136)] = 0f32
- compute_4[(cse_var_2 + 137)] = 0f32
- compute_4[(cse_var_2 + 138)] = 0f32
- compute_4[(cse_var_2 + 139)] = 0f32
- compute_4[(cse_var_2 + 140)] = 0f32
- compute_4[(cse_var_2 + 141)] = 0f32
- compute_4[(cse_var_2 + 142)] = 0f32
- compute_4[(cse_var_2 + 143)] = 0f32
- compute_4[(cse_var_2 + 160)] = 0f32
- compute_4[(cse_var_2 + 161)] = 0f32
- compute_4[(cse_var_2 + 162)] = 0f32
- compute_4[(cse_var_2 + 163)] = 0f32
- compute_4[(cse_var_2 + 164)] = 0f32
- compute_4[(cse_var_2 + 165)] = 0f32
- compute_4[(cse_var_2 + 166)] = 0f32
- compute_4[(cse_var_2 + 167)] = 0f32
- compute_4[(cse_var_2 + 168)] = 0f32
- compute_4[(cse_var_2 + 169)] = 0f32
- compute_4[(cse_var_2 + 170)] = 0f32
- compute_4[(cse_var_2 + 171)] = 0f32
- compute_4[(cse_var_2 + 172)] = 0f32
- compute_4[(cse_var_2 + 173)] = 0f32
- compute_4[(cse_var_2 + 174)] = 0f32
- compute_4[(cse_var_2 + 175)] = 0f32
- compute_4[(cse_var_2 + 192)] = 0f32
- compute_4[(cse_var_2 + 193)] = 0f32
- compute_4[(cse_var_2 + 194)] = 0f32
- compute_4[(cse_var_2 + 195)] = 0f32
- compute_4[(cse_var_2 + 196)] = 0f32
- compute_4[(cse_var_2 + 197)] = 0f32
- compute_4[(cse_var_2 + 198)] = 0f32
- compute_4[(cse_var_2 + 199)] = 0f32
- compute_4[(cse_var_2 + 200)] = 0f32
- compute_4[(cse_var_2 + 201)] = 0f32
- compute_4[(cse_var_2 + 202)] = 0f32
- compute_4[(cse_var_2 + 203)] = 0f32
- compute_4[(cse_var_2 + 204)] = 0f32
- compute_4[(cse_var_2 + 205)] = 0f32
- compute_4[(cse_var_2 + 206)] = 0f32
- compute_4[(cse_var_2 + 207)] = 0f32
- compute_4[(cse_var_2 + 224)] = 0f32
- compute_4[(cse_var_2 + 225)] = 0f32
- compute_4[(cse_var_2 + 226)] = 0f32
- compute_4[(cse_var_2 + 227)] = 0f32
- compute_4[(cse_var_2 + 228)] = 0f32
- compute_4[(cse_var_2 + 229)] = 0f32
- compute_4[(cse_var_2 + 230)] = 0f32
- compute_4[(cse_var_2 + 231)] = 0f32
- compute_4[(cse_var_2 + 232)] = 0f32
- compute_4[(cse_var_2 + 233)] = 0f32
- compute_4[(cse_var_2 + 234)] = 0f32
- compute_4[(cse_var_2 + 235)] = 0f32
- compute_4[(cse_var_2 + 236)] = 0f32
- compute_4[(cse_var_2 + 237)] = 0f32
- compute_4[(cse_var_2 + 238)] = 0f32
- compute_4[(cse_var_2 + 239)] = 0f32
- for (elem_idx: int32, 0, (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
- let cse_var_131: int32 = (elem_idx*16)
- let cse_var_130: int32 = (cse_var_2 + 99)
- let cse_var_129: int32 = (cse_var_2 + 98)
- let cse_var_128: int32 = (cse_var_2 + 97)
- let cse_var_127: int32 = (cse_var_2 + 96)
- let cse_var_126: int32 = (cse_var_2 + 9)
- let cse_var_125: int32 = (cse_var_2 + 8)
- let cse_var_124: int32 = (cse_var_2 + 79)
- let cse_var_123: int32 = (cse_var_2 + 78)
- let cse_var_122: int32 = (cse_var_2 + 77)
- let cse_var_121: int32 = (cse_var_2 + 76)
- let cse_var_120: int32 = (cse_var_2 + 75)
- let cse_var_119: int32 = (cse_var_2 + 74)
- let cse_var_118: int32 = (cse_var_2 + 73)
- let cse_var_117: int32 = (cse_var_2 + 72)
- let cse_var_116: int32 = (cse_var_2 + 71)
- let cse_var_115: int32 = (cse_var_2 + 70)
- let cse_var_114: int32 = (cse_var_2 + 7)
- let cse_var_113: int32 = (cse_var_2 + 69)
- let cse_var_112: int32 = (cse_var_2 + 68)
- let cse_var_111: int32 = (cse_var_2 + 67)
- let cse_var_110: int32 = (cse_var_2 + 66)
- let cse_var_109: int32 = (cse_var_2 + 65)
- let cse_var_108: int32 = (cse_var_2 + 64)
- let cse_var_107: int32 = (cse_var_2 + 6)
- let cse_var_106: int32 = (cse_var_2 + 5)
- let cse_var_105: int32 = (cse_var_2 + 47)
- let cse_var_104: int32 = (cse_var_2 + 46)
- let cse_var_103: int32 = (cse_var_2 + 45)
- let cse_var_102: int32 = (cse_var_2 + 44)
- let cse_var_101: int32 = (cse_var_2 + 43)
- let cse_var_100: int32 = (cse_var_2 + 42)
- let cse_var_99: int32 = (cse_var_2 + 41)
- let cse_var_98: int32 = (cse_var_2 + 40)
- let cse_var_97: int32 = (cse_var_2 + 4)
- let cse_var_96: int32 = (cse_var_2 + 39)
- let cse_var_95: int32 = (cse_var_2 + 38)
- let cse_var_94: int32 = (cse_var_2 + 37)
- let cse_var_93: int32 = (cse_var_2 + 36)
- let cse_var_92: int32 = (cse_var_2 + 35)
- let cse_var_91: int32 = (cse_var_2 + 34)
- let cse_var_90: int32 = (cse_var_2 + 33)
- let cse_var_89: int32 = (cse_var_2 + 32)
- let cse_var_88: int32 = (cse_var_2 + 3)
- let cse_var_87: int32 = (cse_var_2 + 239)
- let cse_var_86: int32 = (cse_var_2 + 238)
- let cse_var_85: int32 = (cse_var_2 + 237)
- let cse_var_84: int32 = (cse_var_2 + 236)
- let cse_var_83: int32 = (cse_var_2 + 235)
- let cse_var_82: int32 = (cse_var_2 + 234)
- let cse_var_81: int32 = (cse_var_2 + 233)
- let cse_var_80: int32 = (cse_var_2 + 232)
- let cse_var_79: int32 = (cse_var_2 + 231)
- let cse_var_78: int32 = (cse_var_2 + 230)
- let cse_var_77: int32 = (cse_var_2 + 229)
- let cse_var_76: int32 = (cse_var_2 + 228)
- let cse_var_75: int32 = (cse_var_2 + 227)
- let cse_var_74: int32 = (cse_var_2 + 226)
- let cse_var_73: int32 = (cse_var_2 + 225)
- let cse_var_72: int32 = (cse_var_2 + 224)
- let cse_var_71: int32 = (cse_var_2 + 207)
- let cse_var_70: int32 = (cse_var_2 + 206)
- let cse_var_69: int32 = (cse_var_2 + 205)
- let cse_var_68: int32 = (cse_var_2 + 204)
- let cse_var_67: int32 = (cse_var_2 + 203)
- let cse_var_66: int32 = (cse_var_2 + 202)
- let cse_var_65: int32 = (cse_var_2 + 201)
- let cse_var_64: int32 = (cse_var_2 + 200)
- let cse_var_63: int32 = (cse_var_2 + 2)
- let cse_var_62: int32 = (cse_var_2 + 199)
- let cse_var_61: int32 = (cse_var_2 + 198)
- let cse_var_60: int32 = (cse_var_2 + 197)
- let cse_var_59: int32 = (cse_var_2 + 196)
- let cse_var_58: int32 = (cse_var_2 + 195)
- let cse_var_57: int32 = (cse_var_2 + 194)
- let cse_var_56: int32 = (cse_var_2 + 193)
- let cse_var_55: int32 = (cse_var_2 + 192)
- let cse_var_54: int32 = (cse_var_2 + 175)
- let cse_var_53: int32 = (cse_var_2 + 174)
- let cse_var_52: int32 = (cse_var_2 + 173)
- let cse_var_51: int32 = (cse_var_2 + 172)
- let cse_var_50: int32 = (cse_var_2 + 171)
- let cse_var_49: int32 = (cse_var_2 + 170)
- let cse_var_48: int32 = (cse_var_2 + 169)
- let cse_var_47: int32 = (cse_var_2 + 168)
- let cse_var_46: int32 = (cse_var_2 + 167)
- let cse_var_45: int32 = (cse_var_2 + 166)
- let cse_var_44: int32 = (cse_var_2 + 165)
- let cse_var_43: int32 = (cse_var_2 + 164)
- let cse_var_42: int32 = (cse_var_2 + 163)
- let cse_var_41: int32 = (cse_var_2 + 162)
- let cse_var_40: int32 = (cse_var_2 + 161)
- let cse_var_39: int32 = (cse_var_2 + 160)
- let cse_var_38: int32 = (cse_var_2 + 15)
- let cse_var_37: int32 = (cse_var_2 + 143)
- let cse_var_36: int32 = (cse_var_2 + 142)
- let cse_var_35: int32 = (cse_var_2 + 141)
- let cse_var_34: int32 = (cse_var_2 + 140)
- let cse_var_33: int32 = (cse_var_2 + 14)
- let cse_var_32: int32 = (cse_var_2 + 139)
- let cse_var_31: int32 = (cse_var_2 + 138)
- let cse_var_30: int32 = (cse_var_2 + 137)
- let cse_var_29: int32 = (cse_var_2 + 136)
- let cse_var_28: int32 = (cse_var_2 + 135)
- let cse_var_27: int32 = (cse_var_2 + 134)
- let cse_var_26: int32 = (cse_var_2 + 133)
- let cse_var_25: int32 = (cse_var_2 + 132)
- let cse_var_24: int32 = (cse_var_2 + 131)
- let cse_var_23: int32 = (cse_var_2 + 130)
- let cse_var_22: int32 = (cse_var_2 + 13)
- let cse_var_21: int32 = (cse_var_2 + 129)
- let cse_var_20: int32 = (cse_var_2 + 128)
- let cse_var_19: int32 = (cse_var_2 + 12)
- let cse_var_18: int32 = (cse_var_2 + 111)
- let cse_var_17: int32 = (cse_var_2 + 110)
- let cse_var_16: int32 = (cse_var_2 + 11)
- let cse_var_15: int32 = (cse_var_2 + 109)
- let cse_var_14: int32 = (cse_var_2 + 108)
- let cse_var_13: int32 = (cse_var_2 + 107)
- let cse_var_12: int32 = (cse_var_2 + 106)
- let cse_var_11: int32 = (cse_var_2 + 105)
- let cse_var_10: int32 = (cse_var_2 + 104)
- let cse_var_9: int32 = (cse_var_2 + 103)
- let cse_var_8: int32 = (cse_var_2 + 102)
- let cse_var_7: int32 = (cse_var_2 + 101)
- let cse_var_6: int32 = (cse_var_2 + 100)
- let cse_var_5: int32 = (cse_var_2 + 10)
- let cse_var_4: int32 = (cse_var_2 + 1)
- let cse_var_3: int32 = (floordiv(i0.outer.i1.outer.fused, 16)*2048)
- {
- compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_3 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_63] = (compute_4[cse_var_63] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_88] = (compute_4[cse_var_88] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_97] = (compute_4[cse_var_97] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_106] = (compute_4[cse_var_106] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_107] = (compute_4[cse_var_107] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_114] = (compute_4[cse_var_114] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_125] = (compute_4[cse_var_125] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_126] = (compute_4[cse_var_126] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_22] = (compute_4[cse_var_22] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_33] = (compute_4[cse_var_33] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_38] = (compute_4[cse_var_38] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_89] = (compute_4[cse_var_89] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_90] = (compute_4[cse_var_90] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_91] = (compute_4[cse_var_91] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_92] = (compute_4[cse_var_92] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_93] = (compute_4[cse_var_93] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_94] = (compute_4[cse_var_94] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_95] = (compute_4[cse_var_95] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_96] = (compute_4[cse_var_96] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_98] = (compute_4[cse_var_98] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_99] = (compute_4[cse_var_99] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_100] = (compute_4[cse_var_100] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_101] = (compute_4[cse_var_101] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_102] = (compute_4[cse_var_102] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_103] = (compute_4[cse_var_103] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_104] = (compute_4[cse_var_104] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_105] = (compute_4[cse_var_105] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_108] = (compute_4[cse_var_108] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_109] = (compute_4[cse_var_109] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_110] = (compute_4[cse_var_110] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_111] = (compute_4[cse_var_111] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_112] = (compute_4[cse_var_112] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_113] = (compute_4[cse_var_113] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_115] = (compute_4[cse_var_115] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_116] = (compute_4[cse_var_116] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_117] = (compute_4[cse_var_117] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_118] = (compute_4[cse_var_118] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_119] = (compute_4[cse_var_119] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_120] = (compute_4[cse_var_120] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_121] = (compute_4[cse_var_121] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_122] = (compute_4[cse_var_122] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_123] = (compute_4[cse_var_123] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_124] = (compute_4[cse_var_124] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_127] = (compute_4[cse_var_127] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_128] = (compute_4[cse_var_128] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_129] = (compute_4[cse_var_129] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_130] = (compute_4[cse_var_130] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_20] = (compute_4[cse_var_20] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_21] = (compute_4[cse_var_21] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_23] = (compute_4[cse_var_23] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_24] = (compute_4[cse_var_24] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_25] = (compute_4[cse_var_25] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_26] = (compute_4[cse_var_26] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_27] = (compute_4[cse_var_27] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_28] = (compute_4[cse_var_28] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_29] = (compute_4[cse_var_29] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_30] = (compute_4[cse_var_30] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_31] = (compute_4[cse_var_31] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_32] = (compute_4[cse_var_32] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_34] = (compute_4[cse_var_34] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_35] = (compute_4[cse_var_35] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_36] = (compute_4[cse_var_36] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_37] = (compute_4[cse_var_37] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_39] = (compute_4[cse_var_39] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_40] = (compute_4[cse_var_40] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_41] = (compute_4[cse_var_41] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_42] = (compute_4[cse_var_42] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_43] = (compute_4[cse_var_43] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_44] = (compute_4[cse_var_44] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_45] = (compute_4[cse_var_45] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_46] = (compute_4[cse_var_46] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_47] = (compute_4[cse_var_47] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_48] = (compute_4[cse_var_48] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_49] = (compute_4[cse_var_49] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_50] = (compute_4[cse_var_50] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_51] = (compute_4[cse_var_51] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_52] = (compute_4[cse_var_52] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_53] = (compute_4[cse_var_53] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_54] = (compute_4[cse_var_54] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_55] = (compute_4[cse_var_55] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_56] = (compute_4[cse_var_56] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_57] = (compute_4[cse_var_57] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_58] = (compute_4[cse_var_58] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_59] = (compute_4[cse_var_59] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_60] = (compute_4[cse_var_60] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_61] = (compute_4[cse_var_61] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_62] = (compute_4[cse_var_62] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_64] = (compute_4[cse_var_64] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_65] = (compute_4[cse_var_65] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_66] = (compute_4[cse_var_66] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_67] = (compute_4[cse_var_67] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_68] = (compute_4[cse_var_68] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_69] = (compute_4[cse_var_69] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_70] = (compute_4[cse_var_70] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_71] = (compute_4[cse_var_71] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_72] = (compute_4[cse_var_72] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_73] = (compute_4[cse_var_73] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_74] = (compute_4[cse_var_74] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_75] = (compute_4[cse_var_75] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_76] = (compute_4[cse_var_76] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_77] = (compute_4[cse_var_77] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_78] = (compute_4[cse_var_78] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_79] = (compute_4[cse_var_79] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_80] = (compute_4[cse_var_80] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_81] = (compute_4[cse_var_81] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_82] = (compute_4[cse_var_82] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_83] = (compute_4[cse_var_83] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_84] = (compute_4[cse_var_84] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_85] = (compute_4[cse_var_85] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_86] = (compute_4[cse_var_86] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_87] = (compute_4[cse_var_87] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4: Buffer(compute_3, float32, [2048], [])[cse_var_1] = 0f32
+ compute_4[(cse_var_1 + 1)] = 0f32
+ compute_4[(cse_var_1 + 2)] = 0f32
+ compute_4[(cse_var_1 + 3)] = 0f32
+ compute_4[(cse_var_1 + 4)] = 0f32
+ compute_4[(cse_var_1 + 5)] = 0f32
+ compute_4[(cse_var_1 + 6)] = 0f32
+ compute_4[(cse_var_1 + 7)] = 0f32
+ compute_4[(cse_var_1 + 8)] = 0f32
+ compute_4[(cse_var_1 + 9)] = 0f32
+ compute_4[(cse_var_1 + 10)] = 0f32
+ compute_4[(cse_var_1 + 11)] = 0f32
+ compute_4[(cse_var_1 + 12)] = 0f32
+ compute_4[(cse_var_1 + 13)] = 0f32
+ compute_4[(cse_var_1 + 14)] = 0f32
+ compute_4[(cse_var_1 + 15)] = 0f32
+ compute_4[(cse_var_1 + 16)] = 0f32
+ compute_4[(cse_var_1 + 17)] = 0f32
+ compute_4[(cse_var_1 + 18)] = 0f32
+ compute_4[(cse_var_1 + 19)] = 0f32
+ compute_4[(cse_var_1 + 20)] = 0f32
+ compute_4[(cse_var_1 + 21)] = 0f32
+ compute_4[(cse_var_1 + 22)] = 0f32
+ compute_4[(cse_var_1 + 23)] = 0f32
+ compute_4[(cse_var_1 + 24)] = 0f32
+ compute_4[(cse_var_1 + 25)] = 0f32
+ compute_4[(cse_var_1 + 26)] = 0f32
+ compute_4[(cse_var_1 + 27)] = 0f32
+ compute_4[(cse_var_1 + 28)] = 0f32
+ compute_4[(cse_var_1 + 29)] = 0f32
+ compute_4[(cse_var_1 + 30)] = 0f32
+ compute_4[(cse_var_1 + 31)] = 0f32
+ compute_4[(cse_var_1 + 32)] = 0f32
+ compute_4[(cse_var_1 + 33)] = 0f32
+ compute_4[(cse_var_1 + 34)] = 0f32
+ compute_4[(cse_var_1 + 35)] = 0f32
+ compute_4[(cse_var_1 + 36)] = 0f32
+ compute_4[(cse_var_1 + 37)] = 0f32
+ compute_4[(cse_var_1 + 38)] = 0f32
+ compute_4[(cse_var_1 + 39)] = 0f32
+ compute_4[(cse_var_1 + 40)] = 0f32
+ compute_4[(cse_var_1 + 41)] = 0f32
+ compute_4[(cse_var_1 + 42)] = 0f32
+ compute_4[(cse_var_1 + 43)] = 0f32
+ compute_4[(cse_var_1 + 44)] = 0f32
+ compute_4[(cse_var_1 + 45)] = 0f32
+ compute_4[(cse_var_1 + 46)] = 0f32
+ compute_4[(cse_var_1 + 47)] = 0f32
+ compute_4[(cse_var_1 + 48)] = 0f32
+ compute_4[(cse_var_1 + 49)] = 0f32
+ compute_4[(cse_var_1 + 50)] = 0f32
+ compute_4[(cse_var_1 + 51)] = 0f32
+ compute_4[(cse_var_1 + 52)] = 0f32
+ compute_4[(cse_var_1 + 53)] = 0f32
+ compute_4[(cse_var_1 + 54)] = 0f32
+ compute_4[(cse_var_1 + 55)] = 0f32
+ compute_4[(cse_var_1 + 56)] = 0f32
+ compute_4[(cse_var_1 + 57)] = 0f32
+ compute_4[(cse_var_1 + 58)] = 0f32
+ compute_4[(cse_var_1 + 59)] = 0f32
+ compute_4[(cse_var_1 + 60)] = 0f32
+ compute_4[(cse_var_1 + 61)] = 0f32
+ compute_4[(cse_var_1 + 62)] = 0f32
+ compute_4[(cse_var_1 + 63)] = 0f32
+ compute_4[(cse_var_1 + 64)] = 0f32
+ compute_4[(cse_var_1 + 65)] = 0f32
+ compute_4[(cse_var_1 + 66)] = 0f32
+ compute_4[(cse_var_1 + 67)] = 0f32
+ compute_4[(cse_var_1 + 68)] = 0f32
+ compute_4[(cse_var_1 + 69)] = 0f32
+ compute_4[(cse_var_1 + 70)] = 0f32
+ compute_4[(cse_var_1 + 71)] = 0f32
+ compute_4[(cse_var_1 + 72)] = 0f32
+ compute_4[(cse_var_1 + 73)] = 0f32
+ compute_4[(cse_var_1 + 74)] = 0f32
+ compute_4[(cse_var_1 + 75)] = 0f32
+ compute_4[(cse_var_1 + 76)] = 0f32
+ compute_4[(cse_var_1 + 77)] = 0f32
+ compute_4[(cse_var_1 + 78)] = 0f32
+ compute_4[(cse_var_1 + 79)] = 0f32
+ compute_4[(cse_var_1 + 80)] = 0f32
+ compute_4[(cse_var_1 + 81)] = 0f32
+ compute_4[(cse_var_1 + 82)] = 0f32
+ compute_4[(cse_var_1 + 83)] = 0f32
+ compute_4[(cse_var_1 + 84)] = 0f32
+ compute_4[(cse_var_1 + 85)] = 0f32
+ compute_4[(cse_var_1 + 86)] = 0f32
+ compute_4[(cse_var_1 + 87)] = 0f32
+ compute_4[(cse_var_1 + 88)] = 0f32
+ compute_4[(cse_var_1 + 89)] = 0f32
+ compute_4[(cse_var_1 + 90)] = 0f32
+ compute_4[(cse_var_1 + 91)] = 0f32
+ compute_4[(cse_var_1 + 92)] = 0f32
+ compute_4[(cse_var_1 + 93)] = 0f32
+ compute_4[(cse_var_1 + 94)] = 0f32
+ compute_4[(cse_var_1 + 95)] = 0f32
+ compute_4[(cse_var_1 + 96)] = 0f32
+ compute_4[(cse_var_1 + 97)] = 0f32
+ compute_4[(cse_var_1 + 98)] = 0f32
+ compute_4[(cse_var_1 + 99)] = 0f32
+ compute_4[(cse_var_1 + 100)] = 0f32
+ compute_4[(cse_var_1 + 101)] = 0f32
+ compute_4[(cse_var_1 + 102)] = 0f32
+ compute_4[(cse_var_1 + 103)] = 0f32
+ compute_4[(cse_var_1 + 104)] = 0f32
+ compute_4[(cse_var_1 + 105)] = 0f32
+ compute_4[(cse_var_1 + 106)] = 0f32
+ compute_4[(cse_var_1 + 107)] = 0f32
+ compute_4[(cse_var_1 + 108)] = 0f32
+ compute_4[(cse_var_1 + 109)] = 0f32
+ compute_4[(cse_var_1 + 110)] = 0f32
+ compute_4[(cse_var_1 + 111)] = 0f32
+ compute_4[(cse_var_1 + 112)] = 0f32
+ compute_4[(cse_var_1 + 113)] = 0f32
+ compute_4[(cse_var_1 + 114)] = 0f32
+ compute_4[(cse_var_1 + 115)] = 0f32
+ compute_4[(cse_var_1 + 116)] = 0f32
+ compute_4[(cse_var_1 + 117)] = 0f32
+ compute_4[(cse_var_1 + 118)] = 0f32
+ compute_4[(cse_var_1 + 119)] = 0f32
+ compute_4[(cse_var_1 + 120)] = 0f32
+ compute_4[(cse_var_1 + 121)] = 0f32
+ compute_4[(cse_var_1 + 122)] = 0f32
+ compute_4[(cse_var_1 + 123)] = 0f32
+ compute_4[(cse_var_1 + 124)] = 0f32
+ compute_4[(cse_var_1 + 125)] = 0f32
+ compute_4[(cse_var_1 + 126)] = 0f32
+ compute_4[(cse_var_1 + 127)] = 0f32
+ for (elem_idx: int32, 0, (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])) {
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ compute_4[cse_var_1] = (compute_4[cse_var_1] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((i.outer.inner*2048) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_2: int32 = (cse_var_1 + 1)
+ compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_3: int32 = (cse_var_1 + 2)
+ compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_4: int32 = (cse_var_1 + 3)
+ compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_5: int32 = (cse_var_1 + 4)
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_6: int32 = (cse_var_1 + 5)
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_7: int32 = (cse_var_1 + 6)
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_8: int32 = (cse_var_1 + 7)
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_9: int32 = (cse_var_1 + 8)
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_10: int32 = (cse_var_1 + 9)
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_11: int32 = (cse_var_1 + 10)
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_12: int32 = (cse_var_1 + 11)
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_13: int32 = (cse_var_1 + 12)
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_14: int32 = (cse_var_1 + 13)
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_15: int32 = (cse_var_1 + 14)
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_16: int32 = (cse_var_1 + 15)
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_17: int32 = (cse_var_1 + 16)
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_18: int32 = (cse_var_1 + 17)
+ compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_19: int32 = (cse_var_1 + 18)
+ compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_20: int32 = (cse_var_1 + 19)
+ compute_4[cse_var_20] = (compute_4[cse_var_20] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_21: int32 = (cse_var_1 + 20)
+ compute_4[cse_var_21] = (compute_4[cse_var_21] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_22: int32 = (cse_var_1 + 21)
+ compute_4[cse_var_22] = (compute_4[cse_var_22] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_23: int32 = (cse_var_1 + 22)
+ compute_4[cse_var_23] = (compute_4[cse_var_23] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_24: int32 = (cse_var_1 + 23)
+ compute_4[cse_var_24] = (compute_4[cse_var_24] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_25: int32 = (cse_var_1 + 24)
+ compute_4[cse_var_25] = (compute_4[cse_var_25] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_26: int32 = (cse_var_1 + 25)
+ compute_4[cse_var_26] = (compute_4[cse_var_26] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_27: int32 = (cse_var_1 + 26)
+ compute_4[cse_var_27] = (compute_4[cse_var_27] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_28: int32 = (cse_var_1 + 27)
+ compute_4[cse_var_28] = (compute_4[cse_var_28] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_29: int32 = (cse_var_1 + 28)
+ compute_4[cse_var_29] = (compute_4[cse_var_29] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_30: int32 = (cse_var_1 + 29)
+ compute_4[cse_var_30] = (compute_4[cse_var_30] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_31: int32 = (cse_var_1 + 30)
+ compute_4[cse_var_31] = (compute_4[cse_var_31] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_32: int32 = (cse_var_1 + 31)
+ compute_4[cse_var_32] = (compute_4[cse_var_32] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 256)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_33: int32 = (cse_var_1 + 32)
+ compute_4[cse_var_33] = (compute_4[cse_var_33] + (placeholder_16[((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_34: int32 = (cse_var_1 + 33)
+ compute_4[cse_var_34] = (compute_4[cse_var_34] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_35: int32 = (cse_var_1 + 34)
+ compute_4[cse_var_35] = (compute_4[cse_var_35] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_36: int32 = (cse_var_1 + 35)
+ compute_4[cse_var_36] = (compute_4[cse_var_36] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_37: int32 = (cse_var_1 + 36)
+ compute_4[cse_var_37] = (compute_4[cse_var_37] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_38: int32 = (cse_var_1 + 37)
+ compute_4[cse_var_38] = (compute_4[cse_var_38] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_39: int32 = (cse_var_1 + 38)
+ compute_4[cse_var_39] = (compute_4[cse_var_39] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_40: int32 = (cse_var_1 + 39)
+ compute_4[cse_var_40] = (compute_4[cse_var_40] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_41: int32 = (cse_var_1 + 40)
+ compute_4[cse_var_41] = (compute_4[cse_var_41] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_42: int32 = (cse_var_1 + 41)
+ compute_4[cse_var_42] = (compute_4[cse_var_42] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_43: int32 = (cse_var_1 + 42)
+ compute_4[cse_var_43] = (compute_4[cse_var_43] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_44: int32 = (cse_var_1 + 43)
+ compute_4[cse_var_44] = (compute_4[cse_var_44] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_45: int32 = (cse_var_1 + 44)
+ compute_4[cse_var_45] = (compute_4[cse_var_45] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_46: int32 = (cse_var_1 + 45)
+ compute_4[cse_var_46] = (compute_4[cse_var_46] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_47: int32 = (cse_var_1 + 46)
+ compute_4[cse_var_47] = (compute_4[cse_var_47] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_48: int32 = (cse_var_1 + 47)
+ compute_4[cse_var_48] = (compute_4[cse_var_48] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 512)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_49: int32 = (cse_var_1 + 48)
+ compute_4[cse_var_49] = (compute_4[cse_var_49] + (placeholder_16[((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_50: int32 = (cse_var_1 + 49)
+ compute_4[cse_var_50] = (compute_4[cse_var_50] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_51: int32 = (cse_var_1 + 50)
+ compute_4[cse_var_51] = (compute_4[cse_var_51] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_52: int32 = (cse_var_1 + 51)
+ compute_4[cse_var_52] = (compute_4[cse_var_52] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_53: int32 = (cse_var_1 + 52)
+ compute_4[cse_var_53] = (compute_4[cse_var_53] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_54: int32 = (cse_var_1 + 53)
+ compute_4[cse_var_54] = (compute_4[cse_var_54] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_55: int32 = (cse_var_1 + 54)
+ compute_4[cse_var_55] = (compute_4[cse_var_55] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_56: int32 = (cse_var_1 + 55)
+ compute_4[cse_var_56] = (compute_4[cse_var_56] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_57: int32 = (cse_var_1 + 56)
+ compute_4[cse_var_57] = (compute_4[cse_var_57] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_58: int32 = (cse_var_1 + 57)
+ compute_4[cse_var_58] = (compute_4[cse_var_58] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_59: int32 = (cse_var_1 + 58)
+ compute_4[cse_var_59] = (compute_4[cse_var_59] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_60: int32 = (cse_var_1 + 59)
+ compute_4[cse_var_60] = (compute_4[cse_var_60] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_61: int32 = (cse_var_1 + 60)
+ compute_4[cse_var_61] = (compute_4[cse_var_61] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_62: int32 = (cse_var_1 + 61)
+ compute_4[cse_var_62] = (compute_4[cse_var_62] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_63: int32 = (cse_var_1 + 62)
+ compute_4[cse_var_63] = (compute_4[cse_var_63] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_64: int32 = (cse_var_1 + 63)
+ compute_4[cse_var_64] = (compute_4[cse_var_64] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 768)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_65: int32 = (cse_var_1 + 64)
+ compute_4[cse_var_65] = (compute_4[cse_var_65] + (placeholder_16[((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_66: int32 = (cse_var_1 + 65)
+ compute_4[cse_var_66] = (compute_4[cse_var_66] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_67: int32 = (cse_var_1 + 66)
+ compute_4[cse_var_67] = (compute_4[cse_var_67] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_68: int32 = (cse_var_1 + 67)
+ compute_4[cse_var_68] = (compute_4[cse_var_68] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_69: int32 = (cse_var_1 + 68)
+ compute_4[cse_var_69] = (compute_4[cse_var_69] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_70: int32 = (cse_var_1 + 69)
+ compute_4[cse_var_70] = (compute_4[cse_var_70] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_71: int32 = (cse_var_1 + 70)
+ compute_4[cse_var_71] = (compute_4[cse_var_71] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_72: int32 = (cse_var_1 + 71)
+ compute_4[cse_var_72] = (compute_4[cse_var_72] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_73: int32 = (cse_var_1 + 72)
+ compute_4[cse_var_73] = (compute_4[cse_var_73] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_74: int32 = (cse_var_1 + 73)
+ compute_4[cse_var_74] = (compute_4[cse_var_74] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_75: int32 = (cse_var_1 + 74)
+ compute_4[cse_var_75] = (compute_4[cse_var_75] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_76: int32 = (cse_var_1 + 75)
+ compute_4[cse_var_76] = (compute_4[cse_var_76] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_77: int32 = (cse_var_1 + 76)
+ compute_4[cse_var_77] = (compute_4[cse_var_77] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_78: int32 = (cse_var_1 + 77)
+ compute_4[cse_var_78] = (compute_4[cse_var_78] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_79: int32 = (cse_var_1 + 78)
+ compute_4[cse_var_79] = (compute_4[cse_var_79] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_80: int32 = (cse_var_1 + 79)
+ compute_4[cse_var_80] = (compute_4[cse_var_80] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1024)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_81: int32 = (cse_var_1 + 80)
+ compute_4[cse_var_81] = (compute_4[cse_var_81] + (placeholder_16[((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_82: int32 = (cse_var_1 + 81)
+ compute_4[cse_var_82] = (compute_4[cse_var_82] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_83: int32 = (cse_var_1 + 82)
+ compute_4[cse_var_83] = (compute_4[cse_var_83] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_84: int32 = (cse_var_1 + 83)
+ compute_4[cse_var_84] = (compute_4[cse_var_84] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_85: int32 = (cse_var_1 + 84)
+ compute_4[cse_var_85] = (compute_4[cse_var_85] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_86: int32 = (cse_var_1 + 85)
+ compute_4[cse_var_86] = (compute_4[cse_var_86] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_87: int32 = (cse_var_1 + 86)
+ compute_4[cse_var_87] = (compute_4[cse_var_87] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_88: int32 = (cse_var_1 + 87)
+ compute_4[cse_var_88] = (compute_4[cse_var_88] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_89: int32 = (cse_var_1 + 88)
+ compute_4[cse_var_89] = (compute_4[cse_var_89] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_90: int32 = (cse_var_1 + 89)
+ compute_4[cse_var_90] = (compute_4[cse_var_90] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_91: int32 = (cse_var_1 + 90)
+ compute_4[cse_var_91] = (compute_4[cse_var_91] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_92: int32 = (cse_var_1 + 91)
+ compute_4[cse_var_92] = (compute_4[cse_var_92] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_93: int32 = (cse_var_1 + 92)
+ compute_4[cse_var_93] = (compute_4[cse_var_93] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_94: int32 = (cse_var_1 + 93)
+ compute_4[cse_var_94] = (compute_4[cse_var_94] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_95: int32 = (cse_var_1 + 94)
+ compute_4[cse_var_95] = (compute_4[cse_var_95] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_96: int32 = (cse_var_1 + 95)
+ compute_4[cse_var_96] = (compute_4[cse_var_96] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1280)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_97: int32 = (cse_var_1 + 96)
+ compute_4[cse_var_97] = (compute_4[cse_var_97] + (placeholder_16[((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_98: int32 = (cse_var_1 + 97)
+ compute_4[cse_var_98] = (compute_4[cse_var_98] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_99: int32 = (cse_var_1 + 98)
+ compute_4[cse_var_99] = (compute_4[cse_var_99] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_100: int32 = (cse_var_1 + 99)
+ compute_4[cse_var_100] = (compute_4[cse_var_100] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_101: int32 = (cse_var_1 + 100)
+ compute_4[cse_var_101] = (compute_4[cse_var_101] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_102: int32 = (cse_var_1 + 101)
+ compute_4[cse_var_102] = (compute_4[cse_var_102] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_103: int32 = (cse_var_1 + 102)
+ compute_4[cse_var_103] = (compute_4[cse_var_103] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_104: int32 = (cse_var_1 + 103)
+ compute_4[cse_var_104] = (compute_4[cse_var_104] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_105: int32 = (cse_var_1 + 104)
+ compute_4[cse_var_105] = (compute_4[cse_var_105] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_106: int32 = (cse_var_1 + 105)
+ compute_4[cse_var_106] = (compute_4[cse_var_106] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_107: int32 = (cse_var_1 + 106)
+ compute_4[cse_var_107] = (compute_4[cse_var_107] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_108: int32 = (cse_var_1 + 107)
+ compute_4[cse_var_108] = (compute_4[cse_var_108] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_109: int32 = (cse_var_1 + 108)
+ compute_4[cse_var_109] = (compute_4[cse_var_109] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_110: int32 = (cse_var_1 + 109)
+ compute_4[cse_var_110] = (compute_4[cse_var_110] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_111: int32 = (cse_var_1 + 110)
+ compute_4[cse_var_111] = (compute_4[cse_var_111] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_112: int32 = (cse_var_1 + 111)
+ compute_4[cse_var_112] = (compute_4[cse_var_112] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1536)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_113: int32 = (cse_var_1 + 112)
+ compute_4[cse_var_113] = (compute_4[cse_var_113] + (placeholder_16[((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_114: int32 = (cse_var_1 + 113)
+ compute_4[cse_var_114] = (compute_4[cse_var_114] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_115: int32 = (cse_var_1 + 114)
+ compute_4[cse_var_115] = (compute_4[cse_var_115] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_116: int32 = (cse_var_1 + 115)
+ compute_4[cse_var_116] = (compute_4[cse_var_116] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_117: int32 = (cse_var_1 + 116)
+ compute_4[cse_var_117] = (compute_4[cse_var_117] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_118: int32 = (cse_var_1 + 117)
+ compute_4[cse_var_118] = (compute_4[cse_var_118] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_119: int32 = (cse_var_1 + 118)
+ compute_4[cse_var_119] = (compute_4[cse_var_119] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_120: int32 = (cse_var_1 + 119)
+ compute_4[cse_var_120] = (compute_4[cse_var_120] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_121: int32 = (cse_var_1 + 120)
+ compute_4[cse_var_121] = (compute_4[cse_var_121] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_122: int32 = (cse_var_1 + 121)
+ compute_4[cse_var_122] = (compute_4[cse_var_122] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_123: int32 = (cse_var_1 + 122)
+ compute_4[cse_var_123] = (compute_4[cse_var_123] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_124: int32 = (cse_var_1 + 123)
+ compute_4[cse_var_124] = (compute_4[cse_var_124] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_125: int32 = (cse_var_1 + 124)
+ compute_4[cse_var_125] = (compute_4[cse_var_125] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_126: int32 = (cse_var_1 + 125)
+ compute_4[cse_var_126] = (compute_4[cse_var_126] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_127: int32 = (cse_var_1 + 126)
+ compute_4[cse_var_127] = (compute_4[cse_var_127] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_128: int32 = (cse_var_1 + 127)
+ compute_4[cse_var_128] = (compute_4[cse_var_128] + (placeholder_16[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[(((i.outer.inner*2048) + placeholder_18[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)]) + 1792)], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 8) {
- for (i1.inner: int32, 0, 32) {
- let cse_var_132: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
- compute_5: Buffer(compute_2, float32, [65536], [])[cse_var_132] = max((compute_4[((i0.inner*32) + i1.inner)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[cse_var_132]), 0f32)
- }
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_129: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*16))
+ compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_129, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_129, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -1071,7 +1320,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.713 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.712 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 090385133a..fbcd5039cf 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:40.913</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:53.282</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</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>00:40.875</p></td>
+<td><p>00:53.247</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>00:00.022</p></td>
+<td><p>00:00.020</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_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 41168745d1..ade5eed1dc 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -567,8 +567,7 @@ for this template</p>
waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 20.64/20.64 result: MeasureResult(costs=(0.011214620777777776,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8706092834472656, timestamp=1671134424.2356322) [('tile_f', [-1, 16, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,600394
-No: 2 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -690,8 +689,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1280805
-No: 3 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2244356
+No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -813,272 +812,161 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4819687
-No: 4 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1601396
+No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
+ yield remote, remote.load_module(os.path.split(build_result.filename)[1])
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
+ costs = time_f(*args).results
+ File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
+ blob = feval(*args)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
+ 4: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1730
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 13: operator()
- at ../src/driver/driver_api.cc:388
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1749
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1693
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1617
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+ 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../src/runtime/rpc/rpc_module.cc:129
+ 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1012
+ 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
+ at ../src/runtime/rpc/rpc_endpoint.cc:804
+ File "../src/runtime/rpc/rpc_endpoint.cc", line 804
+TVMError:
+---------------------------------------------------------------
+An error occurred during the execution of TVM.
+For more information, please see: https://tvm.apache.org/docs/errors.html
+---------------------------------------------------------------
+ Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
+
+During handling of the above exception, another exception occurred:
Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1730
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 13: operator()
- at ../src/driver/driver_api.cc:388
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1749
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1693
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1617
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,743342
-No: 5 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
+ costs = time_f(*args).results
+ File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
+ self.gen.throw(type, value, traceback)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
+ remote.remove(build_result.filename)
+ File "/workspace/python/tvm/rpc/client.py", line 144, in remove
+ self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
+ File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
+ return self._sess.get_function(name)
+ File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
+ self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
+ File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
+ raise get_last_ffi_error()
tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1730
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 13: operator()
- at ../src/driver/driver_api.cc:388
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1749
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1693
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ 52: 0xffffffffffffffff
+ 51: _start
+ 50: __libc_start_main
+ 49: _Py_UnixMain
+ 48: 0x0000000000650da0
+ 47: 0x0000000000650afa
+ 46: _PyFunction_FastCallDict
+ 45: _PyEval_EvalCodeWithName
+ 44: _PyEval_EvalFrameDefault
+ 43: _PyFunction_FastCallKeywords
+ 42: _PyEval_EvalCodeWithName
+ 41: _PyEval_EvalFrameDefault
+ 40: _PyMethodDef_RawFastCallKeywords
+ 39: 0x0000000000546369
+ 38: _PyEval_EvalCodeWithName
+ 37: _PyEval_EvalFrameDefault
+ 36: _PyFunction_FastCallKeywords
+ 35: _PyEval_EvalCodeWithName
+ 34: _PyEval_EvalFrameDefault
+ 33: _PyFunction_FastCallDict
+ 32: _PyEval_EvalCodeWithName
+ 31: _PyEval_EvalFrameDefault
+ 30: _PyObject_FastCallDict
+ 29: 0x00000000004c06e1
+ 28: _PyFunction_FastCallDict
+ 27: _PyEval_EvalFrameDefault
+ 26: _PyMethodDescr_FastCallKeywords
+ 25: 0x00000000005dcb58
+ 24: 0x00000000005dc83f
+ 23: 0x00000000004ba127
+ 22: _PyEval_EvalFrameDefault
+ 21: _PyFunction_FastCallKeywords
+ 20: _PyEval_EvalFrameDefault
+ 19: _PyFunction_FastCallKeywords
+ 18: _PyEval_EvalFrameDefault
+ 17: _PyFunction_FastCallKeywords
+ 16: _PyEval_EvalCodeWithName
+ 15: _PyEval_EvalFrameDefault
+ 14: 0x0000000000537c30
+ 13: _PyObject_FastCallKeywords
+ 12: 0x00007f8167708fa2
+ 11: _ctypes_callproc
+ 10: ffi_call
+ 9: ffi_call_unix64
+ 8: TVMModGetFunction
+ at ../src/runtime/c_runtime_api.cc:408
+ 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
+ at ../src/runtime/module.cc:66
+ 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
+ at ../src/runtime/rpc/rpc_module.cc:185
+ 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1007
+ 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.h:223
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
at ../include/tvm/runtime/packed_func.h:1617
2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
1: Call
at ../include/tvm/runtime/packed_func.h:1213
0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+ at ../src/runtime/rpc/rpc_endpoint.cc:684
+ File "../src/runtime/rpc/rpc_endpoint.cc", line 684
+TVMError:
+---------------------------------------------------------------
+An error occurred during the execution of TVM.
+For more information, please see: https://tvm.apache.org/docs/errors.html
+---------------------------------------------------------------
+ Check failed: (code == RPCCode::kReturn) is false: code=1
Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1730
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 13: operator()
- at ../src/driver/driver_api.cc:388
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1749
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1693
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1617
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7934948
-No: 6 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
- res = future.result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
- return self.__get_result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
- raise self._exception
- File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
- result = self.fn(*self.args, **self.kwargs)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
- worker = lambda *args: self._worker_run(*args)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
- return proc.recv()
- File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
- raise TimeoutError()
-TimeoutError
-
- [('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4701736
-No: 7 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+ 52: 0xffffffffffffffff
+ 51: _start
+ 50: __libc_start_main
+ 49: _Py_UnixMain
+ 48: 0x0000000000650da0
+ 47: 0x0000000000650afa
+ 46: _PyFunction_FastCallDict
+ 45: _PyEval_EvalCodeWithName
+ 44: _PyEval_EvalFrameDefault
+ 43: _PyFunction_FastCallKeywords
+ 42: _PyEval_EvalCodeWithName
+ 41: _PyEval_EvalFrameDefault
+ 40: _PyMethodDef_RawFastCallKeywords
+ 39: 0x0000000000546369
+ 38: _PyEval_EvalCodeWithName
+ 37: _PyEval_EvalFrameDefault
+ 36: _PyFunction_FastCallKeywords
+ 35: _PyEval_EvalCodeWithName
+ 34: _PyEval_EvalFrameDefault
+ 33: _PyFunction_FastCallDict
+ 32: _PyEval_EvalCodeWithName
+ 31: _PyEval_EvalFrameDefault
+ 30: _PyObject_FastCallDict
+ 29: 0x00000000004c06e1
+ 28: _PyFunction_FastCallDict
+ 27: _PyEval_EvalFrameDefault
+ 26: _PyMethodDescr_FastCallKeywords
+ 25: 0x00000000005dcb58
+ 24: 0x00000000005dc83f
+ 23: 0x00000000004ba127
+ 22: _PyEval_EvalFrameDefault
+ 21: _PyFunction_FastCallKeywords
+ 20: _PyEval_EvalFrameDefault
+ 19: _PyFunction_FastCall [('tile_f', [-1, 4, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7096202
+No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1200,8 +1088,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9621138
-No: 8 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,422669
+No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1323,8 +1211,26 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 128]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9797251
-No: 9 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7791711
+No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+TimeoutError
+
+ [('tile_f', [-1, 32, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8178075
+No: 7 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1446,8 +1352,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5319969
-No: 10 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4596761
+No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1569,8 +1475,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1920700
-No: 11 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1953322
+No: 9 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1692,8 +1598,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9238852
-No: 12 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 256, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8950973
+No: 10 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1815,8 +1721,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6910795
-No: 13 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8518019
+No: 11 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1938,8 +1844,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6661236
-No: 14 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8316157
+No: 12 GFLOPS: 2.06/2.06 result: MeasureResult(costs=(0.1121591415,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.885895013809204, timestamp=1671150812.0305164) [('tile_f', [-1, 32, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6493580
+No: 13 GFLOPS: 0.00/2.06 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2061,8 +1968,10 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1342482
-No: 15 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2431251
+No: 14 GFLOPS: 2.24/2.24 result: MeasureResult(costs=(0.10351821124999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.995007276535034, timestamp=1671150816.201508) [('tile_f', [-1, 2, 4, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8200708
+No: 15 GFLOPS: 36.88/36.88 result: MeasureResult(costs=(0.0062773861875,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.57865571975708, timestamp=1671150816.9564357) [('tile_f', [-1, 2, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5543275
+No: 16 GFLOPS: 0.00/36.88 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2184,9 +2093,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2505094
-No: 16 GFLOPS: 3.72/20.64 result: MeasureResult(costs=(0.0622214735,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.070925235748291, timestamp=1671134443.9414694) [('tile_f', [-1, 1, 1, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7310324
-No: 17 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6237617
+No: 17 GFLOPS: 0.00/36.88 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2308,8 +2216,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7492083
-No: 18 GFLOPS: 0.00/20.64 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7409293
+No: 18 GFLOPS: 63.89/63.89 result: MeasureResult(costs=(0.0036235520357142856,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6129930019378662, timestamp=1671150818.7755003) [('tile_f', [-1, 64, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8330545
+No: 19 GFLOPS: 0.00/63.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2431,9 +2340,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9712757
-No: 19 GFLOPS: 58.33/58.33 result: MeasureResult(costs=(0.003968929269230769,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3788962364196777, timestamp=1671134445.5341394) [('tile_f', [-1, 4, 64, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3502056
-No: 20 GFLOPS: 2.20/58.33 result: MeasureResult(costs=(0.10519447325,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.414799451828003, timestamp=1671134447.3109863) [('tile_f', [-1, 8, 1, 16]), ('tile_y', [-1, 1, 1, 7]), ('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', 0)],None,842107
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4184767
+No: 20 GFLOPS: 22.83/63.89 result: MeasureResult(costs=(0.010139647600000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2491390705108643, timestamp=1671150819.5261936) [('tile_f', [-1, 1, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,483015
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2472,9 +2380,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 4, 64, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3502056
+[('tile_f', [-1, 64, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8330545
Finish loading 20 records
-Time cost of this operator: 0.004350
+Time cost of this operator: 0.004044
</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 9dade17515..2311e83860 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -598,10 +598,10 @@ 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 309.3 98.726 (1, 2, 10, 10, 3) 2 1 [309.3]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.964 (1, 6, 10, 10) 1 1 [3.021]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.309 (1, 1, 10, 10, 3) 1 1 [0.969]
-Total_time - 313.29 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.8 98.725 (1, 2, 10, 10, 3) 2 1 [312.8]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.063 0.967 (1, 6, 10, 10) 1 1 [3.063]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.978 0.309 (1, 1, 10, 10, 3) 1 1 [0.978]
+Total_time - 316.84 - - - - -
</pre></div>
</div>
</div>
@@ -653,10 +653,10 @@ 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 136.9 97.997 (1, 6, 10, 10, 1) 2 1 [136.9]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.835 1.313 (1, 6, 10, 10) 1 1 [1.835]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.964 0.69 (1, 1, 10, 10, 3) 1 1 [0.964]
-Total_time - 139.698 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 104.9 97.502 (1, 6, 10, 10, 1) 2 1 [104.9]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.773 1.648 (1, 6, 10, 10) 1 1 [1.773]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.914 0.85 (1, 3, 10, 10, 1) 1 1 [0.914]
+Total_time - 107.588 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index 18c6a74cf6..c310aaa0af 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -440,8 +440,7 @@ download a cat image and preprocess it to use as the model input.</p>
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
0%| | 0.00/3.42M [00:00<?, ?B/s]
- 61%|###### | 2.09M/3.42M [00:00<00:00, 14.0MB/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 21.7MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 93.9MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -565,7 +564,7 @@ via the host <cite>main.cc`</cite> or if a Zephyr emulated board is selected as
Torch top-1 id: 282, class name: tiger cat
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.907 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.986 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/12b9ecc04c41abaa12022061771821d1/micro_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index dd1c0cb787..eed94dba93 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -530,7 +530,7 @@ 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/tmpfzal6q_o/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpfa7d9238/images/random'
</pre></div>
</div>
</div>
@@ -590,8 +590,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [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/tmpfzal6q_o/images/target contains 8144 images
-/tmp/tmpfzal6q_o/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], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpfa7d9238/images/target contains 8144 images
+/tmp/tmpfa7d9238/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -703,13 +703,13 @@ 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: 0.2115 - accuracy: 0.9251 - val_loss: 0.1319 - val_accuracy: 0.9569 - 47s/epoch - 143ms/step
+328/328 - 44s - loss: 0.2389 - accuracy: 0.9189 - val_loss: 0.1032 - val_accuracy: 0.9630 - 44s/epoch - 134ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.0981 - accuracy: 0.9643 - val_loss: 0.1193 - val_accuracy: 0.9615 - 43s/epoch - 132ms/step
+328/328 - 40s - loss: 0.1080 - accuracy: 0.9593 - val_loss: 0.0938 - val_accuracy: 0.9671 - 40s/epoch - 123ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0727 - accuracy: 0.9723 - val_loss: 0.1170 - val_accuracy: 0.9626 - 43s/epoch - 132ms/step
+328/328 - 40s - loss: 0.0698 - accuracy: 0.9728 - val_loss: 0.1001 - val_accuracy: 0.9671 - 40s/epoch - 122ms/step
-<keras.callbacks.History object at 0x7f0a580e6ad0>
+<keras.callbacks.History object at 0x7efeb1d117d0>
</pre></div>
</div>
</div>
@@ -971,7 +971,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 42.924 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 50.743 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 9143574c07..ed982f4170 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:47.777</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:54.746</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,23 +349,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:42.924</p></td>
+<td><p>04:50.743</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:01.907</p></td>
+<td><p>01:01.986</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:51.188</p></td>
+<td><p>00:50.699</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:07.915</p></td>
+<td><p>00:07.595</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.840</p></td>
+<td><p>00:03.722</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index cea3f21608..a685abadd1 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:44.815</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:44.041</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:32.650</p></td>
+<td><p>00:32.318</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.542</p></td>
+<td><p>00:10.183</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>00:01.617</p></td>
+<td><p>00:01.533</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 8a69d8b441..ae28143b6a 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -535,7 +535,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f0a534879e0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7efeb1f0da70>
</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 5e9c38eb0f..63963ab1f8 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:06.962</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:07.495</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,27 +349,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:04.379</p></td>
+<td><p>00:04.960</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:01.206</p></td>
+<td><p>00:01.183</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>00:00.589</p></td>
+<td><p>00:00.576</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>00:00.566</p></td>
+<td><p>00:00.556</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>00:00.117</p></td>
+<td><p>00:00.118</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.051</p></td>
+<td><p>00:00.050</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 00bd2e1acb..21a759daa9 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -586,7 +586,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpphos1fye/input0.cc'\nsource_filename = \"/tmp/tmpphos1fye/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/tmpdniot803/input0.cc'\nsource_filename = \"/tmp/tmpdniot803/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 7a350a6887..f22558341b 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1615,7 +1615,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1899,7 +1899,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 087284504d..c76b4387ba 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/ce97138eb/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 83e8bb2dba..82fcf00727 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/ce97138eb/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 7805bb579a..7e471c68eb 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/ce97138eb/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 a8c5d0aa49..5f5b498b13 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/ce97138eb/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 3ae3756216..bc6c93b608 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/ce97138eb/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 e1a98ec7e3..ace5e7a1ff 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/ce97138eb/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 72400cf96d..2091ddd9f5 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/ce97138eb/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 4b81f93132..818cf7ad95 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/ce97138eb/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 955602edaa..0ac2bfabe2 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/ce97138eb/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 f122497c5b..d5e551ec6d 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/ce97138eb/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 3b23c9c6f4..e0d3cad55b 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/ce97138eb/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 81254cf86b..cf96627cd7 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/ce97138eb/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 9fee8b446f..eb021b9ee3 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/ce97138eb/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 05a6c2b080..0bf8472657 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/ce97138eb/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 4f8f55f822..7b13b968c2 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/ce97138eb/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 6de0746771..d65cfbbf62 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/ce97138eb/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 40ab91122a..b8c71d41f1 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/ce97138eb/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 ab256261e5..1ddb96a06c 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/ce97138eb/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 c31ddcbf74..80a596e04d 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/ce97138eb/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 1d27838f98..c96650da5a 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/ce97138eb/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 2cd84c249d..cbeecf8e88 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/ce97138eb/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 593f457743..14818fc85d 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/ce97138eb/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 7f7251c402..a02e15fac2 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/ce97138eb/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 c107726668..7a3637bc86 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/ce97138eb/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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/ce97138eb/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/cdb4eea13/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 2994d28a89..d216d84279 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 0524bc7109..691c0b875e 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:26.086</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:25.201</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:26.079</p></td>
+<td><p>00:25.195</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 40b297aae2..7ef36be10e 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -582,7 +582,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 28.99s!
+resnet18_v1 inference graph built in 27.57s!
</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 b07f80dfe9..d3b2d6c906 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -600,7 +600,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 19.51s!
+yolov3-tiny inference graph built in 18.83s!
</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 80641b427a..7a32948e41 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:40.516</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:37.181</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:51.588</p></td>
+<td><p>00:50.130</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>00:48.928</p></td>
+<td><p>00:47.051</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 2ce99b2905..b1279b11d2 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.170</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.173</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.705</p></td>
+<td><p>00:02.720</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>00:00.465</p></td>
+<td><p>00:00.454</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 32a801e479..50d82d7db0 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.828</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.803</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.437</p></td>
+<td><p>00:00.427</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>00:00.391</p></td>
+<td><p>00:00.376</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index a38c41024f..10347f053f 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -577,7 +577,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 95.950 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 92.876 ms
</pre></div>
</div>
</div>
@@ -651,7 +651,7 @@ 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 13.490 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 16.354 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 2a6bfcc181..41d9ec5787 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -679,16 +679,16 @@ 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: 2.54/2.54 result: MeasureResult(costs=(0.1057228566,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9456357955932617, timestamp=1671132993.9879565) [('tile_y', [-1, 8]), ('tile_x', [-1, 4])],None,23
-No: 2 GFLOPS: 12.22/12.22 result: MeasureResult(costs=(0.021961225600000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6002020835876465, timestamp=1671132994.5979462) [('tile_y', [-1, 256]), ('tile_x', [-1, 256])],None,88
-No: 3 GFLOPS: 8.75/12.22 result: MeasureResult(costs=(0.030663131,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7832496166229248, timestamp=1671132996.109403) [('tile_y', [-1, 512]), ('tile_x', [-1, 64])],None,69
-No: 4 GFLOPS: 11.78/12.22 result: MeasureResult(costs=(0.0227864714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6155939102172852, timestamp=1671132997.502146) [('tile_y', [-1, 32]), ('tile_x', [-1, 256])],None,85
-No: 5 GFLOPS: 12.79/12.79 result: MeasureResult(costs=(0.020993404200000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5696730613708496, timestamp=1671132998.200661) [('tile_y', [-1, 128]), ('tile_x', [-1, 512])],None,97
-No: 6 GFLOPS: 3.13/12.79 result: MeasureResult(costs=(0.0856952252,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6118481159210205, timestamp=1671133000.6068947) [('tile_y', [-1, 2]), ('tile_x', [-1, 8])],None,31
-No: 7 GFLOPS: 0.51/12.79 result: MeasureResult(costs=(0.5270117990000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.669428586959839, timestamp=1671133009.2976425) [('tile_y', [-1, 128]), ('tile_x', [-1, 1])],None,7
-No: 8 GFLOPS: 1.73/12.79 result: MeasureResult(costs=(0.1547205766,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.695625066757202, timestamp=1671133012.0230503) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 9 GFLOPS: 14.60/14.60 result: MeasureResult(costs=(0.018383960600000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.815500020980835, timestamp=1671133012.9544334) [('tile_y', [-1, 64]), ('tile_x', [-1, 64])],None,66
-No: 10 GFLOPS: 13.72/14.60 result: MeasureResult(costs=(0.0195635744,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.560798168182373, timestamp=1671133013.5176134) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
+No: 1 GFLOPS: 12.84/12.84 result: MeasureResult(costs=(0.020908782199999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5888190269470215, timestamp=1671149365.2509778) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
+No: 2 GFLOPS: 10.55/12.84 result: MeasureResult(costs=(0.0254483944,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6654369831085205, timestamp=1671149365.908091) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 3 GFLOPS: 2.11/12.84 result: MeasureResult(costs=(0.12707509,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.277238130569458, timestamp=1671149368.9420745) [('tile_y', [-1, 128]), ('tile_x', [-1, 4])],None,27
+No: 4 GFLOPS: 3.06/12.84 result: MeasureResult(costs=(0.087751631,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.649143934249878, timestamp=1671149371.3521419) [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
+No: 5 GFLOPS: 13.01/13.01 result: MeasureResult(costs=(0.0206402432,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5729818344116211, timestamp=1671149372.04685) [('tile_y', [-1, 128]), ('tile_x', [-1, 512])],None,97
+No: 6 GFLOPS: 1.75/13.01 result: MeasureResult(costs=(0.1538126638,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6816587448120117, timestamp=1671149374.7573478) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 8.82/13.01 result: MeasureResult(costs=(0.030418642799999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.717548131942749, timestamp=1671149376.2418528) [('tile_y', [-1, 2]), ('tile_x', [-1, 32])],None,51
+No: 8 GFLOPS: 0.90/13.01 result: MeasureResult(costs=(0.298880578,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.0075554847717285, timestamp=1671149381.271068) [('tile_y', [-1, 64]), ('tile_x', [-1, 2])],None,16
+No: 9 GFLOPS: 2.30/13.01 result: MeasureResult(costs=(0.1166373722,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.086557388305664, timestamp=1671149383.4721088) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 10 GFLOPS: 1.63/13.01 result: MeasureResult(costs=(0.1645712018,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.840363025665283, timestamp=1671149386.3538458) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
</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 98813779e2..cc11c8f818 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -560,7 +560,7 @@ 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': 515.405821380001, 'median': 515.0413227499996, 'std': 3.0268202307209173}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 508.923503159998, 'median': 509.0428255500001, 'std': 1.7475491963004322}
</pre></div>
</div>
</div>
@@ -712,179 +712,177 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 10.62/ 13.06 GFLOPS | Progress: (4/20) | 8.31 s
-[Task 1/25] Current/Best: 3.45/ 16.74 GFLOPS | Progress: (8/20) | 12.25 s
-[Task 1/25] Current/Best: 17.88/ 17.88 GFLOPS | Progress: (12/20) | 15.87 s
-[Task 1/25] Current/Best: 7.02/ 22.63 GFLOPS | Progress: (16/20) | 21.73 s
-[Task 1/25] Current/Best: 9.29/ 22.63 GFLOPS | Progress: (20/20) | 24.21 s Done.
+[Task 1/25] Current/Best: 13.59/ 17.55 GFLOPS | Progress: (4/20) | 8.95 s
+[Task 1/25] Current/Best: 22.85/ 22.85 GFLOPS | Progress: (8/20) | 11.80 s
+[Task 1/25] Current/Best: 18.39/ 22.85 GFLOPS | Progress: (12/20) | 14.28 s
+[Task 1/25] Current/Best: 19.17/ 22.85 GFLOPS | Progress: (16/20) | 16.27 s
+[Task 1/25] Current/Best: 15.85/ 22.85 GFLOPS | Progress: (20/20) | 20.62 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 4.91/ 17.37 GFLOPS | Progress: (4/20) | 3.53 s
-[Task 2/25] Current/Best: 13.21/ 17.55 GFLOPS | Progress: (8/20) | 5.13 s
-[Task 2/25] Current/Best: 14.06/ 17.55 GFLOPS | Progress: (12/20) | 7.08 s
-[Task 2/25] Current/Best: 11.13/ 17.55 GFLOPS | Progress: (16/20) | 8.66 s
-[Task 2/25] Current/Best: 9.98/ 17.55 GFLOPS | Progress: (20/20) | 10.40 s Done.
+[Task 2/25] Current/Best: 12.47/ 15.74 GFLOPS | Progress: (4/20) | 3.51 s
+[Task 2/25] Current/Best: 14.82/ 17.28 GFLOPS | Progress: (8/20) | 5.08 s
+[Task 2/25] Current/Best: 15.28/ 17.28 GFLOPS | Progress: (12/20) | 6.93 s
+[Task 2/25] Current/Best: 17.87/ 17.87 GFLOPS | Progress: (16/20) | 9.85 s
+[Task 2/25] Current/Best: 8.54/ 17.87 GFLOPS | Progress: (20/20) | 11.47 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 3.06/ 14.99 GFLOPS | Progress: (4/20) | 4.78 s
-[Task 3/25] Current/Best: 11.36/ 20.00 GFLOPS | Progress: (8/20) | 6.94 s
-[Task 3/25] Current/Best: 13.74/ 20.00 GFLOPS | Progress: (12/20) | 9.49 s
-[Task 3/25] Current/Best: 13.58/ 20.00 GFLOPS | Progress: (16/20) | 12.18 s
-[Task 3/25] Current/Best: 9.21/ 20.00 GFLOPS | Progress: (20/20) | 14.79 s Done.
+[Task 3/25] Current/Best: 12.26/ 14.66 GFLOPS | Progress: (4/20) | 3.98 s
+[Task 3/25] Current/Best: 8.98/ 14.66 GFLOPS | Progress: (8/20) | 7.38 s
+[Task 3/25] Current/Best: 6.76/ 14.66 GFLOPS | Progress: (12/20) | 9.84 s
+[Task 3/25] Current/Best: 13.07/ 18.33 GFLOPS | Progress: (16/20) | 12.26 s
+[Task 3/25] Current/Best: 14.68/ 18.33 GFLOPS | Progress: (20/20) | 14.48 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.27/ 12.00 GFLOPS | Progress: (4/20) | 4.94 s
-[Task 4/25] Current/Best: 13.50/ 16.09 GFLOPS | Progress: (8/20) | 6.75 s
-[Task 4/25] Current/Best: 10.12/ 16.39 GFLOPS | Progress: (12/20) | 12.76 s
-[Task 4/25] Current/Best: 12.06/ 16.39 GFLOPS | Progress: (16/20) | 14.64 s
-[Task 4/25] Current/Best: 13.60/ 16.39 GFLOPS | Progress: (20/20) | 17.66 s Done.
+[Task 4/25] Current/Best: 11.19/ 21.36 GFLOPS | Progress: (4/20) | 3.89 s
+[Task 4/25] Current/Best: 13.13/ 21.36 GFLOPS | Progress: (8/20) | 6.06 s
+[Task 4/25] Current/Best: 11.84/ 21.36 GFLOPS | Progress: (12/20) | 11.56 s
+[Task 4/25] Current/Best: 12.79/ 21.36 GFLOPS | Progress: (16/20) | 13.30 s
+[Task 4/25] Current/Best: 10.03/ 21.36 GFLOPS | Progress: (20/20) | 15.96 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 15.77/ 15.77 GFLOPS | Progress: (4/20) | 4.11 s
-[Task 5/25] Current/Best: 9.83/ 15.77 GFLOPS | Progress: (8/20) | 7.66 s
-[Task 5/25] Current/Best: 23.08/ 23.08 GFLOPS | Progress: (12/20) | 9.28 s
-[Task 5/25] Current/Best: 17.41/ 23.08 GFLOPS | Progress: (16/20) | 11.38 s
-[Task 5/25] Current/Best: 7.96/ 23.08 GFLOPS | Progress: (20/20) | 13.49 s Done.
+[Task 5/25] Current/Best: 17.80/ 17.81 GFLOPS | Progress: (4/20) | 4.24 s
+[Task 5/25] Current/Best: 20.72/ 21.56 GFLOPS | Progress: (8/20) | 5.99 s
+[Task 5/25] Current/Best: 12.21/ 21.56 GFLOPS | Progress: (12/20) | 8.40 s
+[Task 5/25] Current/Best: 5.81/ 21.56 GFLOPS | Progress: (16/20) | 10.18 s
+[Task 5/25] Current/Best: 6.87/ 21.56 GFLOPS | Progress: (20/20) | 12.69 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 15.97/ 17.46 GFLOPS | Progress: (4/20) | 5.50 s
-[Task 6/25] Current/Best: 12.17/ 17.56 GFLOPS | Progress: (8/20) | 7.97 s
-[Task 6/25] Current/Best: 5.74/ 17.56 GFLOPS | Progress: (12/20) | 12.49 s
-[Task 6/25] Current/Best: 5.05/ 23.30 GFLOPS | Progress: (16/20) | 14.89 s
-[Task 6/25] Current/Best: 20.82/ 23.30 GFLOPS | Progress: (20/20) | 18.23 s Done.
+[Task 6/25] Current/Best: 11.35/ 21.97 GFLOPS | Progress: (4/20) | 6.84 s
+[Task 6/25] Current/Best: 13.16/ 21.97 GFLOPS | Progress: (8/20) | 9.55 s
+[Task 6/25] Current/Best: 14.42/ 21.97 GFLOPS | Progress: (12/20) | 13.48 s
+[Task 6/25] Current/Best: 8.71/ 21.97 GFLOPS | Progress: (16/20) | 16.39 s
+[Task 6/25] Current/Best: 11.11/ 21.97 GFLOPS | Progress: (20/20) | 18.64 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 12.16/ 12.16 GFLOPS | Progress: (4/20) | 4.83 s
-[Task 7/25] Current/Best: 21.78/ 21.78 GFLOPS | Progress: (8/20) | 7.74 s
-[Task 7/25] Current/Best: 19.24/ 21.78 GFLOPS | Progress: (12/20) | 10.15 s
-[Task 7/25] Current/Best: 7.40/ 21.78 GFLOPS | Progress: (16/20) | 13.00 s
-[Task 7/25] Current/Best: 20.28/ 21.78 GFLOPS | Progress: (20/20) | 15.74 s Done.
+[Task 7/25] Current/Best: 16.22/ 16.22 GFLOPS | Progress: (4/20) | 4.13 s
+[Task 7/25] Current/Best: 5.73/ 16.22 GFLOPS | Progress: (8/20) | 7.00 s
+[Task 7/25] Current/Best: 7.18/ 21.08 GFLOPS | Progress: (12/20) | 9.43 s
+[Task 7/25] Current/Best: 14.97/ 21.08 GFLOPS | Progress: (16/20) | 11.70 s
+[Task 7/25] Current/Best: 9.87/ 21.08 GFLOPS | Progress: (20/20) | 14.13 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 9.22/ 14.39 GFLOPS | Progress: (4/20) | 10.56 s
-[Task 8/25] Current/Best: 5.19/ 14.39 GFLOPS | Progress: (8/20) | 17.31 s
-[Task 8/25] Current/Best: 7.90/ 14.39 GFLOPS | Progress: (12/20) | 20.58 s
-[Task 8/25] Current/Best: 13.95/ 14.39 GFLOPS | Progress: (16/20) | 24.36 s
-[Task 8/25] Current/Best: 2.85/ 14.39 GFLOPS | Progress: (20/20) | 28.40 s Done.
+[Task 8/25] Current/Best: 9.69/ 17.87 GFLOPS | Progress: (4/20) | 6.17 s
+[Task 8/25] Current/Best: 11.92/ 17.87 GFLOPS | Progress: (8/20) | 8.91 s
+[Task 8/25] Current/Best: 2.86/ 17.87 GFLOPS | Progress: (12/20) | 13.48 s
+[Task 8/25] Current/Best: 13.77/ 17.87 GFLOPS | Progress: (16/20) | 18.74 s
+[Task 8/25] Current/Best: 13.65/ 17.87 GFLOPS | Progress: (20/20) | 21.57 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 15.89/ 22.54 GFLOPS | Progress: (4/20) | 7.54 s
-[Task 9/25] Current/Best: 14.83/ 23.32 GFLOPS | Progress: (8/20) | 11.49 s
-[Task 9/25] Current/Best: 7.47/ 23.32 GFLOPS | Progress: (12/20) | 13.30 s
-[Task 9/25] Current/Best: 18.76/ 23.33 GFLOPS | Progress: (16/20) | 24.29 s
-[Task 9/25] Current/Best: 12.15/ 23.33 GFLOPS | Progress: (20/20) | 28.31 s
+[Task 9/25] Current/Best: 13.95/ 20.29 GFLOPS | Progress: (4/20) | 3.38 s
+[Task 9/25] Current/Best: 17.77/ 20.29 GFLOPS | Progress: (8/20) | 5.95 s
+[Task 9/25] Current/Best: 19.16/ 20.29 GFLOPS | Progress: (12/20) | 15.47 s
+[Task 9/25] Current/Best: 12.85/ 20.29 GFLOPS | Progress: (16/20) | 24.23 s
+[Task 9/25] Current/Best: 22.71/ 22.71 GFLOPS | Progress: (20/20) | 29.39 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 14.21/ 16.73 GFLOPS | Progress: (4/20) | 4.00 s
-[Task 10/25] Current/Best: 4.47/ 17.85 GFLOPS | Progress: (8/20) | 5.93 s
-[Task 10/25] Current/Best: 11.31/ 18.32 GFLOPS | Progress: (12/20) | 7.97 s
-[Task 10/25] Current/Best: 14.42/ 22.00 GFLOPS | Progress: (16/20) | 9.61 s
-[Task 10/25] Current/Best: 4.54/ 22.00 GFLOPS | Progress: (20/20) | 12.08 s Done.
+[Task 10/25] Current/Best: 19.02/ 19.02 GFLOPS | Progress: (4/20) | 3.53 s
+[Task 10/25] Current/Best: 17.51/ 21.95 GFLOPS | Progress: (8/20) | 5.12 s
+[Task 10/25] Current/Best: 13.07/ 21.95 GFLOPS | Progress: (12/20) | 7.32 s
+[Task 10/25] Current/Best: 10.99/ 21.95 GFLOPS | Progress: (16/20) | 9.24 s
+[Task 10/25] Current/Best: 7.95/ 21.95 GFLOPS | Progress: (20/20) | 11.15 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 11.06/ 15.82 GFLOPS | Progress: (4/20) | 4.64 s
-[Task 11/25] Current/Best: 17.47/ 18.78 GFLOPS | Progress: (8/20) | 6.87 s
-[Task 11/25] Current/Best: 11.09/ 21.18 GFLOPS | Progress: (12/20) | 9.34 s
-[Task 11/25] Current/Best: 10.94/ 23.86 GFLOPS | Progress: (16/20) | 12.43 s
-[Task 11/25] Current/Best: 17.92/ 23.86 GFLOPS | Progress: (20/20) | 14.92 s Done.
+[Task 11/25] Current/Best: 6.20/ 13.44 GFLOPS | Progress: (4/20) | 4.40 s
+[Task 11/25] Current/Best: 6.29/ 21.15 GFLOPS | Progress: (8/20) | 7.09 s
+[Task 11/25] Current/Best: 14.30/ 21.15 GFLOPS | Progress: (12/20) | 10.06 s
+[Task 11/25] Current/Best: 8.01/ 21.15 GFLOPS | Progress: (16/20) | 12.28 s
+[Task 11/25] Current/Best: 7.00/ 21.15 GFLOPS | Progress: (20/20) | 15.23 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 10.62/ 16.76 GFLOPS | Progress: (4/20) | 5.67 s
-[Task 12/25] Current/Best: 14.52/ 20.72 GFLOPS | Progress: (8/20) | 7.59 s
-[Task 12/25] Current/Best: 12.41/ 20.72 GFLOPS | Progress: (12/20) | 13.37 s
-[Task 12/25] Current/Best: 11.04/ 20.72 GFLOPS | Progress: (16/20) | 19.24 s
-[Task 12/25] Current/Best: 12.78/ 20.72 GFLOPS | Progress: (20/20) | 22.56 s Done.
+[Task 12/25] Current/Best: 13.40/ 13.40 GFLOPS | Progress: (4/20) | 6.86 s
+[Task 12/25] Current/Best: 12.67/ 13.40 GFLOPS | Progress: (8/20) | 10.76 s
+[Task 12/25] Current/Best: 10.32/ 21.06 GFLOPS | Progress: (12/20) | 15.79 s
+[Task 12/25] Current/Best: 8.33/ 21.06 GFLOPS | Progress: (16/20) | 19.78 s
+[Task 12/25] Current/Best: 10.10/ 21.06 GFLOPS | Progress: (20/20) | 23.35 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 12.08/ 20.43 GFLOPS | Progress: (4/20) | 4.99 s
-[Task 13/25] Current/Best: 12.97/ 20.43 GFLOPS | Progress: (8/20) | 8.34 s
-[Task 13/25] Current/Best: 21.18/ 21.18 GFLOPS | Progress: (12/20) | 10.84 s
-[Task 13/25] Current/Best: 5.83/ 21.18 GFLOPS | Progress: (16/20) | 14.57 s
-[Task 13/25] Current/Best: 16.94/ 21.18 GFLOPS | Progress: (20/20) | 17.77 s Done.
+[Task 13/25] Current/Best: 14.26/ 19.38 GFLOPS | Progress: (4/20) | 5.61 s
+[Task 13/25] Current/Best: 9.82/ 19.85 GFLOPS | Progress: (8/20) | 8.17 s
+[Task 13/25] Current/Best: 10.94/ 21.26 GFLOPS | Progress: (12/20) | 11.38 s
+[Task 13/25] Current/Best: 11.51/ 21.26 GFLOPS | Progress: (16/20) | 14.54 s
+[Task 13/25] Current/Best: 17.17/ 21.26 GFLOPS | Progress: (20/20) | 17.75 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 8.97/ 16.75 GFLOPS | Progress: (4/20) | 4.04 s
-[Task 14/25] Current/Best: 15.04/ 18.10 GFLOPS | Progress: (8/20) | 6.48 s
-[Task 14/25] Current/Best: 11.54/ 18.26 GFLOPS | Progress: (12/20) | 8.97 s
-[Task 14/25] Current/Best: 18.86/ 18.86 GFLOPS | Progress: (16/20) | 11.20 s Done.
-
-[Task 14/25] Current/Best: 9.00/ 18.86 GFLOPS | Progress: (20/20) | 14.67 s Done.
+[Task 14/25] Current/Best: 4.50/ 14.10 GFLOPS | Progress: (4/20) | 4.86 s
+[Task 14/25] Current/Best: 5.11/ 14.10 GFLOPS | Progress: (8/20) | 12.41 s
+[Task 14/25] Current/Best: 5.96/ 14.10 GFLOPS | Progress: (12/20) | 17.37 s
+[Task 14/25] Current/Best: 7.48/ 17.86 GFLOPS | Progress: (16/20) | 21.00 s
+[Task 14/25] Current/Best: 15.63/ 17.86 GFLOPS | Progress: (20/20) | 28.02 s Done.
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 14.10/ 21.43 GFLOPS | Progress: (4/20) | 3.60 s
-[Task 15/25] Current/Best: 18.48/ 21.43 GFLOPS | Progress: (8/20) | 5.23 s
-[Task 15/25] Current/Best: 9.20/ 23.31 GFLOPS | Progress: (12/20) | 6.82 s
-[Task 15/25] Current/Best: 13.96/ 23.31 GFLOPS | Progress: (16/20) | 10.99 s
-[Task 15/25] Current/Best: 11.02/ 23.31 GFLOPS | Progress: (20/20) | 14.83 s Done.
-
+[Task 15/25] Current/Best: 16.69/ 16.69 GFLOPS | Progress: (4/20) | 6.65 s
+[Task 15/25] Current/Best: 15.44/ 16.69 GFLOPS | Progress: (8/20) | 8.81 s
+[Task 15/25] Current/Best: 11.59/ 16.81 GFLOPS | Progress: (12/20) | 10.78 s
+[Task 15/25] Current/Best: 14.12/ 16.81 GFLOPS | Progress: (16/20) | 17.19 s
+[Task 15/25] Current/Best: 6.57/ 16.81 GFLOPS | Progress: (20/20) | 23.95 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 16.04/ 16.04 GFLOPS | Progress: (4/20) | 5.69 s
-[Task 16/25] Current/Best: 12.63/ 16.28 GFLOPS | Progress: (8/20) | 8.17 s
-[Task 16/25] Current/Best: 13.81/ 16.28 GFLOPS | Progress: (12/20) | 11.18 s
-[Task 16/25] Current/Best: 13.15/ 16.28 GFLOPS | Progress: (16/20) | 14.58 s
-[Task 16/25] Current/Best: 14.86/ 18.16 GFLOPS | Progress: (20/20) | 16.55 s Done.
+[Task 16/25] Current/Best: 11.88/ 11.88 GFLOPS | Progress: (4/20) | 5.21 s
+[Task 16/25] Current/Best: 10.22/ 15.48 GFLOPS | Progress: (8/20) | 7.05 s
+[Task 16/25] Current/Best: 7.90/ 15.48 GFLOPS | Progress: (12/20) | 9.53 s
+[Task 16/25] Current/Best: 15.31/ 18.18 GFLOPS | Progress: (16/20) | 11.07 s
+[Task 16/25] Current/Best: 9.67/ 18.18 GFLOPS | Progress: (20/20) | 12.57 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 11.89/ 11.89 GFLOPS | Progress: (4/20) | 5.35 s
-[Task 17/25] Current/Best: 9.74/ 11.89 GFLOPS | Progress: (8/20) | 8.59 s
-[Task 17/25] Current/Best: 13.97/ 17.79 GFLOPS | Progress: (12/20) | 10.79 s
-[Task 17/25] Current/Best: 6.11/ 20.37 GFLOPS | Progress: (16/20) | 14.57 s
-[Task 17/25] Current/Best: 21.38/ 21.38 GFLOPS | Progress: (20/20) | 19.96 s Done.
+[Task 17/25] Current/Best: 19.05/ 19.05 GFLOPS | Progress: (4/20) | 4.19 s
+[Task 17/25] Current/Best: 19.84/ 21.73 GFLOPS | Progress: (8/20) | 6.56 s
+[Task 17/25] Current/Best: 15.91/ 21.73 GFLOPS | Progress: (12/20) | 9.54 s
+[Task 17/25] Current/Best: 9.61/ 21.73 GFLOPS | Progress: (16/20) | 12.02 s
+[Task 17/25] Current/Best: 9.69/ 21.73 GFLOPS | Progress: (20/20) | 15.33 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 5.11/ 17.87 GFLOPS | Progress: (4/20) | 8.01 s
-[Task 18/25] Current/Best: 13.15/ 19.42 GFLOPS | Progress: (8/20) | 10.46 s
-[Task 18/25] Current/Best: 5.62/ 20.94 GFLOPS | Progress: (12/20) | 12.64 s
-[Task 18/25] Current/Best: 20.44/ 20.94 GFLOPS | Progress: (16/20) | 16.33 s
-[Task 18/25] Current/Best: 19.43/ 20.94 GFLOPS | Progress: (20/20) | 20.35 s Done.
+[Task 18/25] Current/Best: 2.98/ 15.20 GFLOPS | Progress: (4/20) | 5.79 s
+[Task 18/25] Current/Best: 4.87/ 17.94 GFLOPS | Progress: (8/20) | 8.32 s
+[Task 18/25] Current/Best: 15.81/ 17.94 GFLOPS | Progress: (12/20) | 10.26 s
+[Task 18/25] Current/Best: 4.33/ 19.04 GFLOPS | Progress: (16/20) | 13.78 s
+[Task 18/25] Current/Best: 8.72/ 19.04 GFLOPS | Progress: (20/20) | 22.25 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 18.16/ 18.16 GFLOPS | Progress: (4/20) | 6.76 s
-[Task 19/25] Current/Best: 6.16/ 18.94 GFLOPS | Progress: (8/20) | 11.69 s
-[Task 19/25] Current/Best: 18.06/ 21.54 GFLOPS | Progress: (12/20) | 14.67 s
-[Task 19/25] Current/Best: 21.70/ 21.70 GFLOPS | Progress: (16/20) | 17.09 s
-[Task 19/25] Current/Best: 4.32/ 21.70 GFLOPS | Progress: (20/20) | 21.65 s Done.
+[Task 19/25] Current/Best: 19.94/ 19.94 GFLOPS | Progress: (4/20) | 4.45 s
+[Task 19/25] Current/Best: 13.60/ 19.94 GFLOPS | Progress: (8/20) | 7.54 s
+[Task 19/25] Current/Best: 19.27/ 19.94 GFLOPS | Progress: (12/20) | 10.86 s
+[Task 19/25] Current/Best: 10.54/ 22.39 GFLOPS | Progress: (16/20) | 13.86 s
+[Task 19/25] Current/Best: 10.28/ 22.39 GFLOPS | Progress: (20/20) | 19.68 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 10.17/ 10.70 GFLOPS | Progress: (4/20) | 5.37 s
-[Task 20/25] Current/Best: 10.74/ 18.20 GFLOPS | Progress: (8/20) | 8.91 s
-[Task 20/25] Current/Best: 13.61/ 18.20 GFLOPS | Progress: (12/20) | 10.74 s
-[Task 20/25] Current/Best: 12.99/ 18.20 GFLOPS | Progress: (16/20) | 16.37 s
-[Task 20/25] Current/Best: 8.26/ 18.20 GFLOPS | Progress: (20/20) | 18.83 s
-[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 8.49/ 13.47 GFLOPS | Progress: (4/20) | 4.71 s
-[Task 21/25] Current/Best: 7.59/ 16.62 GFLOPS | Progress: (8/20) | 7.16 s
-[Task 21/25] Current/Best: 14.55/ 16.62 GFLOPS | Progress: (12/20) | 9.51 s Done.
-
-[Task 21/25] Current/Best: 11.87/ 16.62 GFLOPS | Progress: (16/20) | 12.55 s
-[Task 21/25] Current/Best: 11.43/ 19.95 GFLOPS | Progress: (20/20) | 14.72 s Done.
-
+[Task 20/25] Current/Best: 12.23/ 15.43 GFLOPS | Progress: (4/20) | 4.58 s
+[Task 20/25] Current/Best: 13.30/ 15.65 GFLOPS | Progress: (8/20) | 6.50 s
+[Task 20/25] Current/Best: 11.48/ 16.27 GFLOPS | Progress: (12/20) | 14.49 s
+[Task 20/25] Current/Best: 10.50/ 16.27 GFLOPS | Progress: (16/20) | 17.56 s
+[Task 20/25] Current/Best: 20.47/ 20.47 GFLOPS | Progress: (20/20) | 21.94 s
+[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+ Done.
+
+[Task 21/25] Current/Best: 15.53/ 15.53 GFLOPS | Progress: (4/20) | 4.57 s
+[Task 21/25] Current/Best: 11.37/ 17.13 GFLOPS | Progress: (8/20) | 6.95 s
+[Task 21/25] Current/Best: 10.69/ 17.13 GFLOPS | Progress: (12/20) | 9.05 s
+[Task 21/25] Current/Best: 9.75/ 17.13 GFLOPS | Progress: (16/20) | 11.28 s
+[Task 21/25] Current/Best: 1.62/ 18.87 GFLOPS | Progress: (20/20) | 13.94 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 10.63/ 20.95 GFLOPS | Progress: (4/20) | 4.89 s
-[Task 22/25] Current/Best: 13.77/ 20.95 GFLOPS | Progress: (8/20) | 6.47 s
-[Task 22/25] Current/Best: 14.42/ 20.95 GFLOPS | Progress: (12/20) | 8.74 s
-[Task 22/25] Current/Best: 6.67/ 20.95 GFLOPS | Progress: (16/20) | 11.57 s
-[Task 22/25] Current/Best: 20.76/ 20.95 GFLOPS | Progress: (20/20) | 14.61 s Done.
+[Task 22/25] Current/Best: 5.27/ 17.94 GFLOPS | Progress: (4/20) | 4.20 s
+[Task 22/25] Current/Best: 9.16/ 17.94 GFLOPS | Progress: (8/20) | 7.68 s
+[Task 22/25] Current/Best: 6.88/ 18.22 GFLOPS | Progress: (12/20) | 11.53 s
+[Task 22/25] Current/Best: 16.61/ 18.22 GFLOPS | Progress: (16/20) | 13.88 s
+[Task 22/25] Current/Best: 20.22/ 20.22 GFLOPS | Progress: (20/20) | 15.46 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 8.16/ 19.85 GFLOPS | Progress: (4/20) | 4.99 s
-[Task 23/25] Current/Best: 18.95/ 19.85 GFLOPS | Progress: (8/20) | 7.75 s
-[Task 23/25] Current/Best: 18.74/ 20.60 GFLOPS | Progress: (12/20) | 10.56 s
-[Task 23/25] Current/Best: 12.90/ 20.60 GFLOPS | Progress: (16/20) | 14.54 s
-[Task 23/25] Current/Best: 10.99/ 21.53 GFLOPS | Progress: (20/20) | 19.45 s Done.
+[Task 23/25] Current/Best: 4.46/ 11.08 GFLOPS | Progress: (4/20) | 5.80 s
+[Task 23/25] Current/Best: 12.95/ 20.71 GFLOPS | Progress: (8/20) | 9.98 s
+[Task 23/25] Current/Best: 10.74/ 20.71 GFLOPS | Progress: (12/20) | 13.26 s
+[Task 23/25] Current/Best: 18.35/ 20.71 GFLOPS | Progress: (16/20) | 16.15 s
+[Task 23/25] Current/Best: 22.00/ 22.00 GFLOPS | Progress: (20/20) | 18.54 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 1.78/ 9.68 GFLOPS | Progress: (4/20) | 3.59 s
-[Task 24/25] Current/Best: 5.16/ 9.68 GFLOPS | Progress: (8/20) | 9.65 s
-[Task 24/25] Current/Best: 3.72/ 9.68 GFLOPS | Progress: (12/20) | 20.82 s
-[Task 24/25] Current/Best: 9.21/ 9.68 GFLOPS | Progress: (16/20) | 32.93 s
-[Task 24/25] Current/Best: 1.83/ 9.68 GFLOPS | Progress: (20/20) | 43.86 s
-[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
-[Task 25/25] Current/Best: 1.54/ 8.74 GFLOPS | Progress: (4/20) | 4.13 s
-[Task 25/25] Current/Best: 7.81/ 8.74 GFLOPS | Progress: (8/20) | 8.89 s
-[Task 25/25] Current/Best: 3.50/ 8.74 GFLOPS | Progress: (12/20) | 19.83 s
-[Task 25/25] Current/Best: 8.96/ 8.96 GFLOPS | Progress: (16/20) | 31.31 s
-[Task 25/25] Current/Best: 7.20/ 9.47 GFLOPS | Progress: (20/20) | 43.17 s
+[Task 24/25] Current/Best: 3.01/ 7.78 GFLOPS | Progress: (4/20) | 12.71 s
+[Task 24/25] Current/Best: 8.58/ 8.58 GFLOPS | Progress: (8/20) | 23.65 s
+[Task 24/25] Current/Best: 9.74/ 9.74 GFLOPS | Progress: (12/20) | 34.59 s
+[Task 24/25] Current/Best: 1.86/ 9.74 GFLOPS | Progress: (16/20) | 45.51 s
+[Task 24/25] Current/Best: 3.04/ 9.74 GFLOPS | Progress: (20/20) | 52.56 s
+[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 25/25] Current/Best: 2.97/ 7.13 GFLOPS | Progress: (4/20) | 12.77 s
+[Task 25/25] Current/Best: 1.55/ 7.13 GFLOPS | Progress: (8/20) | 14.89 s
+[Task 25/25] Current/Best: 2.51/ 7.13 GFLOPS | Progress: (12/20) | 25.87 s
+[Task 25/25] Current/Best: 8.37/ 8.37 GFLOPS | Progress: (16/20) | 29.11 s
+[Task 25/25] Current/Best: 5.24/ 8.37 GFLOPS | Progress: (20/20) | 40.04 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -945,8 +943,8 @@ model using optimized operators to speed up our computations.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"class='</span><span class="si">%s</span><span class="s2">' with probability=</span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621105
-class='n02123159 tiger cat' with probability=0.356377
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621103
+class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -983,8 +981,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 420.40497239999695, 'median': 420.71705995001594, 'std': 2.3541167080824197}
-unoptimized: {'mean': 515.405821380001, 'median': 515.0413227499996, 'std': 3.0268202307209173}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 424.66174119000243, 'median': 423.78276120000464, 'std': 2.1590939253187806}
+unoptimized: {'mean': 508.923503159998, 'median': 509.0428255500001, 'std': 1.7475491963004322}
</pre></div>
</div>
</div>
@@ -998,7 +996,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 11 minutes 51.785 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 11 minutes 59.039 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 ee6ce02600..a2126a27ba 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -537,7 +537,7 @@ 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>1.257e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.288e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 9d000ce3f6..aba1cc5e89 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -494,7 +494,7 @@ 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, 0x85cd340)), stage(b, placeholder(b, 0x211c7910)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x1a99e260)), stage(b, placeholder(b, 0xa0132b0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index ebe35b194c..c6167db9ad 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>15:06.528</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>15:17.980</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,27 +349,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>11:51.785</p></td>
+<td><p>11:59.039</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>01:13.490</p></td>
+<td><p>01:16.354</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>00:59.134</p></td>
+<td><p>01:01.063</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:33.625</p></td>
+<td><p>00:33.475</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>00:26.028</p></td>
+<td><p>00:25.846</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:01.471</p></td>
+<td><p>00:01.207</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>
@@ -377,26 +377,26 @@
<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>00:00.159</p></td>
+<td><p>00:00.160</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>00:00.007</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>00:00.001</p></td>
+<td><p>00:00.002</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>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="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>
-<tr class="row-odd"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_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>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index b9603f446b..4dd9abe4b4 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -551,8 +551,8 @@ 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
-naive: 0.000007
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000006
+naive: 0.000008
</pre></div>
</div>
</div>
@@ -600,7 +600,7 @@ compile and run this new schedule with the parallel operation applied:</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd_parallel</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"parallel"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.h [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000007
</pre></div>
</div>
</div>
@@ -671,10 +671,10 @@ factor to be the number of threads on your CPU.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.505199998831813e-06 1.0
- naive 6.7013000000000005e-06 0.8928875980710786
-parallel 8.189200000000001e-06 1.091136811980314
- vector 2.4592800000000003e-05 3.276768107955535
+ numpy 6.244270000479446e-06 1.0
+ naive 7.9129e-06 1.267225792509362
+parallel 6.997299999999999e-06 1.1205953617416822
+ vector 2.46278e-05 3.9440639174970067
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -990,7 +990,7 @@ 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: 0.017862
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017793
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1031,7 +1031,7 @@ 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: 3.253786
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.440954
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1095,7 +1095,7 @@ 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: 0.310376
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.289748
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1153,7 +1153,7 @@ 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: 0.349501
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.329821
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1207,7 +1207,7 @@ 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: 0.116475
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.116800
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1282,7 +1282,7 @@ 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: 0.108511
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.109298
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1355,7 +1355,7 @@ 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: 0.110442
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110138
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1421,7 +1421,7 @@ 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: 0.143344
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.145736
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1482,13 +1482,13 @@ 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 3.2537857751 1.0
- blocking 0.3103759217 0.0953891691564916
- vectorization 0.3495007787 0.10741358001334882
-loop permutation 0.11647482649999999 0.03579671021716859
- array packing 0.1085111202 0.033349190051291895
- block caching 0.11044218000000001 0.033942670978886355
- parallelization 0.1433438763 0.04405449104761501
+ none 3.4409538483 1.0
+ blocking 0.2897479329 0.084205701579854
+ vectorization 0.3298209069 0.09585159273872496
+loop permutation 0.1167999963 0.03394407523300696
+ array packing 0.1092977568 0.031763796208425885
+ block caching 0.11013792169999999 0.03200796248819598
+ parallelization 0.14573564519999999 0.04235326936221494
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1520,6 +1520,7 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.063 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>