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 2022/03/24 11:11:51 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@3bd52e63a3150db0e67b855a808685e596657d2b)
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 df65742 deploying docs (apache/tvm@3bd52e63a3150db0e67b855a808685e596657d2b)
df65742 is described below
commit df6574294115e35d49b6f1cbd1a133fa432b2d38
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Thu Mar 24 11:11:46 2022 +0000
deploying docs (apache/tvm@3bd52e63a3150db0e67b855a808685e596657d2b)
---
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_paddle.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../extend_tvm/low_level_custom_pass.rst.txt | 8 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 6 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 16 +-
.../tune_conv2d_layer_cuda.rst.txt | 459 +++-----------------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 91 +---
.../tune_with_autotvm/sg_execution_times.rst.txt | 12 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 34 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../schedule_primitives.rst.txt | 6 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 8 +-
.../work_with_schedules/tuple_inputs.rst.txt | 10 +-
.../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/matrix_multiply_opt.rst.txt | 8 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/vta_get_started.rst.txt | 4 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 6 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 53 +--
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 26 +-
.../tutorial/tensor_expr_get_started.rst.txt | 56 +--
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_caffe2.html | 10 +-
docs/how_to/compile_models/from_coreml.html | 6 +-
docs/how_to/compile_models/from_darknet.html | 4 +-
docs/how_to/compile_models/from_keras.html | 6 +-
docs/how_to/compile_models/from_mxnet.html | 10 +-
docs/how_to/compile_models/from_onnx.html | 12 +-
docs/how_to/compile_models/from_paddle.html | 6 +-
docs/how_to/compile_models/from_pytorch.html | 14 +-
docs/how_to/compile_models/from_tensorflow.html | 8 +-
docs/how_to/compile_models/from_tflite.html | 8 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 10 +-
.../how_to/deploy_models/deploy_model_on_rasp.html | 8 +-
.../deploy_object_detection_pytorch.html | 45 +-
docs/how_to/deploy_models/deploy_prequantized.html | 16 +-
.../deploy_models/deploy_prequantized_tflite.html | 12 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_sparse.html | 12 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 37 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 16 +-
docs/how_to/extend_tvm/low_level_custom_pass.html | 8 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_infra.html | 2 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 8 +-
.../optimize_operators/opt_conv_tensorcore.html | 12 +-
docs/how_to/optimize_operators/opt_gemm.html | 36 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 471 ++++-----------------
.../tune_with_autoscheduler/tune_network_arm.html | 2 +-
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_mali.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 6 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 101 ++---
.../tune_with_autotvm/sg_execution_times.html | 12 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 38 +-
docs/how_to/tune_with_autotvm/tune_relay_arm.html | 2 +-
docs/how_to/tune_with_autotvm/tune_relay_cuda.html | 2 +-
.../tune_with_autotvm/tune_relay_mobile_gpu.html | 2 +-
docs/how_to/tune_with_autotvm/tune_relay_x86.html | 2 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 18 +-
docs/how_to/work_with_microtvm/micro_tflite.html | 2 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
docs/how_to/work_with_relay/build_gcn.html | 2 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
.../how_to/work_with_relay/using_external_lib.html | 4 +-
docs/how_to/work_with_schedules/extern_op.html | 12 +-
docs/how_to/work_with_schedules/reduction.html | 6 +-
docs/how_to/work_with_schedules/scan.html | 6 +-
.../work_with_schedules/schedule_primitives.html | 6 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 24 +-
docs/how_to/work_with_schedules/tuple_inputs.html | 10 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
docs/reference/api/python/ndarray.html | 4 +-
docs/reference/api/python/relay/image.html | 2 +-
docs/reference/api/python/relay/index.html | 2 +-
docs/reference/api/python/relay/nn.html | 2 +-
docs/reference/api/python/topi.html | 2 +-
.../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 +-
.../vta/tutorials/autotvm/tune_relay_vta.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 14 +-
.../vta/tutorials/frontend/deploy_detection.html | 8 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/matrix_multiply.html | 10 +-
.../vta/tutorials/optimize/convolution_opt.html | 8 +-
.../tutorials/optimize/matrix_multiply_opt.html | 20 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/vta_get_started.html | 12 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 16 +-
docs/tutorial/autotvm_matmul_x86.html | 4 +-
docs/tutorial/autotvm_relay_x86.html | 203 ++++-----
docs/tutorial/cross_compilation_and_rpc.html | 14 +-
docs/tutorial/intro_topi.html | 10 +-
docs/tutorial/relay_quick_start.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 90 ++--
docs/tutorial/tensor_ir_blitz_course.html | 8 +-
155 files changed, 1202 insertions(+), 1936 deletions(-)
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 65101a9..dadf8de 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -98,7 +98,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip028d6d4c-438f-443c-9d66-7db994dc95a7 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip2d3e26a2-418e-4a55-a538-ed40c7d51b5b 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_paddle.rst.txt b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
index 96bf32c..86b8d26 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -182,7 +182,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 10.499 seconds)
+ **Total running time of the script:** ( 1 minutes 5.542 seconds)
.. _sphx_glr_download_how_to_compile_models_from_paddle.py:
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 375271a..64fa648 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -79,7 +79,7 @@ Load a pretrained PyTorch model
.. code-block:: none
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
8%|7 | 3.54M/44.7M [00:00<00:01, 36.9MB/s]
16%|#5 | 7.06M/44.7M [00:00<00:01, 35.5MB/s]
49%|####9 | 21.9M/44.7M [00:00<00:00, 89.1MB/s]
89%|########9 | 39.9M/44.7M [00:00<00:00, 128MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 108MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
38%|###8 | 17.1M/44.7M [00:00<00:00, 180MB/s]
92%|#########1| 40.9M/44.7M [00:00<00:00, 220MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 217MB/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 7cc37c1..3b8894c 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -380,7 +380,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 9.234 seconds)
+ **Total running time of the script:** ( 1 minutes 8.938 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 3f79727..e682be9 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
@@ -5,15 +5,15 @@
Computation times
=================
-**05:49.702** total execution time for **how_to_compile_models** files:
+**05:33.129** total execution time for **how_to_compile_models** files:
-- **01:10.499**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
-- **01:09.234**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
-- **00:58.972**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
-- **00:45.009**: :ref:`sphx_glr_how_to_compile_models_from_caffe2.py` (``from_caffe2.py``)
-- **00:25.884**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
-- **00:22.304**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
-- **00:21.029**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
-- **00:19.537**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
-- **00:14.678**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
-- **00:02.555**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
+- **01:08.938**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
+- **01:05.542**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
+- **00:55.581**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
+- **00:41.936**: :ref:`sphx_glr_how_to_compile_models_from_caffe2.py` (``from_caffe2.py``)
+- **00:25.540**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
+- **00:20.321**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
+- **00:20.197**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
+- **00:18.940**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
+- **00:13.481**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
+- **00:02.653**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.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 4c982ee..e0e4d20 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
@@ -393,7 +393,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.6170 16.6062 16.9316 16.3222 0.1629
+ 16.0706 16.1013 16.3075 15.8013 0.1648
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 cb09c46..619868a 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
@@ -108,7 +108,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
7%|7 | 12.5M/170M [00:00<00:01, 131MB/s]
20%|#9 | 33.7M/170M [00:00<00:00, 185MB/s]
33%|###2 | 55.4M/170M [00:00<00:00, 204MB/s]
46%|####5 | 77.8M/170M [00:00<00:00, 216MB/s]
58%|#####8 | 98.5M/170M [00:00<00:00, 215MB/s]
70%|####### | 119M/170M [00:00<00:00, 214MB/s]
82%|########2 | 139M/170M [00:00<00:00, 213MB/s]
94%|#########4| 160M/170M [00:00<00:00, 200MB/s]
100%|##########| 170M/170M [00:00<00:00, 202MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
3%|2 | 5.07M/170M [00:00<00:03, 51.6MB/s]
7%|6 | 11.7M/170M [00:00<00:02, 61.8MB/s]
10%|# | 17.6M/170M [00:00<00:02, 58.2MB/s]
14%|#4 | 24.6M/170M [00:00<00:02, 63.7MB/s]
18%|#8 | 30.7M/170M [00:00<00:02, 53.7MB/s]
21%|##1 | 36.0M/170M [00:00<00:02, 52.3MB/s]
24%|##4 | 41.2M/170M [00:00<00:02, 48.4MB/s]
27%|##7 | 45.9M/170M [00:00<00:02, 46.3MB/s]
31%|###1 | 53.1M/170M [00:01<00:02, 54.2MB/s]
35%|###4 | 59.1M/170M [00:01<00:02, 56.7MB/s]
39%|###8 | 66.0M/170M [00:01<00:01, 59.2MB/s]
42%|####2 | 71.8M/170M [00:01<00:01, 57.0MB/s]
46%|####5 | 77.8M/170M [00:01<00:01, 58.8MB/s]
49%|####9 | 83.5M/170M [00:01<00:01, 53.6MB/s]
53%|#####2 | 89.6M/170M [00:01<00:01, 56.4MB/s]
56%|#####6 | 95.9M/170M [00:01<00:01, 58.3MB/s]
60%|#####9 | 102M/170M [00:01<00:01, 49.5MB/s
]
63%|######3 | 107M/170M [00:02<00:01, 52.7MB/s]
67%|######6 | 113M/170M [00:02<00:01, 55.1MB/s]
70%|######9 | 119M/170M [00:02<00:01, 53.1MB/s]
74%|#######4 | 126M/170M [00:02<00:00, 60.0MB/s]
79%|#######8 | 134M/170M [00:02<00:00, 65.8MB/s]
83%|########3 | 142M/170M [00:02<00:00, 70.2MB/s]
87%|########7 | 149M/170M [00:02<00:00, 69.8MB/s]
91%|#########1| 155M/170M [00:02<00:00, 69.8MB/s]
95%|#########5| 162M/170M [00:02<00:00, 68.6MB/s]
99%|#########9| 169M/170M [00:03<00:00, 59.9MB/s]
100%|##########| 170M/170M [00:03<00:00, 58.1MB/s]
/usr/local/lib/python3.7/dist-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3702: 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).
@@ -255,7 +255,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 12.191 seconds)
+ **Total running time of the script:** ( 3 minutes 5.334 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 449ddf1..7b3c18b 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -187,7 +187,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
42%|####1 | 5.63M/13.6M [00:00<00:00, 59.0MB/s]
85%|########4 | 11.5M/13.6M [00:00<00:00, 60.3MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 61.1MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 157MB/s]
@@ -348,7 +348,7 @@ 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)
- 90.4001 90.3649 93.2152 89.9955 0.3631
+ 90.1497 90.1021 90.7025 89.8559 0.1703
@@ -388,7 +388,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.473 seconds)
+ **Total running time of the script:** ( 1 minutes 3.532 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 316931b..bcf7290 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
@@ -351,7 +351,7 @@ 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)
- 121.1093 120.9318 126.7829 119.3034 1.0425
+ 117.5013 117.4614 119.8671 116.2796 0.6565
@@ -385,7 +385,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 1.357 seconds)
+ **Total running time of the script:** ( 1 minutes 59.415 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 85d0f37..4970cb6 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -221,7 +221,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 15.693 seconds)
+ **Total running time of the script:** ( 1 minutes 12.105 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 bf518d0..b6bd215 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
@@ -137,7 +137,7 @@ 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]
3%|2 | 3429/132723 [00:00<00:03, 34284.23KB/s]
7%|6 | 9221/132723 [00:00<00:02, 48183.38KB/s]
13%|#3 | 17510/132723 [00:00<00:01, 64026.44KB/s]
20%|#9 | 26061/132723 [00:00<00:01, 72504.40KB/s]
26%|##6 | 34648/132723 [00:00<00:01, 77322.07KB/s]
33%|###2 | 43158/132723 [00:00<00:01, 79964.48KB/s]
39%|###8 | 51713/132723 [00:00<00:00, 81787.95KB/s]
45%|####5 | 60298/132723 [00:00<00:00, 83077.59KB/s]
52%|#####1 | 68606/132723 [00:00<00:00, 77049.32KB/s]
58%|#####8 | 77191/132723 [00:01<00:00, 79619.96KB/s]
64%|######4 | 85225/132723 [00:01<00:00, 60282.83KB/s]
71%|####### | 93761/132723 [00:01<00:00, 66334.34KB/s]
77%|#######7 | 102232/132723 [00:01<00:00, 71044.58KB/s]
84%|########3 | 110849/132723 [00:01<00:00, 75098.62KB/s]
90%|######### | 119478/132723 [00:01<00:00, 78195.46KB/s]
97%|#########
6| 128120/132723 [00:01<00:00, 80525.00KB/s]
100%|##########| 132723/132723 [00:01<00:00, 74132.61KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|4 | 5784/132723 [00:00<00:02, 57824.20KB/s]
10%|# | 13456/132723 [00:00<00:01, 68924.54KB/s]
16%|#6 | 21317/132723 [00:00<00:01, 73343.70KB/s]
22%|##2 | 29258/132723 [00:00<00:01, 75736.20KB/s]
28%|##7 | 37134/132723 [00:00<00:01, 76816.16KB/s]
34%|###3 | 44816/132723 [00:00<00:01, 76465.41KB/s]
40%|###9 | 52463/132723 [00:00<00:01, 76412.72KB/s]
45%|####5 | 60111/132723 [00:00<00:00, 76418.72KB/s]
51%|#####1 | 67754/132723 [00:00<00:00, 76380.90KB/s]
57%|#####6 | 75393/132723 [00:01<00:00, 66557.80KB/s]
62%|######2 | 82636/132723 [00:01<00:00, 68184.47KB/s]
68%|######8 | 90369/132723 [00:01<00:00, 70776.77KB/s]
74%|#######4 | 98288/132723 [00:01<00:00, 66511.84KB/s]
80%|#######9 | 106034/132723 [00:01<00:00, 69491.96KB/s]
86%|########5 | 113970/132723 [00:01<00:00, 72253.90KB/s]
92%|#########
1| 121997/132723 [00:01<00:00, 74543.36KB/s]
98%|#########7| 130018/132723 [00:01<00:00, 76184.16KB/s]
100%|##########| 132723/132723 [00:01<00:00, 72971.63KB/s]
@@ -202,7 +202,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 32.591 seconds)
+ **Total running time of the script:** ( 2 minutes 20.596 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 c4ac652..5d893cb 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
@@ -5,13 +5,13 @@
Computation times
=================
-**11:03.474** total execution time for **how_to_deploy_models** files:
+**10:30.202** total execution time for **how_to_deploy_models** files:
-- **03:12.191**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
-- **02:32.591**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
-- **02:01.357**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
-- **01:15.693**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
-- **01:07.473**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
-- **00:30.507**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
-- **00:23.429**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
-- **00:00.233**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
+- **03:05.334**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
+- **02:20.596**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
+- **01:59.415**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
+- **01:12.105**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
+- **01:03.532**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
+- **00:27.048**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
+- **00:21.977**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
+- **00:00.195**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
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 900f85f..4525e51 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
@@ -423,7 +423,7 @@ 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.zip59767a97-0ad8-4929-badf-08459abfeb60 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip5ae111cf-f869-4d47-beea-9eb16a4ed0aa from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
diff --git a/docs/_sources/how_to/extend_tvm/low_level_custom_pass.rst.txt b/docs/_sources/how_to/extend_tvm/low_level_custom_pass.rst.txt
index 784da15..2031c57 100644
--- a/docs/_sources/how_to/extend_tvm/low_level_custom_pass.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/low_level_custom_pass.rst.txt
@@ -73,8 +73,8 @@ our customized lowering pass to manipulate the IR directly instead of using sche
@main = primfn(a_1: handle, b_1: handle, c_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {c: Buffer(c_2: Pointer(float32), float32, [128], []),
- a: Buffer(a_2: Pointer(float32), float32, [128], []),
+ buffers = {a: Buffer(a_2: Pointer(float32), float32, [128], []),
+ c: Buffer(c_2: Pointer(float32), float32, [128], []),
b: Buffer(b_2: Pointer(float32), float32, [128], [])}
buffer_map = {a_1: a, b_1: b, c_1: c} {
for (i: int32, 0, 128) {
@@ -220,8 +220,8 @@ Thus, a good place to put this transformation pass is just after Phase 1.
@main = primfn(a_1: handle, b_1: handle, c_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {c: Buffer(c_2: Pointer(float32), float32, [128], []),
- a: Buffer(a_2: Pointer(float32), float32, [128], []),
+ buffers = {a: Buffer(a_2: Pointer(float32), float32, [128], []),
+ c: Buffer(c_2: Pointer(float32), float32, [128], []),
b: Buffer(b_2: Pointer(float32), float32, [128], [])}
buffer_map = {a_1: a, b_1: b, c_1: c} {
for (i.outer: int32, 0, 16) {
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 c3ff80a..45ad1e1 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
@@ -5,9 +5,9 @@
Computation times
=================
-**00:38.832** total execution time for **how_to_extend_tvm** files:
+**00:37.861** total execution time for **how_to_extend_tvm** files:
-- **00:35.231**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
-- **00:02.301**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
-- **00:01.090**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
-- **00:00.211**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
+- **00:34.387**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
+- **00:02.238**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
+- **00:01.035**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
+- **00:00.201**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
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 a9e6b48..7245a5d 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
@@ -199,10 +199,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6184us [6184us] (44.54%; 44.54%)
- FoldScaleAxis: 7700us [2us] (55.46%; 55.46%)
- FoldConstant: 7698us [1637us] (55.44%; 99.97%)
- InferType: 6061us [6061us] (43.65%; 78.73%)
+ InferType: 5947us [5947us] (45.45%; 45.45%)
+ FoldScaleAxis: 7137us [2us] (54.55%; 54.55%)
+ FoldConstant: 7135us [1499us] (54.53%; 99.97%)
+ InferType: 5636us [5636us] (43.07%; 78.98%)
@@ -239,10 +239,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 5808us [5808us] (44.75%; 44.75%)
- FoldScaleAxis: 7172us [2us] (55.25%; 55.25%)
- FoldConstant: 7169us [1502us] (55.24%; 99.97%)
- InferType: 5667us [5667us] (43.66%; 79.04%)
+ InferType: 5707us [5707us] (44.45%; 44.45%)
+ FoldScaleAxis: 7132us [2us] (55.55%; 55.55%)
+ FoldConstant: 7131us [1488us] (55.54%; 99.98%)
+ InferType: 5643us [5643us] (43.95%; 79.14%)
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 624123e..5f5324c 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
@@ -295,7 +295,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 37.199587 ms
+ Convolution: 39.902019 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 f8c31ce..039d7b3 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
@@ -404,8 +404,8 @@ one time.
@main = primfn(A_1: handle, W_1: handle, Conv_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {Conv: Buffer(Conv_2: Pointer(float32), float32, [25690112], []),
- A: Buffer(A_2: Pointer(float16), float16, [12845056], []),
+ buffers = {A: Buffer(A_2: Pointer(float16), float16, [12845056], []),
+ Conv: Buffer(Conv_2: Pointer(float32), float32, [25690112], []),
W: Buffer(W_2: Pointer(float16), float16, [1179648], [])}
buffer_map = {A_1: A, W_1: W, Conv_1: Conv} {
attr [IterVar(blockIdx.z: int32, (nullptr), "ThreadIndex", "blockIdx.z")] "thread_extent" = 196;
@@ -626,7 +626,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 10.582005 ms
+ conv2d with tensor core: 10.024482 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 02ed7b2..3b7815e 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -118,8 +118,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.019487
- Baseline: 3.498123
+ Numpy running time: 0.017994
+ Baseline: 3.368371
@@ -209,7 +209,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.329103
+ Opt1: 0.299226
@@ -307,7 +307,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.354727
+ Opt2: 0.334333
@@ -398,7 +398,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.148588
+ Opt3: 0.115858
@@ -516,7 +516,7 @@ flattening.
.. code-block:: none
- Opt4: 0.111834
+ Opt4: 0.110707
@@ -633,7 +633,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.112383
+ Opt5: 0.111014
@@ -753,7 +753,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.148875
+ Opt6: 0.144690
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 e2868cc..18118ad 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
@@ -5,8 +5,8 @@
Computation times
=================
-**00:36.534** total execution time for **how_to_optimize_operators** files:
+**00:34.799** total execution time for **how_to_optimize_operators** files:
-- **00:33.806**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
-- **00:01.512**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
-- **00:01.217**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
+- **00:32.190**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
+- **00:01.438**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
+- **00:01.171**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
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 c398ebd..ea30e0a 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
@@ -5,11 +5,11 @@
Computation times
=================
-**04:56.995** total execution time for **how_to_tune_with_autoscheduler** files:
-
-- **02:21.763**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
-- **01:20.596**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
-- **00:40.553**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
-- **00:16.852**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
-- **00:08.749**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
-- **00:08.482**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
+**04:53.221** total execution time for **how_to_tune_with_autoscheduler** files:
+
+- **02:20.441**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
+- **01:19.767**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
+- **00:40.193**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
+- **00:15.743**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
+- **00:08.728**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
+- **00:08.348**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
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 3c7506f..142a2ce 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
@@ -216,217 +216,42 @@ cooperative fetching, unrolling and operator fusion.
Lowered TIR:
@main = primfn(data_1: handle, kernel_1: handle, bias_1: handle, compute_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {compute: Buffer(compute_2: Pointer(float32), float32, [25088], []),
+ buffers = {data: Buffer(data_2: Pointer(float32), float32, [25088], []),
+ compute: Buffer(compute_2: Pointer(float32), float32, [25088], []),
bias: Buffer(bias_2: Pointer(float32), float32, [512], []),
- data: Buffer(data_2: Pointer(float32), float32, [25088], []),
kernel: Buffer(kernel_2: Pointer(float32), float32, [2359296], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 56;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
allocate(conv2d_nchw: Pointer(local float32), float32, [2]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [216]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [768]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
conv2d_nchw_1[1] = 0f32
for (rc.outer.outer: int32, 0, 64) {
- let cse_var_1: int32 = (rc.outer.outer*72)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- if @tir.likely((threadIdx.x_1 < 216), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [216], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[((((((rc.outer.outer*392) + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod(th [...]
+ for (ry.outer.outer: int32, 0, 3) {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ for (ax0.ax1.fused.ax2.fused.ax3.fused.inner.s: int32, 0, 6) {
+ if @tir.likely((threadIdx.x_1 < 12), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[((threadIdx.x_1*6) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s), 9))) && (floormod(((threadIdx.x_1*6) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s), 9) < 8)), data[((((((rc.outer.outer*392) [...]
+ }
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 28), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 84), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 140), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 168), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 196), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 224), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 280), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 308), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 336), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 364), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 392), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 420), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 448), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 476), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 532), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 560), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 7) {
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 16)) < 48), dtype=bool) {
+ kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*112) + threadIdx.x_2)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*14) + floordiv(threadIdx.x_2, 8)), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*112) + threadIdx.x_2), 24), 3)*9)) + (ry.outer.outer*3)) + floormod(((ax0.ax1.fused.ax [...]
+ }
+ }
+ for (rc.outer.inner: int32, 0, 8) {
+ for (rx.outer.inner: int32, 0, 3) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + rx.outer.inner) + 384)]))
+ }
}
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2304)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2305)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2306)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2307)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2308)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2309)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2310)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2311)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2312)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2313)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2314)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2315)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 30)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 30)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2316)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 31)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 31)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2317)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 32)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 32)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2318)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 33)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 33)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2319)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 34)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 34)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2320)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 35)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 35)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2321)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2322)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2323)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2324)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 57)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 57)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2325)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 58)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 58)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2326)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 59)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 59)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2327)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 60)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 60)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2328)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 61)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 61)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2329)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 62)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 62)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2330)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2331)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2332)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2333)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2334)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2335)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2336)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2337)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2338)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 89)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 89)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2339)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2340)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2341)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2342)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 111)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 111)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2343)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 112)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 112)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2344)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 113)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 113)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2345)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 114)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 114)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2346)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 115)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 115)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2347)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 116)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 116)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2348)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2349)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2350)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2351)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 138)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 138)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2352)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 139)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 139)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2353)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2354)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 141)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 141)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2355)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 142)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 142)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2356)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 143)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 143)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2357)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2358)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2359)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2360)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2361)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2362)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2363)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2364)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2365)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 170)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 170)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2366)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2367)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2368)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2369)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2370)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2371)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2372)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2373)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2374)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2375)]))
}
}
- compute[(((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*7)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*64) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*7)) + floormod(blockIdx.x, 7)) + 1568)] = max((conv2d_nchw_1[1] + bias[(((floordiv(blockIdx.x, 7)*64) + floordiv(threadIdx.x, 7)) + 32)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (floordiv(threadIdx.x, 7)*49)) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*32) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*1568) + (floordiv(threadIdx.x, 7)*49)) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x, 7)) + 784)] = max((conv2d_nchw_1[1] + bias[(((floordiv(blockIdx.x, 7)*32) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
}
}
@@ -478,7 +303,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.333 ms
+ Execution time of this operator: 0.395 ms
@@ -524,34 +349,34 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=32)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -571,14 +396,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=6)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 0)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -596,188 +421,36 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[2];
- __shared__ float pad_temp_shared[216];
- __shared__ float kernel_shared[4608];
+ __shared__ float pad_temp_shared[72];
+ __shared__ float kernel_shared[768];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 216) {
- pad_temp_shared[((int)threadIdx.x)] = (((((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1568) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2240) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2464) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2688) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2912) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3136) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3360) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3584) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3808) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4256) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
- if (((int)threadIdx.x) < 128) {
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4480) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ for (int ax0_ax1_fused_ax2_fused_ax3_fused_inner_s = 0; ax0_ax1_fused_ax2_fused_ax3_fused_inner_s < 6; ++ax0_ax1_fused_ax2_fused_ax3_fused_inner_s) {
+ if (((int)threadIdx.x) < 12) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s) % 9))) && ((((((int)threadIdx.x) * 6) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + (ax0_ax1_fused_ax2_fused_ax3_fused_inne [...]
+ }
+ }
+ for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 7; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 4)) < 48) {
+ kernel_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 112) + ((int)threadIdx.x))] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 14) + (((int)threadIdx.x) >> 3)) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 112) + ((int)threadIdx.x)) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 112) + ((int)threadIdx.x)) % 3))];
+ }
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
+ for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + rx_outer_inner) + 384)]));
+ }
+ }
}
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2304)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2305)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2306)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2307)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2308)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2309)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2310)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2311)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2312)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2313)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2314)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2315)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 30)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 30)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2316)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 31)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 31)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2317)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 32)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 32)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2318)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 33)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 33)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2319)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 34)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 34)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2320)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 35)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 35)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2321)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2322)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2323)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2324)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 57)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 57)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2325)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 58)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 58)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2326)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 59)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 59)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2327)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 60)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 60)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2328)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 61)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 61)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2329)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 62)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 62)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2330)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2331)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2332)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2333)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2334)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2335)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2336)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2337)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2338)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 89)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 89)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2339)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2340)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2341)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2342)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 111)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 111)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2343)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 112)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 112)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2344)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 113)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 113)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2345)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 114)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 114)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2346)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 115)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 115)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2347)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 116)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 116)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2348)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2349)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2350)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2351)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 138)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 138)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2352)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 139)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 139)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2353)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 140)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 140)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2354)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 141)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 141)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2355)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 142)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 142)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2356)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 143)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 143)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2357)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2358)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2359)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2360)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2361)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2362)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2363)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2364)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2365)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 170)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 170)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2366)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2367)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2368)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2369)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2370)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2371)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2372)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2373)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2374)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2375)]));
}
- compute[((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 7)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 7)) + (((int)blockIdx.x) % 7)) + 1568)] = max((conv2d_nchw[1] + bias[((((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) / 7)) + 32)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7)) + 784)] = max((conv2d_nchw[1] + bias[((((((int)blockIdx.x) / 7) * 32) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
}
@@ -835,7 +508,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 21.763 seconds)
+ **Total running time of the script:** ( 2 minutes 20.441 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 faf7024..fc8f01d 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
@@ -614,7 +614,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.9322 9.9368 9.9573 9.9026 0.0226
+ 10.0901 10.0769 10.1200 10.0735 0.0212
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 44b58ec..b48a72f 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
@@ -633,7 +633,7 @@ 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)
- 771.1824 773.7858 774.1353 765.6259 3.9316
+ 763.3909 764.9626 768.9731 756.2370 5.3169
@@ -658,7 +658,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 20.596 seconds)
+ **Total running time of the script:** ( 1 minutes 19.767 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 2992f08..b17e0c1 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
@@ -355,81 +355,32 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
Lowered TIR:
@main = primfn(placeholder_5: handle, placeholder_6: handle, placeholder_7: handle, placeholder_8: handle, placeholder_9: handle, compute_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {placeholder_3: Buffer(placeholder_10: Pointer(float32), float32, [32768], []),
+ buffers = {placeholder_4: Buffer(placeholder_10: Pointer(float32), float32, [32768], []),
placeholder_2: Buffer(placeholder_11: Pointer(int32), int32, [4916], []),
- placeholder_1: Buffer(placeholder_12: Pointer(float32), float32, [78656], []),
+ placeholder_3: Buffer(placeholder_12: Pointer(float32), float32, [65536], []),
+ placeholder: Buffer(placeholder_13: Pointer(int32), int32, [33], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], []),
- placeholder_4: Buffer(placeholder_13: Pointer(int32), int32, [33], []),
- placeholder: Buffer(placeholder_14: Pointer(float32), float32, [65536], [])}
- buffer_map = {compute_1: compute, placeholder_9: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_5: placeholder_3, placeholder_8: placeholder_4} {
- 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, 4) {
- for (i.inner.init: int32, 0, 32) {
- let cse_var_1: int32 = ((i.outer.inner*512) + (i.inner.init*16))
- {
- 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
- }
+ placeholder_1: Buffer(placeholder_14: Pointer(float32), float32, [78656], [])}
+ buffer_map = {placeholder_8: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_9: placeholder_3, compute_1: compute, placeholder_5: placeholder_4} {
+ for (i0.outer.i1.outer.fused: int32, 0, 512) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [128]), storage_scope = global {
+ for (i.inner.init: int32, 0, 8) {
+ for (j.init: int32, 0, 16) {
+ compute_4: Buffer(compute_3, float32, [128], [])[((i.inner.init*16) + j.init)] = 0f32
}
- for (elem_idx: int32, 0, (placeholder_4[(i0.outer.i1.outer.fused + 1)] - placeholder_4[i0.outer.i1.outer.fused])) {
- for (i.inner: int32, 0, 32) {
- let cse_var_19: int32 = (elem_idx*16)
- let cse_var_18: int32 = ((i.outer.inner*8192) + (i.inner*256))
- let cse_var_17: int32 = ((i.outer.inner*512) + (i.inner*16))
- let cse_var_16: int32 = (cse_var_17 + 1)
- let cse_var_15: int32 = (cse_var_17 + 11)
- let cse_var_14: int32 = (cse_var_17 + 12)
- let cse_var_13: int32 = (cse_var_17 + 13)
- let cse_var_12: int32 = (cse_var_17 + 14)
- let cse_var_11: int32 = (cse_var_17 + 15)
- let cse_var_10: int32 = (cse_var_17 + 2)
- let cse_var_9: int32 = (cse_var_17 + 3)
- let cse_var_8: int32 = (cse_var_17 + 4)
- let cse_var_7: int32 = (cse_var_17 + 5)
- let cse_var_6: int32 = (cse_var_17 + 6)
- let cse_var_5: int32 = (cse_var_17 + 7)
- let cse_var_4: int32 = (cse_var_17 + 8)
- let cse_var_3: int32 = (cse_var_17 + 9)
- let cse_var_2: int32 = (cse_var_17 + 10)
- {
- compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_1[((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 1)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 2)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 3)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 4)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 5)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 6)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 7)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 8)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 9)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 10)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 11)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 12)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 13)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 14)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 15)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder[(cse_var_1 + 1)] - placeholder[cse_var_1])) {
+ for (i.inner: int32, 0, 8) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ let cse_var_2: int32 = ((i.inner*16) + j)
+ compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_1[(((placeholder[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder_4[(((floordiv(i0.outer.i1.outer.fused, 32)*2048) + (i.inner*256)) + placeholder_2[(placeholder[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
- for (i0.inner: int32, 0, 128) {
- let cse_var_20: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*16))
- compute[ramp(cse_var_20, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder[ramp(cse_var_20, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 8) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute[ramp(cse_var_4, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_3[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -483,7 +434,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.730 ms
+ Execution time of this operator: 1.537 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 7320034..6d583bb 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:44.982** total execution time for **how_to_tune_with_autotvm** files:
+**00:44.251** total execution time for **how_to_tune_with_autotvm** files:
-- **00:44.095**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
-- **00:00.233**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
-- **00:00.220**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
-- **00:00.217**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
-- **00:00.216**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
+- **00:43.353**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
+- **00:00.239**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
+- **00:00.223**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
+- **00:00.220**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:00.216**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
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 ce9c005..ce5570c 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
@@ -859,8 +859,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
- No: 6 GFLOPS: 109.82/109.82 result: MeasureResult(costs=(0.0021079240625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7039425373077393, timestamp=1648107564.920924) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
- No: 7 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 103.69/103.69 result: MeasureResult(costs=(0.0022325490625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5873916149139404, timestamp=1648113806.2056143) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+ No: 7 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -983,7 +983,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
- No: 8 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1106,7 +1106,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
- No: 9 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1229,7 +1229,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
- No: 10 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/103.69 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
@@ -1247,7 +1247,7 @@ for this template
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
- No: 11 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1370,7 +1370,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
- No: 12 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1493,7 +1493,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
- No: 13 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1616,7 +1616,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
- No: 14 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1739,7 +1739,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
- No: 15 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1862,7 +1862,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
- No: 16 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1985,7 +1985,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
- No: 17 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2108,7 +2108,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
- No: 18 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2231,7 +2231,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
- No: 19 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 721, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 685, in run_through_rpc
@@ -2319,7 +2319,7 @@ for this template
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007fe9db845fa2
+ 12: 0x00007fa0cb8d9fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2384,7 +2384,7 @@ for this template
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
- No: 20 GFLOPS: 143.28/143.28 result: MeasureResult(costs=(0.00161575352,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4582786560058594, timestamp=1648107591.5020921) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+ No: 20 GFLOPS: 143.52/143.52 result: MeasureResult(costs=(0.0016130478870967741,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3990607261657715, timestamp=1648113832.552889) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
@@ -2437,7 +2437,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
- Time cost of this operator: 0.002058
+ Time cost of this operator: 0.002014
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 6d7486b..38b1b0b 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
@@ -292,10 +292,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 314.4 98.752 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.073 0.965 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.283 (1, 1, 10, 10, 3) 1 1
- Total_time - 318.374 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.3 98.73 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.076 0.979 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.915 0.291 (1, 1, 10, 10, 3) 1 1
+ Total_time - 314.29 - - - -
@@ -357,10 +357,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 82.95 96.888 (1, 6, 10, 10, 1) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.74 2.032 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.925 1.08 (1, 1, 10, 10, 3) 1 1
- Total_time - 85.614 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.6 96.778 (1, 6, 10, 10, 1) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.77 2.125 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.914 1.097 (1, 1, 10, 10, 3) 1 1
+ Total_time - 83.284 - - - -
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 d216f25..b424733 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
@@ -5,10 +5,10 @@
Computation times
=================
-**00:45.039** total execution time for **how_to_work_with_microtvm** files:
+**00:44.148** total execution time for **how_to_work_with_microtvm** files:
-- **00:40.865**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
-- **00:03.554**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
-- **00:00.208**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
-- **00:00.208**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
-- **00:00.204**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
+- **00:40.053**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
+- **00:03.482**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
+- **00:00.207**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
+- **00:00.204**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
+- **00:00.201**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
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 420e831..8f94933 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
@@ -5,8 +5,8 @@
Computation times
=================
-**00:04.234** total execution time for **how_to_work_with_relay** files:
+**00:04.344** total execution time for **how_to_work_with_relay** files:
-- **00:02.544**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
-- **00:01.470**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
-- **00:00.220**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
+- **00:02.477**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
+- **00:01.661**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
+- **00:00.206**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
diff --git a/docs/_sources/how_to/work_with_schedules/schedule_primitives.rst.txt b/docs/_sources/how_to/work_with_schedules/schedule_primitives.rst.txt
index c920e2c..f3b46f8 100644
--- a/docs/_sources/how_to/work_with_schedules/schedule_primitives.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/schedule_primitives.rst.txt
@@ -87,13 +87,13 @@ schedule computes tensor in a serial manner in a row-major order.
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(float32), float32, [(stride: int32*m: int32)], [], type="auto"),
- A: Buffer(A_2: Pointer(float32), float32, [(stride_1: int32*m)], [], type="auto"),
+ buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*m: int32)], [], type="auto"),
+ C: Buffer(C_2: Pointer(float32), float32, [(stride_1: int32*m)], [], type="auto"),
B: Buffer(B_2: Pointer(float32), float32, [(stride_2: int32*m)], [], type="auto")}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (i: int32, 0, m) {
for (j: int32, 0, n: int32) {
- C[((i*stride) + (j*stride_3: int32))] = (A[((i*stride_1) + (j*stride_4: int32))]*B[((i*stride_2) + (j*stride_5: int32))])
+ C[((i*stride_1) + (j*stride_3: int32))] = (A[((i*stride) + (j*stride_4: int32))]*B[((i*stride_2) + (j*stride_5: int32))])
}
}
}
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 e70691d..6c9ef0a 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
@@ -5,13 +5,13 @@
Computation times
=================
-**00:05.985** total execution time for **how_to_work_with_schedules** files:
+**00:05.933** total execution time for **how_to_work_with_schedules** files:
-- **00:02.277**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
-- **00:01.053**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
-- **00:00.777**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
-- **00:00.765**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
-- **00:00.347**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
-- **00:00.265**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
-- **00:00.252**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
-- **00:00.248**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
+- **00:02.178**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
+- **00:01.196**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
+- **00:00.808**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
+- **00:00.743**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
+- **00:00.321**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
+- **00:00.235**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
+- **00:00.226**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:00.225**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
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 62cf6ff..34f53bd 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -238,8 +238,8 @@ such placeholder can be put to let TVM automatically bind the inferred value for
@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, [65536], []),
- C: Buffer(C_2: Pointer(float32), float32, [524288], []),
+ buffers = {C: Buffer(C_2: Pointer(float32), float32, [524288], []),
+ A: Buffer(A_2: Pointer(float32), float32, [65536], []),
B: Buffer(B_2: Pointer(float32), float32, [32768], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (i: int32, 0, 1024) {
@@ -314,8 +314,8 @@ The importing needs to happen before the tensorized GEMV being executed.
A: Buffer(A_2: Pointer(float32), float32, [65536], []),
B: Buffer(B_2: Pointer(float32), float32, [32768], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpi8h9kn87/input0.cc'
- source_filename = "/tmp/tmpi8h9kn87/input0.cc"
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpz09omo2l/input0.cc'
+ source_filename = "/tmp/tmpz09omo2l/input0.cc"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-pc-linux-gnu"
diff --git a/docs/_sources/how_to/work_with_schedules/tuple_inputs.rst.txt b/docs/_sources/how_to/work_with_schedules/tuple_inputs.rst.txt
index 06e9a08..6d241ba 100644
--- a/docs/_sources/how_to/work_with_schedules/tuple_inputs.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tuple_inputs.rst.txt
@@ -64,15 +64,15 @@ together in the next schedule procedure.
@main = primfn(A0_1: handle, A1_1: handle, B_2: handle, B_3: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {B_1: Buffer(B_4: Pointer(float32), float32, [(stride: int32*m: int32)], [], type="auto"),
- B: Buffer(B_5: Pointer(float32), float32, [(stride_1: int32*m)], [], type="auto"),
- A0: Buffer(A0_2: Pointer(float32), float32, [(stride_2: int32*m)], [], type="auto"),
+ buffers = {B: Buffer(B_4: Pointer(float32), float32, [(stride: int32*m: int32)], [], type="auto"),
+ A0: Buffer(A0_2: Pointer(float32), float32, [(stride_1: int32*m)], [], type="auto"),
+ B_1: Buffer(B_5: Pointer(float32), float32, [(stride_2: int32*m)], [], type="auto"),
A1: Buffer(A1_2: Pointer(float32), float32, [(stride_3: int32*m)], [], type="auto")}
buffer_map = {A0_1: A0, A1_1: A1, B_2: B, B_3: B_1} {
for (i: int32, 0, m) {
for (j: int32, 0, n: int32) {
- B[((i*stride_1) + (j*stride_4: int32))] = (A0[((i*stride_2) + (j*stride_5: int32))] + 2f32)
- B_1[((i*stride) + (j*stride_6: int32))] = (A1[((i*stride_3) + (j*stride_7: int32))]*3f32)
+ B[((i*stride) + (j*stride_4: int32))] = (A0[((i*stride_1) + (j*stride_5: int32))] + 2f32)
+ B_1[((i*stride_2) + (j*stride_6: int32))] = (A1[((i*stride_3) + (j*stride_7: int32))]*3f32)
}
}
}
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 c32fd2a..6d67758 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
@@ -5,7 +5,7 @@
Computation times
=================
-**00:20.364** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:19.697** total execution time for **topic_vta_tutorials_autotvm** files:
-- **00:20.147**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
-- **00:00.217**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
+- **00:19.490**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
+- **00:00.208**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
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 aa86cb7..a14c863 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -265,7 +265,7 @@ 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 21.76s!
+ resnet18_v1 inference graph built in 20.96s!
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 7a13187..771d2b7 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -301,7 +301,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:439: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 15.78s!
+ yolov3-tiny inference graph built in 14.40s!
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 0e9912b..4060dd8 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
@@ -5,7 +5,7 @@
Computation times
=================
-**01:30.035** total execution time for **topic_vta_tutorials_frontend** files:
+**01:27.808** total execution time for **topic_vta_tutorials_frontend** files:
-- **00:47.963**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
-- **00:42.071**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
+- **00:46.678**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
+- **00:41.130**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
diff --git a/docs/_sources/topic/vta/tutorials/optimize/matrix_multiply_opt.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/matrix_multiply_opt.rst.txt
index 21371d3..a77b8dd 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/matrix_multiply_opt.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/matrix_multiply_opt.rst.txt
@@ -189,8 +189,8 @@ Those include:
@main = primfn(data_1: handle, weight_1: handle, res_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {res: Buffer(res_2: Pointer(int8), int8, [1024], []),
- data: Buffer(data_2: Pointer(int8), int8, [1024], []),
+ buffers = {data: Buffer(data_2: Pointer(int8), int8, [1024], []),
+ res: Buffer(res_2: Pointer(int8), int8, [1024], []),
weight: Buffer(weight_2: Pointer(int8), int8, [1048576], [])}
buffer_map = {data_1: data, weight_1: weight, res_1: res} {
allocate(data_buf: Pointer(global int8), int8, [1024]), storage_scope = global;
@@ -502,8 +502,8 @@ and mapping the shift, and clipping computation to the vector ALU.
@main = primfn(data_1: handle, weight_1: handle, res_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {data: Buffer(data_2: Pointer(int8), int8, [1024], []),
- res: Buffer(res_2: Pointer(int8), int8, [1024], []),
+ buffers = {res: Buffer(res_2: Pointer(int8), int8, [1024], []),
+ data: Buffer(data_2: Pointer(int8), int8, [1024], []),
weight: Buffer(weight_2: Pointer(int8), int8, [1048576], [])}
buffer_map = {data_1: data, weight_1: weight, res_1: res} {
@tir.vta.coproc_dep_push(3, 2, dtype=int32)
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 8321f23..259e247 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
@@ -5,7 +5,7 @@
Computation times
=================
-**00:03.592** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.549** total execution time for **topic_vta_tutorials_optimize** files:
-- **00:03.038**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
-- **00:00.554**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
+- **00:02.987**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
+- **00:00.562**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
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 f2f57bc..b7fd981 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:01.091** total execution time for **topic_vta_tutorials** files:
+**00:01.035** total execution time for **topic_vta_tutorials** files:
-- **00:00.564**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
-- **00:00.527**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
+- **00:00.526**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
+- **00:00.509**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
diff --git a/docs/_sources/topic/vta/tutorials/vta_get_started.rst.txt b/docs/_sources/topic/vta/tutorials/vta_get_started.rst.txt
index ed54e6b..da8b0d6 100644
--- a/docs/_sources/topic/vta/tutorials/vta_get_started.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/vta_get_started.rst.txt
@@ -304,8 +304,8 @@ After we construct the schedule, by default the schedule computes
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(int8), int8, [1024], []),
- A: Buffer(A_2: Pointer(int32), int32, [1024], []),
+ buffers = {A: Buffer(A_2: Pointer(int32), int32, [1024], []),
+ C: Buffer(C_2: Pointer(int8), int8, [1024], []),
B: Buffer(B_2: Pointer(int32), int32, [1024], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
allocate(A_buf: Pointer(global int32), int32, [1024]), storage_scope = global;
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 3a1acc0..f34210d 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -216,8 +216,8 @@ operator fusion.
Lowered TIR:
@main = primfn(A_1: handle, B_1: handle, C_1: handle, out_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {out: Buffer(out_2: Pointer(float32), float32, [1048576], []),
- C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
+ buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
+ out: Buffer(out_2: Pointer(float32), float32, [1048576], []),
A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
B: Buffer(B_2: Pointer(float32), float32, [1048576], [])}
buffer_map = {A_1: A, B_1: B, C_1: C, out_1: out} {
@@ -305,7 +305,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 94.036 ms
+ Execution time of this operator: 93.338 ms
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 4bffb0d..52b7dcd 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -268,7 +268,7 @@ standard deviation.
.. code-block:: none
- {'mean': 502.3556121200454, 'median': 502.6672408000195, 'std': 0.6008660766512958}
+ {'mean': 491.822284560003, 'median': 491.5935040000022, 'std': 0.7063807555278793}
@@ -482,30 +482,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 1/25] Current/Best: 12.79/ 16.05 GFLOPS | Progress: (4/10) | 5.35 s
[Task 1/25] Current/Best: 8.31/ 16.08 GFLOPS | Progress: (8/10) | 8.08 s
[Task 1/25] Current/Best: 10.24/ 17.31 GFLOPS | Progress: (10/10) | 10.42 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 6.70/ 23.09 GFLOPS | Progress: (4/10) | 2.01 s
[Task 2/25] Current/Best: 12.77/ 23.09 GFLOPS | Progress: (8/10) | 3.36 s
[Task 2/25] Current/Best: 22.48/ 23.09 GFLOPS | Progress: (10/10) | 4.10 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 21.49/ 21.49 GFLOPS | Progress: (4/10) | 3.02 s
[Task 3/25] Current/Best: 13.81/ 21.49 GFLOPS | Progress: (8/10) | 5.00 s
[Task 3/25] Current/Best: 15.00/ 21.49 GFLOPS | Progress: (10/10) | 5.92 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 11.02/ 13.63 GFLOPS | Progress: (4/10) | 3.89 s
[Task 4/25] Current/Best: 11.75/ 15.79 GFLOPS | Progress: (8/10) | 8.59 s
[Task 4/25] Current/Best: 16.02/ 16.02 GFLOPS | Progress: (10/10) | 9.68 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 6.22/ 19.41 GFLOPS | Progress: (4/10) | 2.53 s
[Task 5/25] Current/Best: 13.74/ 19.41 GFLOPS | Progress: (8/10) | 4.75 s
[Task 5/25] Current/Best: 13.47/ 19.41 GFLOPS | Progress: (10/10) | 5.83 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 19.82/ 19.82 GFLOPS | Progress: (4/10) | 3.12 s
[Task 6/25] Current/Best: 14.73/ 19.82 GFLOPS | Progress: (8/10) | 6.99 s
[Task 6/25] Current/Best: 4.35/ 19.82 GFLOPS | Progress: (10/10) | 9.15 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 16.34/ 18.67 GFLOPS | Progress: (4/10) | 4.08 s
[Task 7/25] Current/Best: 20.82/ 20.82 GFLOPS | Progress: (8/10) | 5.98 s
[Task 7/25] Current/Best: 12.76/ 20.82 GFLOPS | Progress: (10/10) | 7.20 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 2.91/ 21.37 GFLOPS | Progress: (4/10) | 14.12 s
[Task 8/25] Current/Best: 22.41/ 22.41 GFLOPS | Progress: (8/10) | 17.09 s
[Task 8/25] Current/Best: 12.68/ 22.41 GFLOPS | Progress: (10/10) | 18.14 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 9/25] Current/Best: 12.65/ 15.82 GFLOPS | Progress: (4/10) | 3.82 s
[Task 9/25] Current/Best: 13.79/ 19.06 GFLOPS | Progress: (8/10) | 5.07 s
[Task 9/25] Current/Best: 9.85/ 20.36 GFLOPS | Progress: (10/10) | 6.34 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 10.41/ 14.01 GFLOPS | Progress: (4/10) | 3.61 s
[Task 10/25] Current/Best: 19.37/ 19.37 GFLOPS | Progress: (8/10) | 5.43 s
[Task 10/25] Current/Best: 11.35/ 19.37 GFLOPS | Progress: (10/10) | 6.28 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 16.53/ 20.37 GFLOPS | Progress: (4/10) | 2.58 s
[Task 11/25] Current/Best: 21.74/ 21.74 GFLOPS | Progress: (8/10) | 5.45 s
[Task 11/25] Current/Best: 14.46/ 23.99 GFLOPS | Progress: (10/10) | 6.49 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 15.48/ 15.48 GFLOPS | Progress: (4/10) | 6.32 s
[Task 12/25] Current/Best: 9.87/ 20.95 GFLOPS | Progress: (8/10) | 10.22 s
[Task 12/25] Current/Best: 4.43/ 20.95 GFLOPS | Progress: (10/10) | 11.49 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 1.57/ 23.21 GFLOPS | Progress: (4/10) | 5.76 s
[Task 13/25] Current/Best: 13.86/ 23.21 GFLOPS | Progress: (8/10) | 8.19 s
[Task 13/25] Current/Best: 21.06/ 23.21 GFLOPS | Progress: (10/10) | 10.32 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 7.99/ 21.25 GFLOPS | Progress: (4/10) | 4.01 s
[Task 14/25] Current/Best: 12.25/ 21.25 GFLOPS | Progress: (8/10) | 7.90 s
[Task 14/25] Current/Best: 17.83/ 21.25 GFLOPS | Progress: (10/10) | 9.31 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 1/25] Current/Best: 15.48/ 15.48 GFLOPS | Progress: (4/10) | 5.02 s
[Task 1/25] Current/Best: 6.76/ 17.78 GFLOPS | Progress: (8/10) | 7.98 s
[Task 1/25] Current/Best: 14.13/ 17.78 GFLOPS | Progress: (10/10) | 9.01 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 13.44/ 20.29 GFLOPS | Progress: (4/10) | 2.75 s
[Task 2/25] Current/Best: 6.70/ 20.29 GFLOPS | Progress: (8/10) | 4.03 s
[Task 2/25] Current/Best: 13.88/ 20.29 GFLOPS | Progress: (10/10) | 5.27 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 7.21/ 16.04 GFLOPS | Progress: (4/10) | 3.04 s
[Task 3/25] Current/Best: 17.60/ 17.60 GFLOPS | Progress: (8/10) | 4.82 s
[Task 3/25] Current/Best: 1.63/ 17.60 GFLOPS | Progress: (10/10) | 7.17 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 17.57/ 17.65 GFLOPS | Progress: (4/10) | 2.86 s
[Task 4/25] Current/Best: 13.76/ 17.65 GFLOPS | Progress: (8/10) | 9.07 s
[Task 4/25] Current/Best: 14.38/ 17.65 GFLOPS | Progress: (10/10) | 10.44 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 8.67/ 14.09 GFLOPS | Progress: (4/10) | 3.18 s
[Task 5/25] Current/Best: 17.41/ 19.54 GFLOPS | Progress: (8/10) | 4.70 s
[Task 5/25] Current/Best: 18.49/ 19.54 GFLOPS | Progress: (10/10) | 5.35 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 5.35/ 20.86 GFLOPS | Progress: (4/10) | 4.71 s
[Task 6/25] Current/Best: 16.44/ 20.86 GFLOPS | Progress: (8/10) | 6.75 s
[Task 6/25] Current/Best: 15.73/ 20.86 GFLOPS | Progress: (10/10) | 7.81 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 18.17/ 21.44 GFLOPS | Progress: (4/10) | 3.01 s
[Task 7/25] Current/Best: 15.19/ 21.44 GFLOPS | Progress: (8/10) | 5.01 s
[Task 7/25] Current/Best: 12.01/ 21.44 GFLOPS | Progress: (10/10) | 5.82 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 8.37/ 13.28 GFLOPS | Progress: (4/10) | 14.76 s
[Task 8/25] Current/Best: 15.65/ 15.65 GFLOPS | Progress: (8/10) | 17.13 s
[Task 8/25] Current/Best: 3.86/ 15.65 GFLOPS | Progress: (10/10) | 19.49 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 9/25] Current/Best: 9.87/ 20.51 GFLOPS | Progress: (4/10) | 3.95 s
[Task 9/25] Current/Best: 11.48/ 20.51 GFLOPS | Progress: (8/10) | 7.21 s
[Task 9/25] Current/Best: 14.55/ 20.51 GFLOPS | Progress: (10/10) | 8.04 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 13.70/ 22.11 GFLOPS | Progress: (4/10) | 3.36 s
[Task 10/25] Current/Best: 14.13/ 22.11 GFLOPS | Progress: (8/10) | 5.36 s
[Task 10/25] Current/Best: 15.26/ 22.11 GFLOPS | Progress: (10/10) | 6.22 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 17.32/ 18.28 GFLOPS | Progress: (4/10) | 5.25 s
[Task 11/25] Current/Best: 24.35/ 24.35 GFLOPS | Progress: (8/10) | 8.50 s
[Task 11/25] Current/Best: 5.95/ 24.35 GFLOPS | Progress: (10/10) | 9.64 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 18.09/ 22.89 GFLOPS | Progress: (4/10) | 3.59 s
[Task 12/25] Current/Best: 17.99/ 22.89 GFLOPS | Progress: (8/10) | 8.59 s
[Task 12/25] Current/Best: 12.67/ 22.89 GFLOPS | Progress: (10/10) | 9.53 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 14.32/ 22.69 GFLOPS | Progress: (4/10) | 2.87 s
[Task 13/25] Current/Best: 1.57/ 22.69 GFLOPS | Progress: (8/10) | 7.66 s
[Task 13/25] Current/Best: 6.01/ 22.69 GFLOPS | Progress: (10/10) | 8.70 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 20.30/ 20.30 GFLOPS | Progress: (4/10) | 7.99 s
[Task 14/25] Current/Best: 15.41/ 20.30 GFLOPS | Progress: (8/10) | 12.85 s
[Task 14/25] Current/Best: 15.51/ 20.30 GFLOPS | Progress: (10/10) | 13.62 s Done.
+
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 15/25] Current/Best: 11.10/ 11.10 GFLOPS | Progress: (4/10) | 2.33 s
[Task 15/25] Current/Best: 11.65/ 16.34 GFLOPS | Progress: (8/10) | 6.19 s
[Task 15/25] Current/Best: 20.83/ 23.68 GFLOPS | Progress: (10/10) | 6.73 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 16/25] Current/Best: 11.18/ 18.58 GFLOPS | Progress: (4/10) | 3.07 s
[Task 16/25] Current/Best: 3.06/ 19.72 GFLOPS | Progress: (8/10) | 5.92 s
[Task 16/25] Current/Best: 18.46/ 19.72 GFLOPS | Progress: (10/10) | 6.52 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 18.59/ 23.37 GFLOPS | Progress: (4/10) | 2.61 s
[Task 17/25] Current/Best: 9.27/ 23.37 GFLOPS | Progress: (8/10) | 5.49 s
[Task 17/25] Current/Best: 20.74/ 23.37 GFLOPS | Progress: (10/10) | 6.75 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 17.41/ 18.28 GFLOPS | Progress: (4/10) | 2.46 s
[Task 18/25] Current/Best: 13.93/ 18.28 GFLOPS | Progress: (8/10) | 4.65 s
[Task 18/25] Current/Best: 12.43/ 18.28 GFLOPS | Progress: (10/10) | 5.97 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 8.55/ 11.21 GFLOPS | Progress: (4/10) | 4.38 s
[Task 19/25] Current/Best: 10.94/ 19.29 GFLOPS | Progress: (8/10) | 6.92 s
[Task 19/25] Current/Best: 4.39/ 19.29 GFLOPS | Progress: (10/10) | 13.55 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 9.96/ 16.18 GFLOPS | Progress: (4/10) | 2.83 s Done.
+
[Task 20/25] Current/Best: 18.65/ 21.56 GFLOPS | Progress: (8/10) | 4.77 s
[Task 20/25] Current/Best: 10.57/ 21.56 GFLOPS | Progress: (10/10) | 5.86 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 21/25] Current/Best: 4.34/ 11.24 GFLOPS | Progress: (4/10) | 3.72 s
[Task 21/25] Current/Best: 5.42/ 17.81 GFLOPS | Progress: (8/10) | 6.06 s
[Task 21/25] Current/Best: 5.38/ 17.81 GFLOPS | Progress: (10/10) | 6.75 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 22/25] Current/Best: 16.84/ 16.84 GFLOPS | Progress: (4/10) | 2.83 s
[Task 22/25] Current/Best: 19.54/ 21.25 GFLOPS | Progress: (8/10) | 4.08 s
[Task 22/25] Current/Best: 18.39/ 21.25 GFLOPS | Progress: (10/10) | 4.96 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 4.76/ 23.31 GFLOPS | Progress: (4/10) | 9.53 s
[Task 23/25] Current/Best: 19.93/ 23.31 GFLOPS | Progress: (8/10) | 12.85 s
[Task 23/25] Current/Best: 10.75/ 23.31 GFLOPS | Progress: (10/10) | 17.01 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 0.54/ 5.08 GFLOPS | Progress: (4/10) | 11.70 s
[Task 24/25] Current/Best: 7.93/ 7.93 GFLOPS | Progress: (8/10) | 45.32 s
[Task 24/25] Current/Best: 4.07/ 7.93 GFLOPS | Progress: (10/10) | 45.93 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
Done.
-
[Task 15/25] Current/Best: 14.61/ 14.61 GFLOPS | Progress: (4/10) | 3.75 s
[Task 15/25] Current/Best: 10.00/ 14.61 GFLOPS | Progress: (8/10) | 8.20 s
[Task 15/25] Current/Best: 6.05/ 14.61 GFLOPS | Progress: (10/10) | 9.00 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 16/25] Current/Best: 6.64/ 19.18 GFLOPS | Progress: (4/10) | 2.83 s
[Task 16/25] Current/Best: 16.93/ 19.18 GFLOPS | Progress: (8/10) | 3.98 s
[Task 16/25] Current/Best: 10.84/ 19.18 GFLOPS | Progress: (10/10) | 5.28 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 10.21/ 16.43 GFLOPS | Progress: (4/10) | 4.16 s
[Task 17/25] Current/Best: 3.11/ 21.92 GFLOPS | Progress: (8/10) | 7.59 s
[Task 17/25] Current/Best: 3.11/ 21.92 GFLOPS | Progress: (10/10) | 9.02 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 11.24/ 17.61 GFLOPS | Progress: (4/10) | 3.75 s
[Task 18/25] Current/Best: 15.09/ 19.45 GFLOPS | Progress: (8/10) | 5.87 s
[Task 18/25] Current/Best: 16.87/ 19.45 GFLOPS | Progress: (10/10) | 6.65 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 15.57/ 19.24 GFLOPS | Progress: (4/10) | 3.62 s
[Task 19/25] Current/Best: 13.15/ 19.24 GFLOPS | Progress: (8/10) | 7.61 s
[Task 19/25] Current/Best: 6.05/ 19.24 GFLOPS | Progress: (10/10) | 11.45 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 13.47/ 16.10 GFLOPS | Progress: (4/10) | 2.59 s
[Task 20/25] Current/Best: 14.19/ 16.10 GFLOPS | Progress: (8/10) | 5.54 s
[Task 20/25] Current/Best: 7.47/ 16.10 GFLOPS | Progress: (10/10) | 8.31 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 21/25] Current/Best: 16.37/ 16.57 GFLOPS | Progress: (4/10) | 2.89 s
[Task 21/25] Current/Best: 5.36/ 16.57 GFLOPS | Progress: (8/10) | 4.86 s
[Task 21/25] Current/Best: 3.14/ 16.57 GFLOPS | Progress: (10/10) | 5.97 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
Done.
-
[Task 22/25] Current/Best: 19.20/ 19.20 GFLOPS | Progress: (4/10) | 2.76 s
[Task 22/25] Current/Best: 4.46/ 19.20 GFLOPS | Progress: (8/10) | 5.65 s
[Task 22/25] Current/Best: 10.73/ 19.20 GFLOPS | Progress: (10/10) | 6.37 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 10.49/ 22.47 GFLOPS | Progress: (4/10) | 3.92 s
[Task 23/25] Current/Best: 11.88/ 22.47 GFLOPS | Progress: (8/10) | 7.58 s
[Task 23/25] Current/Best: 18.73/ 22.47 GFLOPS | Progress: (10/10) | 8.42 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 7.95/ 7.95 GFLOPS | Progress: (4/10) | 1627.52 s
[Task 24/25] Current/Best: 8.42/ 8.42 GFLOPS | Progress: (8/10) | 1646.31 s
[Task 24/25] Current/Best: 9.88/ 9.88 GFLOPS | Progress: (10/10) | 1647.34 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 25/25] Current/Best: 5.71/ 8.55 GFLOPS | Progress: (4/10) | 23.22 s Done.
-
[Task 25/25] Current/Best: 5.89/ 9.31 GFLOPS | Progress: (8/10) | 25.72 s
[Task 25/25] Current/Best: 2.87/ 9.31 GFLOPS | Progress: (10/10) | 38.42 s
+
[Task 25/25] Current/Best: 8.98/ 9.42 GFLOPS | Progress: (4/10) | 18.83 s
[Task 25/25] Current/Best: 8.15/ 9.42 GFLOPS | Progress: (8/10) | 31.85 s
[Task 25/25] Current/Best: 1.55/ 9.42 GFLOPS | Progress: (10/10) | 44.43 s
The output from this tuning process will look something like this:
@@ -647,8 +648,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 461.7602170999635, 'median': 461.64030329991874, 'std': 0.7627124855057924}
- unoptimized: {'mean': 502.3556121200454, 'median': 502.6672408000195, 'std': 0.6008660766512958}
+ optimized: {'mean': 426.9575861800149, 'median': 426.7440630999772, 'std': 0.8836425172203678}
+ unoptimized: {'mean': 491.822284560003, 'median': 491.5935040000022, 'std': 0.7063807555278793}
@@ -668,7 +669,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 34 minutes 35.781 seconds)
+ **Total running time of the script:** ( 7 minutes 57.497 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 a01177d..4cd3194 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -235,7 +235,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.233e-07 secs/op
+ 1.276e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index d73df1c..8f886d2 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -230,7 +230,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x200c3210)), stage(b, placeholder(b, 0xb96e170)), 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, 0xf52fec0)), stage(b, placeholder(b, 0x22dce1b0)), 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 7cf3bba..d257f96 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,17 +5,17 @@
Computation times
=================
-**37:18.408** total execution time for **tutorial** files:
+**10:28.906** total execution time for **tutorial** files:
-- **34:35.781**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
-- **01:04.130**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
-- **00:46.525**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
-- **00:26.723**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
-- **00:23.500**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
-- **00:00.715**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
-- **00:00.579**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
-- **00:00.220**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
-- **00:00.061**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
-- **00:00.059**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
-- **00:00.058**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
-- **00:00.057**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
+- **07:57.497**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
+- **01:00.132**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
+- **00:48.456**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
+- **00:25.617**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
+- **00:15.608**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
+- **00:00.696**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
+- **00:00.550**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
+- **00:00.201**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
+- **00:00.044**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
+- **00:00.039**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **00:00.033**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
+- **00:00.031**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 09caecc..c76e382 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -244,7 +244,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
Numpy running time: 0.000008
- naive: 0.000006
+ naive: 0.000007
@@ -390,15 +390,15 @@ factor to be the number of threads on your CPU.
vector: 0.000025
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type="auto"),
- A: Buffer(A_2: Pointer(float32), float32, [(stride_1: int32*n)], [], type="auto"),
+ buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type="auto"),
+ C: Buffer(C_2: Pointer(float32), float32, [(stride_1: int32*n)], [], type="auto"),
B: Buffer(B_2: Pointer(float32), float32, [(stride_2: int32*n)], [], type="auto")}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (i.outer: int32, 0, floordiv((n + 3), 4)) "parallel" {
for (i.inner.s: int32, 0, 4) {
if @tir.likely((((i.outer*4) + i.inner.s) < n), dtype=bool) {
let cse_var_1: int32 = ((i.outer*4) + i.inner.s)
- C[(cse_var_1*stride)] = (A[(cse_var_1*stride_1)] + B[(cse_var_1*stride_2)])
+ C[(cse_var_1*stride_1)] = (A[(cse_var_1*stride)] + B[(cse_var_1*stride_2)])
}
}
}
@@ -436,10 +436,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.224830016843043e-06 1.0
- naive 5.8652e-06 0.7131089624939452
- parallel 6.9543e-06 0.8455250729509041
- vector 2.45668e-05 2.986906714143806
+ numpy 8.49431000460754e-06 1.0
+ naive 6.732e-06 0.7925305288302856
+ parallel 7.070899999999999e-06 0.8324278247632302
+ vector 2.47126e-05 2.9093122321407185
@@ -828,7 +828,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019760
+ Numpy running time: 0.018267
@@ -884,7 +884,7 @@ optimizations.
.. code-block:: none
- none: 3.552890
+ none: 3.376311
@@ -911,8 +911,8 @@ nested loops over the indices of the A and B matrices.
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
- A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
B: Buffer(B_2: Pointer(float32), float32, [1048576], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (x: int32, 0, 1024) {
@@ -982,7 +982,7 @@ schedule.
.. code-block:: none
- blocking: 0.335310
+ blocking: 0.289320
@@ -1073,7 +1073,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.355306
+ vectorization: 0.326682
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
@@ -1144,11 +1144,11 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.145115
+ loop permutation: 0.116640
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
- C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
+ buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
+ A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
B: Buffer(B_2: Pointer(float32), float32, [1048576], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (x.outer: int32, 0, 32) {
@@ -1240,7 +1240,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.114273
+ array packing: 0.110079
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
@@ -1330,7 +1330,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.115233
+ block caching: 0.110906
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
@@ -1413,7 +1413,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.149285
+ parallelization: 0.144534
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
@@ -1491,13 +1491,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.5528903428999996 1.0
- blocking 0.3353095335 0.09437655011505591
- vectorization 0.35530559790000005 0.10000466200991348
- loop permutation 0.1451150882 0.04084423502965524
- array packing 0.1142733002 0.032163475134649365
- block caching 0.11523314609999999 0.03243363430292151
- parallelization 0.1492849731 0.04201789492274285
+ none 3.3763106256999995 1.0
+ blocking 0.28932003700000003 0.08569117864859258
+ vectorization 0.3266819908 0.09675708991742135
+ loop permutation 0.1166400076 0.03454658665353618
+ array packing 0.11007855660000002 0.032603207703135365
+ block caching 0.1109057242 0.03284819926099254
+ parallelization 0.14453447940000003 0.04280840699307226
@@ -1534,7 +1534,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.130 seconds)
+ **Total running time of the script:** ( 1 minutes 0.132 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 4e3837d..80dc0c9 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-f36829563870b00a97a7da81c2f403623ad2fd59
+3bd52e63a3150db0e67b855a808685e596657d2b
diff --git a/docs/how_to/compile_models/from_caffe2.html b/docs/how_to/compile_models/from_caffe2.html
index 7360b42..d6636c1 100644
--- a/docs/how_to/compile_models/from_caffe2.html
+++ b/docs/how_to/compile_models/from_caffe2.html
@@ -398,10 +398,10 @@ Writing to /workspace/.caffe2/models/resnet50/value_info.json
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.show.html#matplotlib.pyplot.show" title="View documentation for matplotlib.pyplot.show"><span class="n">plt</span><span class="o">.</span><span class="n">show</span></a><span class="p">()</span>
<span class="c1"># input preprocess</span>
<span class="k">def</span> <span class="nf">transform_image</span><span class="p">(</span><span class="n">image</span><span class="p">):</span>
- <span class="n">image</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">image</span><span class="p">)</span> <span class="o">-</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for nu [...]
- <span class="n">image</span> <span class="o">/=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">([</span><span class="mf">58.395</span><span class="p">,</span> <span class="mf">57.12</span><span class="p">,</span> <span class="mf">57.375</span><span class="p">])</span>
+ <span class="n">image</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">image</span><span class="p">)</span> <span class="o">-</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">123.0</span><span class="p">,</span> <span class="mf">117.0</span><span class="p">,</span> <span class="mf">104.0</span><span class="p"> [...]
+ <span class="n">image</span> <span class="o">/=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">58.395</span><span class="p">,</span> <span class="mf">57.12</span><span class="p">,</span> <span class="mf">57.375</span><span class="p">])</span>
<span class="n">image</span> <span class="o">=</span> <span class="n">image</span><span class="o">.</span><span class="n">transpose</span><span class="p">((</span><span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">))</span>
- <span class="n">image</span> <span class="o">=</span> <span class="n">image</span><span class="p">[</span><a href="https://numpy.org/doc/stable/reference/constants.html#numpy.newaxis" title="View documentation for numpy.newaxis"><span class="n">np</span><span class="o">.</span><span class="n">newaxis</span></a><span class="p">,</span> <span class="p">:]</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">"float32"</span><span [...]
+ <span class="n">image</span> <span class="o">=</span> <span class="n">image</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">newaxis</span><span class="p">,</span> <span class="p">:]</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">"float32"</span><span class="p">)</span>
<span class="k">return</span> <span class="n">image</span>
@@ -449,7 +449,7 @@ Writing to /workspace/.caffe2/models/resnet50/value_info.json
<span class="n">m</span><span class="o">.</span><span class="n">run</span><span class="p">()</span>
<span class="c1"># get outputs</span>
<span class="n">tvm_out</span> <span class="o">=</span> <span class="n">m</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
-<span class="n">top1_tvm</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.argmax.html#numpy.argmax" title="View documentation for numpy.argmax"><span class="n">np</span><span class="o">.</span><span class="n">argmax</span></a><span class="p">(</span><span class="n">tvm_out</span><span class="o">.</span><span class="n">numpy</span><span class="p">()[</span><span class="mi">0</span><span class="p">])</span>
+<span class="n">top1_tvm</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">tvm_out</span><span class="o">.</span><span class="n">numpy</span><span class="p">()[</span><span class="mi">0</span><span class="p">])</span>
</pre></div>
</div>
</div>
@@ -474,7 +474,7 @@ Writing to /workspace/.caffe2/models/resnet50/value_info.json
<span class="c1"># confirm correctness with caffe2 output</span>
<span class="n">p</span> <span class="o">=</span> <span class="n">workspace</span><span class="o">.</span><span class="n">Predictor</span><span class="p">(</span><span class="n">resnet50</span><span class="o">.</span><span class="n">init_net</span><span class="p">,</span> <span class="n">resnet50</span><span class="o">.</span><span class="n">predict_net</span><span class="p">)</span>
<span class="n">caffe2_out</span> <span class="o">=</span> <span class="n">p</span><span class="o">.</span><span class="n">run</span><span class="p">({</span><span class="n">input_name</span><span class="p">:</span> <span class="n">data</span><span class="p">})</span>
-<span class="n">top1_caffe2</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.argmax.html#numpy.argmax" title="View documentation for numpy.argmax"><span class="n">np</span><span class="o">.</span><span class="n">argmax</span></a><span class="p">(</span><span class="n">caffe2_out</span><span class="p">)</span>
+<span class="n">top1_caffe2</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">caffe2_out</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Caffe2 top-1 id: </span><span class="si">{}</span><span class="s2">, class name: </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">top1_caffe2</span><span class="p">,</span> <span class="n">synset</span><span class="p">[</span><span class="n">top1_caffe2</span><span class="p">]))</span>
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_coreml.html b/docs/how_to/compile_models/from_coreml.html
index 51682a1..ff3924e 100644
--- a/docs/how_to/compile_models/from_coreml.html
+++ b/docs/how_to/compile_models/from_coreml.html
@@ -380,8 +380,8 @@ provided by apple in this example</p>
<span class="n">img_path</span> <span class="o">=</span> <span class="n">download_testdata</span><span class="p">(</span><span class="n">img_url</span><span class="p">,</span> <span class="s2">"cat.png"</span><span class="p">,</span> <span class="n">module</span><span class="o">=</span><span class="s2">"data"</span><span class="p">)</span>
<span class="n">img</span> <span class="o">=</span> <span class="n">Image</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">img_path</span><span class="p">)</span><span class="o">.</span><span class="n">resize</span><span class="p">((</span><span class="mi">224</span><span class="p">,</span> <span class="mi">224</span><span class="p">))</span>
<span class="c1"># Mobilenet.mlmodel's input is BGR format</span>
-<span class="n">img_bgr</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">img</span><span class="p">)[:,</span> <span class="p">:,</span> <span class="p">::</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
-<span class="n">x</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.transpose.html#numpy.transpose" title="View documentation for numpy.transpose"><span class="n">np</span><span class="o">.</span><span class="n">transpose</span></a><span class="p">(</span><span class="n">img_bgr</span><span class="p">,</span> <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class [...]
+<span class="n">img_bgr</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">img</span><span class="p">)[:,</span> <span class="p">:,</span> <span class="p">::</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
+<span class="n">x</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">transpose</span><span class="p">(</span><span class="n">img_bgr</span><span class="p">,</span> <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">))[</span><span class="n">np</span><span class="o">.</span><span class="n">newaxis</span><span class="p">,</span> <sp [...]
</pre></div>
</div>
</div>
@@ -413,7 +413,7 @@ provided by apple in this example</p>
<span class="n">m</span><span class="o">.</span><span class="n">run</span><span class="p">()</span>
<span class="c1"># get outputs</span>
<span class="n">tvm_output</span> <span class="o">=</span> <span class="n">m</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
-<span class="n">top1</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.argmax.html#numpy.argmax" title="View documentation for numpy.argmax"><span class="n">np</span><span class="o">.</span><span class="n">argmax</span></a><span class="p">(</span><span class="n">tvm_output</span><span class="o">.</span><span class="n">numpy</span><span class="p">()[</span><span class="mi">0</span><span class="p">])</span>
+<span class="n">top1</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">tvm_output</span><span class="o">.</span><span class="n">numpy</span><span class="p">()[</span><span class="mi">0</span><span class="p">])</span>
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index c4892b3..9396626 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -407,7 +407,7 @@ pip install opencv-python
<span class="n">dtype</span> <span class="o">=</span> <span class="s2">"float32"</span>
<span class="n">batch_size</span> <span class="o">=</span> <span class="mi">1</span>
-<span class="n">data</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.empty.html#numpy.empty" title="View documentation for numpy.empty"><span class="n">np</span><span class="o">.</span><span class="n">empty</span></a><span class="p">([</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">net</span><span class="o">.</span><span class="n">c</span><span class="p">,</span> <span class="n">net</span><span class="o">.</ [...]
+<span class="n">data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">empty</span><span class="p">([</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">net</span><span class="o">.</span><span class="n">c</span><span class="p">,</span> <span class="n">net</span><span class="o">.</span><span class="n">h</span><span class="p">,</span> <span class="n">net</span><span class="o">.</span><span class="n">w</span><span c [...]
<span class="n">shape_dict</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"data"</span><span class="p">:</span> <span class="n">data</span><span class="o">.</span><span class="n">shape</span><span class="p">}</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Converting darknet to relay functions..."</span><span class="p">)</span>
<span class="n">mod</span><span class="p">,</span> <span class="n">params</span> <span class="o">=</span> <a href="../../reference/api/python/relay/frontend.html#tvm.relay.frontend.from_darknet" title="View documentation for tvm.relay.frontend.from_darknet"><span class="n">relay</span><span class="o">.</span><span class="n">frontend</span><span class="o">.</span><span class="n">from_darknet</span></a><span class="p">(</span><span class="n">net</span><span class="p">,</span> <span class=" [...]
@@ -423,7 +423,7 @@ pip install opencv-python
<p>compile the model</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">target</span> <span class="o">=</span> <a href="../../reference/api/python/target.html#tvm.target.Target" title="View documentation for tvm.target.Target"><span class="n">tvm</span><span class="o">.</span><span class="n">target</span><span class="o">.</span><span class="n">Target</span></a><span class="p">(</span><span class="s2">"llvm"</span><span class="p">,</span> <span class= [...]
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">cpu</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
-<span class="n">data</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.empty.html#numpy.empty" title="View documentation for numpy.empty"><span class="n">np</span><span class="o">.</span><span class="n">empty</span></a><span class="p">([</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">net</span><span class="o">.</span><span class="n">c</span><span class="p">,</span> <span class="n">net</span><span class="o">.</ [...]
+<span class="n">data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">empty</span><span class="p">([</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">net</span><span class="o">.</span><span class="n">c</span><span class="p">,</span> <span class="n">net</span><span class="o">.</span><span class="n">h</span><span class="p">,</span> <span class="n">net</span><span class="o">.</span><span class="n">w</span><span c [...]
<span class="n">shape</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"data"</span><span class="p">:</span> <span class="n">data</span><span class="o">.</span><span class="n">shape</span><span class="p">}</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Compiling the model..."</span><span class="p">)</span>
<span class="k">with</span> <a href="../../reference/api/python/ir.html#tvm.transform.PassContext" title="View documentation for tvm.transform.PassContext"><span class="n">tvm</span><span class="o">.</span><span class="n">transform</span><span class="o">.</span><span class="n">PassContext</span></a><span class="p">(</span><span class="n">opt_level</span><span class="o">=</span><span class="mi">3</span><span class="p">):</span>
diff --git a/docs/how_to/compile_models/from_keras.html b/docs/how_to/compile_models/from_keras.html
index 3f59d8f..b619236 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -404,7 +404,7 @@ pip install -U tensorflow --user
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.imshow.html#matplotlib.pyplot.imshow" title="View documentation for matplotlib.pyplot.imshow"><span class="n">plt</span><span class="o">.</span><span class="n">imshow</span></a><span class="p">(</span><span class="n">img</span><span class="p">)</span>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.show.html#matplotlib.pyplot.show" title="View documentation for matplotlib.pyplot.show"><span class="n">plt</span><span class="o">.</span><span class="n">show</span></a><span class="p">()</span>
<span class="c1"># input preprocess</span>
-<span class="n">data</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">img</span><span class="p">)[</span><a href="https://numpy.org/doc/stable/reference/constants.html#numpy.newaxis" title="View documentation for numpy.newaxis"><span class="n">np</span><spa [...]
+<span class="n">data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">img</span><span class="p">)[</span><span class="n">np</span><span class="o">.</span><span class="n">newaxis</span><span class="p">,</span> <span class="p">:]</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">"float32"</span><span class="p">)</span>
<span class="n">data</span> <span class="o">=</span> <span class="n">preprocess_input</span><span class="p">(</span><span class="n">data</span><span class="p">)</span><span class="o">.</span><span class="n">transpose</span><span class="p">([</span><span class="mi">0</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">])</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"input_1"</span><span class="p">,</span> <span class="n">data</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span>
</pre></div>
@@ -437,7 +437,7 @@ pip install -U tensorflow --user
<h2>Execute on TVM<a class="headerlink" href="#execute-on-tvm" title="Permalink to this headline">¶</a></h2>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">dtype</span> <span class="o">=</span> <span class="s2">"float32"</span>
<span class="n">tvm_out</span> <span class="o">=</span> <span class="n">model</span><span class="p">(</span><a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">dt [...]
-<span class="n">top1_tvm</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.argmax.html#numpy.argmax" title="View documentation for numpy.argmax"><span class="n">np</span><span class="o">.</span><span class="n">argmax</span></a><span class="p">(</span><span class="n">tvm_out</span><span class="o">.</span><span class="n">numpy</span><span class="p">()[</span><span class="mi">0</span><span class="p">])</span>
+<span class="n">top1_tvm</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">tvm_out</span><span class="o">.</span><span class="n">numpy</span><span class="p">()[</span><span class="mi">0</span><span class="p">])</span>
</pre></div>
</div>
</div>
@@ -459,7 +459,7 @@ pip install -U tensorflow --user
<span class="nb">print</span><span class="p">(</span><span class="s2">"Relay top-1 id: </span><span class="si">{}</span><span class="s2">, class name: </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">top1_tvm</span><span class="p">,</span> <span class="n">synset</span><span class="p">[</span><span class="n">top1_tvm</span><span class="p">]))</span>
<span class="c1"># confirm correctness with keras output</span>
<span class="n">keras_out</span> <span class="o">=</span> <span class="n">keras_resnet50</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">transpose</span><span class="p">([</span><span class="mi">0</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">1</span><span class="p">]))</span>
-<span class="n">top1_keras</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.argmax.html#numpy.argmax" title="View documentation for numpy.argmax"><span class="n">np</span><span class="o">.</span><span class="n">argmax</span></a><span class="p">(</span><span class="n">keras_out</span><span class="p">)</span>
+<span class="n">top1_keras</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">keras_out</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Keras top-1 id: </span><span class="si">{}</span><span class="s2">, class name: </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">top1_keras</span><span class="p">,</span> <span class="n">synset</span><span class="p">[</span><span class="n">top1_keras</span><span class="p">]))</span>
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index c2d6241..bea833b 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -388,10 +388,10 @@
<span class="k">def</span> <span class="nf">transform_image</span><span class="p">(</span><span class="n">image</span><span class="p">):</span>
- <span class="n">image</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">image</span><span class="p">)</span> <span class="o">-</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for nu [...]
- <span class="n">image</span> <span class="o">/=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">([</span><span class="mf">58.395</span><span class="p">,</span> <span class="mf">57.12</span><span class="p">,</span> <span class="mf">57.375</span><span class="p">])</span>
+ <span class="n">image</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">image</span><span class="p">)</span> <span class="o">-</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">123.0</span><span class="p">,</span> <span class="mf">117.0</span><span class="p">,</span> <span class="mf">104.0</span><span class="p"> [...]
+ <span class="n">image</span> <span class="o">/=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">58.395</span><span class="p">,</span> <span class="mf">57.12</span><span class="p">,</span> <span class="mf">57.375</span><span class="p">])</span>
<span class="n">image</span> <span class="o">=</span> <span class="n">image</span><span class="o">.</span><span class="n">transpose</span><span class="p">((</span><span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">))</span>
- <span class="n">image</span> <span class="o">=</span> <span class="n">image</span><span class="p">[</span><a href="https://numpy.org/doc/stable/reference/constants.html#numpy.newaxis" title="View documentation for numpy.newaxis"><span class="n">np</span><span class="o">.</span><span class="n">newaxis</span></a><span class="p">,</span> <span class="p">:]</span>
+ <span class="n">image</span> <span class="o">=</span> <span class="n">image</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">newaxis</span><span class="p">,</span> <span class="p">:]</span>
<span class="k">return</span> <span class="n">image</span>
@@ -401,7 +401,7 @@
</div>
<img alt="../../_images/sphx_glr_from_mxnet_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_from_mxnet_001.png" />
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip028d6d4c-438f-443c-9d66-7db994dc95a7 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip2d3e26a2-418e-4a55-a538-ed40c7d51b5b from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
</pre></div>
</div>
@@ -439,7 +439,7 @@ We support MXNet static graph(symbol) and HybridBlock in mxnet.gluon</p>
<span class="n">m</span><span class="o">.</span><span class="n">run</span><span class="p">()</span>
<span class="c1"># get outputs</span>
<span class="n">tvm_output</span> <span class="o">=</span> <span class="n">m</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
-<span class="n">top1</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.argmax.html#numpy.argmax" title="View documentation for numpy.argmax"><span class="n">np</span><span class="o">.</span><span class="n">argmax</span></a><span class="p">(</span><span class="n">tvm_output</span><span class="o">.</span><span class="n">numpy</span><span class="p">()[</span><span class="mi">0</span><span class="p">])</span>
+<span class="n">top1</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">tvm_output</span><span class="o">.</span><span class="n">numpy</span><span class="p">()[</span><span class="mi">0</span><span class="p">])</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"TVM prediction top-1:"</span><span class="p">,</span> <span class="n">top1</span><span class="p">,</span> <span class="n">synset</span><span class="p">[</span><span class="n">top1</span><span class="p">])</span>
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_onnx.html b/docs/how_to/compile_models/from_onnx.html
index 52b4af1..22e7cdb 100644
--- a/docs/how_to/compile_models/from_onnx.html
+++ b/docs/how_to/compile_models/from_onnx.html
@@ -394,7 +394,7 @@ luminance (<cite>Y</cite>) channel.</p>
<span class="n">img</span> <span class="o">=</span> <span class="n">Image</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">img_path</span><span class="p">)</span><span class="o">.</span><span class="n">resize</span><span class="p">((</span><span class="mi">224</span><span class="p">,</span> <span class="mi">224</span><span class="p">))</span>
<span class="n">img_ycbcr</span> <span class="o">=</span> <span class="n">img</span><span class="o">.</span><span class="n">convert</span><span class="p">(</span><span class="s2">"YCbCr"</span><span class="p">)</span> <span class="c1"># convert to YCbCr</span>
<span class="n">img_y</span><span class="p">,</span> <span class="n">img_cb</span><span class="p">,</span> <span class="n">img_cr</span> <span class="o">=</span> <span class="n">img_ycbcr</span><span class="o">.</span><span class="n">split</span><span class="p">()</span>
-<span class="n">x</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">img_y</span><span class="p">)[</span><a href="https://numpy.org/doc/stable/reference/constants.html#numpy.newaxis" title="View documentation for numpy.newaxis"><span class="n">np</span><span [...]
+<span class="n">x</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">img_y</span><span class="p">)[</span><span class="n">np</span><span class="o">.</span><span class="n">newaxis</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">newaxis</span><span class="p">,</span> <span class="p">:,</span> <span class="p">:]</span>
</pre></div>
</div>
</div>
@@ -441,14 +441,14 @@ from the model. The chroma channels <cite>Cb</cite> and <cite>Cr</cite> are resi
bicubic algorithm. The image is then recombined and converted back to <cite>RGB</cite>.</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">matplotlib</span> <span class="k">import</span> <span class="n">pyplot</span> <span class="k">as</span> <span class="n">plt</span>
-<span class="n">out_y</span> <span class="o">=</span> <span class="n">Image</span><span class="o">.</span><span class="n">fromarray</span><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/arrays.scalars.html#numpy.uint8" title="View documentation for numpy.uint8"><span class="n">np</span><span class="o">.</span><span class="n">uint8</span></a><span class="p">((</span><span class="n">tvm_output</span><span class="p">[</span><span class="mi">0</span><span class="p">,< [...]
+<span class="n">out_y</span> <span class="o">=</span> <span class="n">Image</span><span class="o">.</span><span class="n">fromarray</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">((</span><span class="n">tvm_output</span><span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">])</span><span class="o">.</span><span class="n">clip</span><span class="p">(</s [...]
<span class="n">out_cb</span> <span class="o">=</span> <span class="n">img_cb</span><span class="o">.</span><span class="n">resize</span><span class="p">(</span><span class="n">out_y</span><span class="o">.</span><span class="n">size</span><span class="p">,</span> <span class="n">Image</span><span class="o">.</span><span class="n">BICUBIC</span><span class="p">)</span>
<span class="n">out_cr</span> <span class="o">=</span> <span class="n">img_cr</span><span class="o">.</span><span class="n">resize</span><span class="p">(</span><span class="n">out_y</span><span class="o">.</span><span class="n">size</span><span class="p">,</span> <span class="n">Image</span><span class="o">.</span><span class="n">BICUBIC</span><span class="p">)</span>
<span class="n">result</span> <span class="o">=</span> <span class="n">Image</span><span class="o">.</span><span class="n">merge</span><span class="p">(</span><span class="s2">"YCbCr"</span><span class="p">,</span> <span class="p">[</span><span class="n">out_y</span><span class="p">,</span> <span class="n">out_cb</span><span class="p">,</span> <span class="n">out_cr</span><span class="p">])</span><span class="o">.</span><span class="n">convert</span><span class="p">(</span><spa [...]
-<span class="n">canvas</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.full.html#numpy.full" title="View documentation for numpy.full"><span class="n">np</span><span class="o">.</span><span class="n">full</span></a><span class="p">((</span><span class="mi">672</span><span class="p">,</span> <span class="mi">672</span> <span class="o">*</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">3</span><span class="p">),</span [...]
-<span class="n">canvas</span><span class="p">[</span><span class="mi">0</span><span class="p">:</span><span class="mi">224</span><span class="p">,</span> <span class="mi">0</span><span class="p">:</span><span class="mi">224</span><span class="p">,</span> <span class="p">:]</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.asarray.html#numpy.asarray" title="View documentation for numpy.asarray"><span class="n">np</span><span class="o">.</span> [...]
-<span class="n">canvas</span><span class="p">[:,</span> <span class="mi">672</span><span class="p">:,</span> <span class="p">:]</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.asarray.html#numpy.asarray" title="View documentation for numpy.asarray"><span class="n">np</span><span class="o">.</span><span class="n">asarray</span></a><span class="p">(</span><span class="n">result</span><span class="p">)</span>
-<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.imshow.html#matplotlib.pyplot.imshow" title="View documentation for matplotlib.pyplot.imshow"><span class="n">plt</span><span class="o">.</span><span class="n">imshow</span></a><span class="p">(</span><span class="n">canvas</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/arrays.scalars.html#numpy.uint8" title="View documentation for numpy [...]
+<span class="n">canvas</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">full</span><span class="p">((</span><span class="mi">672</span><span class="p">,</span> <span class="mi">672</span> <span class="o">*</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">3</span><span class="p">),</span> <span class="mi">255</span><span class="p">)</span>
+<span class="n">canvas</span><span class="p">[</span><span class="mi">0</span><span class="p">:</span><span class="mi">224</span><span class="p">,</span> <span class="mi">0</span><span class="p">:</span><span class="mi">224</span><span class="p">,</span> <span class="p">:]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">asarray</span><span class="p">(</span><span class="n">img</span><span class="p">)</span>
+<span class="n">canvas</span><span class="p">[:,</span> <span class="mi">672</span><span class="p">:,</span> <span class="p">:]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">asarray</span><span class="p">(</span><span class="n">result</span><span class="p">)</span>
+<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.imshow.html#matplotlib.pyplot.imshow" title="View documentation for matplotlib.pyplot.imshow"><span class="n">plt</span><span class="o">.</span><span class="n">imshow</span></a><span class="p">(</span><span class="n">canvas</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">))</span>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.show.html#matplotlib.pyplot.show" title="View documentation for matplotlib.pyplot.show"><span class="n">plt</span><span class="o">.</span><span class="n">show</span></a><span class="p">()</span>
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_paddle.html b/docs/how_to/compile_models/from_paddle.html
index c185d23..b7ff85a 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -401,7 +401,7 @@ A quick solution is</p>
<span class="n">img</span> <span class="o">=</span> <span class="n">Image</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">img_path</span><span class="p">)</span><span class="o">.</span><span class="n">resize</span><span class="p">((</span><span class="mi">224</span><span class="p">,</span> <span class="mi">224</span><span class="p">))</span>
<span class="n">img</span> <span class="o">=</span> <span class="n">transforms</span><span class="p">(</span><span class="n">img</span><span class="p">)</span>
-<span class="n">img</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.expand_dims.html#numpy.expand_dims" title="View documentation for numpy.expand_dims"><span class="n">np</span><span class="o">.</span><span class="n">expand_dims</span></a><span class="p">(</span><span class="n">img</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
+<span class="n">img</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">expand_dims</span><span class="p">(</span><span class="n">img</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
</pre></div>
</div>
</div>
@@ -441,7 +441,7 @@ A quick solution is</p>
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">synset_path</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
<span class="n">synset</span> <span class="o">=</span> <span class="n">f</span><span class="o">.</span><span class="n">readlines</span><span class="p">()</span>
-<span class="n">top1</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.argmax.html#numpy.argmax" title="View documentation for numpy.argmax"><span class="n">np</span><span class="o">.</span><span class="n">argmax</span></a><span class="p">(</span><span class="n">tvm_output</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
+<span class="n">top1</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">tvm_output</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
<span class="nb">print</span><span class="p">(</span><span class="n">f</span><span class="s2">"TVM prediction top-1 id: </span><span class="si">{top1}</span><span class="s2">, class name: </span><span class="si">{synset[top1]}</span><span class="s2">"</span><span class="p">)</span>
</pre></div>
</div>
@@ -449,7 +449,7 @@ A quick solution is</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>TVM prediction top-1 id: 282, class name: 282: 'tiger cat',
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.499 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.542 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-paddle-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/16269b77359771348d507395692524cf/from_paddle.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_paddle.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index c128f86..91186df 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -387,11 +387,9 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 8%|7 | 3.54M/44.7M [00:00<00:01, 36.9MB/s]
- 16%|#5 | 7.06M/44.7M [00:00<00:01, 35.5MB/s]
- 49%|####9 | 21.9M/44.7M [00:00<00:00, 89.1MB/s]
- 89%|########9 | 39.9M/44.7M [00:00<00:00, 128MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 108MB/s]
+ 38%|###8 | 17.1M/44.7M [00:00<00:00, 180MB/s]
+ 92%|#########1| 40.9M/44.7M [00:00<00:00, 220MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 217MB/s]
</pre></div>
</div>
</div>
@@ -416,7 +414,7 @@ be unstable.</p>
<span class="p">]</span>
<span class="p">)</span>
<span class="n">img</span> <span class="o">=</span> <span class="n">my_preprocess</span><span class="p">(</span><span class="n">img</span><span class="p">)</span>
-<span class="n">img</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.expand_dims.html#numpy.expand_dims" title="View documentation for numpy.expand_dims"><span class="n">np</span><span class="o">.</span><span class="n">expand_dims</span></a><span class="p">(</span><span class="n">img</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
+<span class="n">img</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">expand_dims</span><span class="p">(</span><span class="n">img</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
</pre></div>
</div>
</div>
@@ -489,7 +487,7 @@ be unstable.</p>
<span class="n">class_id_to_key</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">class_id_to_key</span><span class="p">]</span>
<span class="c1"># Get top-1 result for TVM</span>
-<span class="n">top1_tvm</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.argmax.html#numpy.argmax" title="View documentation for numpy.argmax"><span class="n">np</span><span class="o">.</span><span class="n">argmax</span></a><span class="p">(</span><span class="n">tvm_output</span><span class="o">.</span><span class="n">numpy</span><span class="p">()[</span><span class="mi">0</span><span class="p">])</span>
+<span class="n">top1_tvm</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">tvm_output</span><span class="o">.</span><span class="n">numpy</span><span class="p">()[</span><span class="mi">0</span><span class="p">])</span>
<span class="n">tvm_class_key</span> <span class="o">=</span> <span class="n">class_id_to_key</span><span class="p">[</span><span class="n">top1_tvm</span><span class="p">]</span>
<span class="c1"># Convert input to PyTorch variable and get PyTorch result for comparison</span>
@@ -498,7 +496,7 @@ be unstable.</p>
<span class="n">output</span> <span class="o">=</span> <span class="n">model</span><span class="p">(</span><span class="n">torch_img</span><span class="p">)</span>
<span class="c1"># Get top-1 result for PyTorch</span>
- <span class="n">top1_torch</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.argmax.html#numpy.argmax" title="View documentation for numpy.argmax"><span class="n">np</span><span class="o">.</span><span class="n">argmax</span></a><span class="p">(</span><span class="n">output</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
+ <span class="n">top1_torch</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">output</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
<span class="n">torch_class_key</span> <span class="o">=</span> <span class="n">class_id_to_key</span><span class="p">[</span><span class="n">top1_torch</span><span class="p">]</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Relay top-1 id: </span><span class="si">{}</span><span class="s2">, class name: </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">top1_tvm</span><span class="p">,</span> <span class="n">key_to_classname</span><span class="p">[</span><span class="n">tvm_class_key</span><span class="p">]))</span>
diff --git a/docs/how_to/compile_models/from_tensorflow.html b/docs/how_to/compile_models/from_tensorflow.html
index bc423fa..45b59f4 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -462,7 +462,7 @@ Hence we supply decoded frame to TVM instead.</p>
<span class="n">image</span> <span class="o">=</span> <span class="n">Image</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">img_path</span><span class="p">)</span><span class="o">.</span><span class="n">resize</span><span class="p">((</span><span class="mi">299</span><span class="p">,</span> <span class="mi">299</span><span class="p">))</span>
-<span class="n">x</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">image</span><span class="p">)</span>
+<span class="n">x</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">image</span><span class="p">)</span>
</pre></div>
</div>
</div>
@@ -524,7 +524,7 @@ lib: target library which can be deployed on target with TVM runtime.</p>
<h2>Process the output<a class="headerlink" href="#process-the-output" title="Permalink to this headline">¶</a></h2>
<p>Process the model output to human readable text for InceptionV1.</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">predictions</span> <span class="o">=</span> <span class="n">tvm_output</span><span class="o">.</span><span class="n">numpy</span><span class="p">()</span>
-<span class="n">predictions</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.squeeze.html#numpy.squeeze" title="View documentation for numpy.squeeze"><span class="n">np</span><span class="o">.</span><span class="n">squeeze</span></a><span class="p">(</span><span class="n">predictions</span><span class="p">)</span>
+<span class="n">predictions</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">squeeze</span><span class="p">(</span><span class="n">predictions</span><span class="p">)</span>
<span class="c1"># Creates node ID --> English string lookup.</span>
<span class="n">node_lookup</span> <span class="o">=</span> <span class="n">tf_testing</span><span class="o">.</span><span class="n">NodeLookup</span><span class="p">(</span><span class="n">label_lookup_path</span><span class="o">=</span><span class="n">map_proto_path</span><span class="p">,</span> <span class="n">uid_lookup_path</span><span class="o">=</span><span class="n">label_path</span><span class="p">)</span>
@@ -583,7 +583,7 @@ rapeseed (score = 0.00021)
<span class="n">softmax_tensor</span> <span class="o">=</span> <span class="n">sess</span><span class="o">.</span><span class="n">graph</span><span class="o">.</span><span class="n">get_tensor_by_name</span><span class="p">(</span><span class="s2">"softmax:0"</span><span class="p">)</span>
<span class="n">predictions</span> <span class="o">=</span> <span class="n">sess</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">softmax_tensor</span><span class="p">,</span> <span class="p">{</span><span class="s2">"DecodeJpeg/contents:0"</span><span class="p">:</span> <span class="n">image_data</span><span class="p">})</span>
- <span class="n">predictions</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.squeeze.html#numpy.squeeze" title="View documentation for numpy.squeeze"><span class="n">np</span><span class="o">.</span><span class="n">squeeze</span></a><span class="p">(</span><span class="n">predictions</span><span class="p">)</span>
+ <span class="n">predictions</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">squeeze</span><span class="p">(</span><span class="n">predictions</span><span class="p">)</span>
<span class="c1"># Creates node ID --> English string lookup.</span>
<span class="n">node_lookup</span> <span class="o">=</span> <span class="n">tf_testing</span><span class="o">.</span><span class="n">NodeLookup</span><span class="p">(</span>
@@ -611,7 +611,7 @@ 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 9.234 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.938 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download 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/from_tflite.html b/docs/how_to/compile_models/from_tflite.html
index 00b3c18..86e60ee 100644
--- a/docs/how_to/compile_models/from_tflite.html
+++ b/docs/how_to/compile_models/from_tflite.html
@@ -427,10 +427,10 @@ flatc --python schema.fbs
<span class="n">resized_image</span> <span class="o">=</span> <span class="n">Image</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">image_path</span><span class="p">)</span><span class="o">.</span><span class="n">resize</span><span class="p">((</span><span class="mi">224</span><span class="p">,</span> <span class="mi">224</span><span class="p">))</span>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.imshow.html#matplotlib.pyplot.imshow" title="View documentation for matplotlib.pyplot.imshow"><span class="n">plt</span><span class="o">.</span><span class="n">imshow</span></a><span class="p">(</span><span class="n">resized_image</span><span class="p">)</span>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.show.html#matplotlib.pyplot.show" title="View documentation for matplotlib.pyplot.show"><span class="n">plt</span><span class="o">.</span><span class="n">show</span></a><span class="p">()</span>
-<span class="n">image_data</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.asarray.html#numpy.asarray" title="View documentation for numpy.asarray"><span class="n">np</span><span class="o">.</span><span class="n">asarray</span></a><span class="p">(</span><span class="n">resized_image</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">"float32"</span><span cla [...]
+<span class="n">image_data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">asarray</span><span class="p">(</span><span class="n">resized_image</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">"float32"</span><span class="p">)</span>
<span class="c1"># Add a dimension to the image so that we have NHWC format layout</span>
-<span class="n">image_data</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.expand_dims.html#numpy.expand_dims" title="View documentation for numpy.expand_dims"><span class="n">np</span><span class="o">.</span><span class="n">expand_dims</span></a><span class="p">(</span><span class="n">image_data</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
+<span class="n">image_data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">expand_dims</span><span class="p">(</span><span class="n">image_data</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="c1"># Preprocess image as described here:</span>
<span class="c1"># https://github.com/tensorflow/models/blob/edb6ed22a801665946c63d650ab9a0b23d98e1b1/research/slim/preprocessing/inception_preprocessing.py#L243</span>
@@ -506,10 +506,10 @@ flatc --python schema.fbs
<span class="n">labels</span> <span class="o">=</span> <span class="n">f</span><span class="o">.</span><span class="n">readlines</span><span class="p">()</span>
<span class="c1"># Convert result to 1D data</span>
-<span class="n">predictions</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.squeeze.html#numpy.squeeze" title="View documentation for numpy.squeeze"><span class="n">np</span><span class="o">.</span><span class="n">squeeze</span></a><span class="p">(</span><span class="n">tvm_output</span><span class="p">)</span>
+<span class="n">predictions</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">squeeze</span><span class="p">(</span><span class="n">tvm_output</span><span class="p">)</span>
<span class="c1"># Get top 1 prediction</span>
-<span class="n">prediction</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.argmax.html#numpy.argmax" title="View documentation for numpy.argmax"><span class="n">np</span><span class="o">.</span><span class="n">argmax</span></a><span class="p">(</span><span class="n">predictions</span><span class="p">)</span>
+<span class="n">prediction</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">predictions</span><span class="p">)</span>
<span class="c1"># Convert id to class name and show the result</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"The image prediction result is: id "</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">prediction</span><span class="p">)</span> <span class="o">+</span> <span class="s2">" name: "</span> <span class="o">+</span> <span class="n">labels</span><span class="p">[</span><span class="n">prediction</span><span class="p">])</span>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index 74ecbcc..3388bab 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -300,18 +300,18 @@
<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>05:49.702</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:33.129</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>01:10.499</strong>: <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></li>
-<li><p><strong>01:09.234</strong>: <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></li>
-<li><p><strong>00:58.972</strong>: <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></li>
-<li><p><strong>00:45.009</strong>: <a class="reference internal" href="from_caffe2.html#sphx-glr-how-to-compile-models-from-caffe2-py"><span class="std std-ref">Compile Caffe2 Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_caffe2.py</span></code>)</p></li>
-<li><p><strong>00:25.884</strong>: <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></li>
-<li><p><strong>00:22.304</strong>: <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></li>
-<li><p><strong>00:21.029</strong>: <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></li>
-<li><p><strong>00:19.537</strong>: <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></li>
-<li><p><strong>00:14.678</strong>: <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></li>
-<li><p><strong>00:02.555</strong>: <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></li>
+<li><p><strong>01:08.938</strong>: <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></li>
+<li><p><strong>01:05.542</strong>: <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></li>
+<li><p><strong>00:55.581</strong>: <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></li>
+<li><p><strong>00:41.936</strong>: <a class="reference internal" href="from_caffe2.html#sphx-glr-how-to-compile-models-from-caffe2-py"><span class="std std-ref">Compile Caffe2 Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_caffe2.py</span></code>)</p></li>
+<li><p><strong>00:25.540</strong>: <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></li>
+<li><p><strong>00:20.321</strong>: <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></li>
+<li><p><strong>00:20.197</strong>: <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></li>
+<li><p><strong>00:18.940</strong>: <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></li>
+<li><p><strong>00:13.481</strong>: <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></li>
+<li><p><strong>00:02.653</strong>: <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></li>
</ul>
</div>
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 ef15542..23cee09 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -497,10 +497,10 @@ transform its format.</p>
<span class="k">def</span> <span class="nf">transform_image</span><span class="p">(</span><span class="n">image</span><span class="p">):</span>
- <span class="n">image</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">image</span><span class="p">)</span> <span class="o">-</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for nu [...]
- <span class="n">image</span> <span class="o">/=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">([</span><span class="mf">58.395</span><span class="p">,</span> <span class="mf">57.12</span><span class="p">,</span> <span class="mf">57.375</span><span class="p">])</span>
+ <span class="n">image</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">image</span><span class="p">)</span> <span class="o">-</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">123.0</span><span class="p">,</span> <span class="mf">117.0</span><span class="p">,</span> <span class="mf">104.0</span><span class="p"> [...]
+ <span class="n">image</span> <span class="o">/=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">58.395</span><span class="p">,</span> <span class="mf">57.12</span><span class="p">,</span> <span class="mf">57.375</span><span class="p">])</span>
<span class="n">image</span> <span class="o">=</span> <span class="n">image</span><span class="o">.</span><span class="n">transpose</span><span class="p">((</span><span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">))</span>
- <span class="n">image</span> <span class="o">=</span> <span class="n">image</span><span class="p">[</span><a href="https://numpy.org/doc/stable/reference/constants.html#numpy.newaxis" title="View documentation for numpy.newaxis"><span class="n">np</span><span class="o">.</span><span class="n">newaxis</span></a><span class="p">,</span> <span class="p">:]</span>
+ <span class="n">image</span> <span class="o">=</span> <span class="n">image</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">newaxis</span><span class="p">,</span> <span class="p">:]</span>
<span class="k">return</span> <span class="n">image</span>
@@ -610,7 +610,7 @@ to the remote android device.</p>
<span class="n">out</span> <span class="o">=</span> <span class="n">module</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
<span class="c1"># get top1 result</span>
-<span class="n">top1</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.argmax.html#numpy.argmax" title="View documentation for numpy.argmax"><span class="n">np</span><span class="o">.</span><span class="n">argmax</span></a><span class="p">(</span><span class="n">out</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
+<span class="n">top1</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">out</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"TVM prediction top-1: </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">synset</span><span class="p">[</span><span class="n">top1</span><span class="p">]))</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Evaluate inference time cost..."</span><span class="p">)</span>
@@ -622,7 +622,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.6170 16.6062 16.9316 16.3222 0.1629
+ 16.0706 16.1013 16.3075 15.8013 0.1648
</pre></div>
</div>
</div>
diff --git a/docs/how_to/deploy_models/deploy_model_on_rasp.html b/docs/how_to/deploy_models/deploy_model_on_rasp.html
index 800c678..0658134 100644
--- a/docs/how_to/deploy_models/deploy_model_on_rasp.html
+++ b/docs/how_to/deploy_models/deploy_model_on_rasp.html
@@ -417,10 +417,10 @@ transform its format.</p>
<span class="k">def</span> <span class="nf">transform_image</span><span class="p">(</span><span class="n">image</span><span class="p">):</span>
- <span class="n">image</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">image</span><span class="p">)</span> <span class="o">-</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for nu [...]
- <span class="n">image</span> <span class="o">/=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">([</span><span class="mf">58.395</span><span class="p">,</span> <span class="mf">57.12</span><span class="p">,</span> <span class="mf">57.375</span><span class="p">])</span>
+ <span class="n">image</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">image</span><span class="p">)</span> <span class="o">-</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">123.0</span><span class="p">,</span> <span class="mf">117.0</span><span class="p">,</span> <span class="mf">104.0</span><span class="p"> [...]
+ <span class="n">image</span> <span class="o">/=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">58.395</span><span class="p">,</span> <span class="mf">57.12</span><span class="p">,</span> <span class="mf">57.375</span><span class="p">])</span>
<span class="n">image</span> <span class="o">=</span> <span class="n">image</span><span class="o">.</span><span class="n">transpose</span><span class="p">((</span><span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">))</span>
- <span class="n">image</span> <span class="o">=</span> <span class="n">image</span><span class="p">[</span><a href="https://numpy.org/doc/stable/reference/constants.html#numpy.newaxis" title="View documentation for numpy.newaxis"><span class="n">np</span><span class="o">.</span><span class="n">newaxis</span></a><span class="p">,</span> <span class="p">:]</span>
+ <span class="n">image</span> <span class="o">=</span> <span class="n">image</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">newaxis</span><span class="p">,</span> <span class="p">:]</span>
<span class="k">return</span> <span class="n">image</span>
@@ -529,7 +529,7 @@ to the remote device.</p>
<span class="c1"># get output</span>
<span class="n">out</span> <span class="o">=</span> <span class="n">module</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
<span class="c1"># get top1 result</span>
-<span class="n">top1</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.argmax.html#numpy.argmax" title="View documentation for numpy.argmax"><span class="n">np</span><span class="o">.</span><span class="n">argmax</span></a><span class="p">(</span><span class="n">out</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
+<span class="n">top1</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">out</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"TVM prediction top-1: </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">synset</span><span class="p">[</span><span class="n">top1</span><span class="p">]))</span>
</pre></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 5dea1ce..c8b3d85 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -398,7 +398,7 @@ be unstable.</p>
<span class="n">model</span> <span class="o">=</span> <span class="n">TraceWrapper</span><span class="p">(</span><span class="n">model_func</span><span class="p">(</span><span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">))</span>
<span class="n">model</span><span class="o">.</span><span class="n">eval</span><span class="p">()</span>
-<span class="n">inp</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span clas [...]
+<span class="n">inp</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="mf">0.0</span><span class="p">,</span> <span class="mf">250.0</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="p">(</spa [...]
<span class="k">with</span> <span class="n">torch</span><span class="o">.</span><span class="n">no_grad</span><span class="p">():</span>
<span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">(</span><span class="n">inp</span><span class="p">)</span>
@@ -409,15 +409,34 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 7%|7 | 12.5M/170M [00:00<00:01, 131MB/s]
- 20%|#9 | 33.7M/170M [00:00<00:00, 185MB/s]
- 33%|###2 | 55.4M/170M [00:00<00:00, 204MB/s]
- 46%|####5 | 77.8M/170M [00:00<00:00, 216MB/s]
- 58%|#####8 | 98.5M/170M [00:00<00:00, 215MB/s]
- 70%|####### | 119M/170M [00:00<00:00, 214MB/s]
- 82%|########2 | 139M/170M [00:00<00:00, 213MB/s]
- 94%|#########4| 160M/170M [00:00<00:00, 200MB/s]
-100%|##########| 170M/170M [00:00<00:00, 202MB/s]
+ 3%|2 | 5.07M/170M [00:00<00:03, 51.6MB/s]
+ 7%|6 | 11.7M/170M [00:00<00:02, 61.8MB/s]
+ 10%|# | 17.6M/170M [00:00<00:02, 58.2MB/s]
+ 14%|#4 | 24.6M/170M [00:00<00:02, 63.7MB/s]
+ 18%|#8 | 30.7M/170M [00:00<00:02, 53.7MB/s]
+ 21%|##1 | 36.0M/170M [00:00<00:02, 52.3MB/s]
+ 24%|##4 | 41.2M/170M [00:00<00:02, 48.4MB/s]
+ 27%|##7 | 45.9M/170M [00:00<00:02, 46.3MB/s]
+ 31%|###1 | 53.1M/170M [00:01<00:02, 54.2MB/s]
+ 35%|###4 | 59.1M/170M [00:01<00:02, 56.7MB/s]
+ 39%|###8 | 66.0M/170M [00:01<00:01, 59.2MB/s]
+ 42%|####2 | 71.8M/170M [00:01<00:01, 57.0MB/s]
+ 46%|####5 | 77.8M/170M [00:01<00:01, 58.8MB/s]
+ 49%|####9 | 83.5M/170M [00:01<00:01, 53.6MB/s]
+ 53%|#####2 | 89.6M/170M [00:01<00:01, 56.4MB/s]
+ 56%|#####6 | 95.9M/170M [00:01<00:01, 58.3MB/s]
+ 60%|#####9 | 102M/170M [00:01<00:01, 49.5MB/s]
+ 63%|######3 | 107M/170M [00:02<00:01, 52.7MB/s]
+ 67%|######6 | 113M/170M [00:02<00:01, 55.1MB/s]
+ 70%|######9 | 119M/170M [00:02<00:01, 53.1MB/s]
+ 74%|#######4 | 126M/170M [00:02<00:00, 60.0MB/s]
+ 79%|#######8 | 134M/170M [00:02<00:00, 65.8MB/s]
+ 83%|########3 | 142M/170M [00:02<00:00, 70.2MB/s]
+ 87%|########7 | 149M/170M [00:02<00:00, 69.8MB/s]
+ 91%|#########1| 155M/170M [00:02<00:00, 69.8MB/s]
+ 95%|#########5| 162M/170M [00:02<00:00, 68.6MB/s]
+ 99%|#########9| 169M/170M [00:03<00:00, 59.9MB/s]
+100%|##########| 170M/170M [00:03<00:00, 58.1MB/s]
/usr/local/lib/python3.7/dist-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3702: 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).
@@ -451,8 +470,8 @@ be unstable.</p>
<span class="n">img</span> <span class="o">=</span> <span class="n">cv2</span><span class="o">.</span><span class="n">imread</span><span class="p">(</span><span class="n">img_path</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">"float32"</span><span class="p">)</span>
<span class="n">img</span> <span class="o">=</span> <span class="n">cv2</span><span class="o">.</span><span class="n">resize</span><span class="p">(</span><span class="n">img</span><span class="p">,</span> <span class="p">(</span><span class="n">in_size</span><span class="p">,</span> <span class="n">in_size</span><span class="p">))</span>
<span class="n">img</span> <span class="o">=</span> <span class="n">cv2</span><span class="o">.</span><span class="n">cvtColor</span><span class="p">(</span><span class="n">img</span><span class="p">,</span> <span class="n">cv2</span><span class="o">.</span><span class="n">COLOR_BGR2RGB</span><span class="p">)</span>
-<span class="n">img</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.transpose.html#numpy.transpose" title="View documentation for numpy.transpose"><span class="n">np</span><span class="o">.</span><span class="n">transpose</span></a><span class="p">(</span><span class="n">img</span> <span class="o">/</span> <span class="mf">255.0</span><span class="p">,</span> <span class="p">[</span><span class="mi">2</span><span class="p">,</span> <span cl [...]
-<span class="n">img</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.expand_dims.html#numpy.expand_dims" title="View documentation for numpy.expand_dims"><span class="n">np</span><span class="o">.</span><span class="n">expand_dims</span></a><span class="p">(</span><span class="n">img</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
+<span class="n">img</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">transpose</span><span class="p">(</span><span class="n">img</span> <span class="o">/</span> <span class="mf">255.0</span><span class="p">,</span> <span class="p">[</span><span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">])</span>
+<span class="n">img</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">expand_dims</span><span class="p">(</span><span class="n">img</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
</pre></div>
</div>
</div>
@@ -512,7 +531,7 @@ 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 12.191 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 5.334 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download 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 b92bd60..c4f2a68 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -381,7 +381,7 @@ Once loaded, we can run compiled, quantized models on any hardware TVM supports.
<span class="n">im</span> <span class="o">=</span> <span class="n">get_real_image</span><span class="p">(</span><span class="mi">224</span><span class="p">,</span> <span class="mi">224</span><span class="p">)</span>
<span class="n">preprocess</span> <span class="o">=</span> <span class="n">get_transform</span><span class="p">()</span>
<span class="n">pt_tensor</span> <span class="o">=</span> <span class="n">preprocess</span><span class="p">(</span><span class="n">im</span><span class="p">)</span>
- <span class="k">return</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.expand_dims.html#numpy.expand_dims" title="View documentation for numpy.expand_dims"><span class="n">np</span><span class="o">.</span><span class="n">expand_dims</span></a><span class="p">(</span><span class="n">pt_tensor</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="mi">0</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">expand_dims</span><span class="p">(</span><span class="n">pt_tensor</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="mi">0</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">get_synset</span><span class="p">():</span>
@@ -450,9 +450,7 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 42%|####1 | 5.63M/13.6M [00:00<00:00, 59.0MB/s]
- 85%|########4 | 11.5M/13.6M [00:00<00:00, 60.3MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 61.1MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 157MB/s]
</pre></div>
</div>
</div>
@@ -511,8 +509,8 @@ standard Relay operators before compilation.</p>
<div class="section" id="compare-the-output-labels">
<h2>Compare the output labels<a class="headerlink" href="#compare-the-output-labels" title="Permalink to this headline">¶</a></h2>
<p>We should see identical labels printed.</p>
-<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">pt_top3_labels</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.argsort.html#numpy.argsort" title="View documentation for numpy.argsort"><span class="n">np</span><span class="o">.</span><span class="n">argsort</span></a><span class="p">(</span><span class="n">pt_result</span><span class="p">[</span><span class="mi">0</span><span class="p">])[: [...]
-<span class="n">tvm_top3_labels</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.argsort.html#numpy.argsort" title="View documentation for numpy.argsort"><span class="n">np</span><span class="o">.</span><span class="n">argsort</span></a><span class="p">(</span><span class="n">tvm_result</span><span class="p">[</span><span class="mi">0</span><span class="p">])[::</span><span class="o">-</span><span class="mi">1</span><span class="p">][:</span [...]
+<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">pt_top3_labels</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argsort</span><span class="p">(</span><span class="n">pt_result</span><span class="p">[</span><span class="mi">0</span><span class="p">])[::</span><span class="o">-</span><span class="mi">1</span><span class="p">][:</span><span class="mi">3</span><span class="p">]</span>
+<span class="n">tvm_top3_labels</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argsort</span><span class="p">(</span><span class="n">tvm_result</span><span class="p">[</span><span class="mi">0</span><span class="p">])[::</span><span class="o">-</span><span class="mi">1</span><span class="p">][:</span><span class="mi">3</span><span class="p">]</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"PyTorch top3 labels:"</span><span class="p">,</span> <span class="p">[</span><span class="n">synset</span><span class="p">[</span><span class="n">label</span><span class="p">]</span> <span class="k">for</span> <span class="n">label</span> <span class="ow">in</span> <span class="n">pt_top3_labels</span><span class="p">])</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"TVM top3 labels:"</span><span class="p">,</span> <span class="p">[</span><span class="n">synset</span><span class="p">[</span><span class="n">label</span><span class="p">]</span> <span class="k">for</span> <span class="n">label</span> <span class="ow">in</span> <span class="n">tvm_top3_labels</span><span class="p">])</span>
@@ -526,7 +524,7 @@ TVM top3 labels: ['tiger cat', 'Egyptian cat', 'tabby, tabby
<p>However, due to the difference in numerics, in general the raw floating point
outputs are not expected to be identical. Here, we print how many floating point
output values are identical out of 1000 outputs from mobilenet v2.</p>
-<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%d</span><span class="s2"> in 1000 raw floating outputs identical."</span> <span class="o">%</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.sum.html#numpy.sum" title="View documentation for numpy.sum"><span class="n">np</span><span class="o">.</span><span class="n">sum</span></a [...]
+<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%d</span><span class="s2"> in 1000 raw floating outputs identical."</span> <span class="o">%</span> <span class="n">np</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">tvm_result</span><span class="p">[</span><span class="mi">0</span><span class="p">]</spa [...]
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
@@ -545,7 +543,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
<p class="sphx-glr-script-out">Out:</p>
<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)
- 90.4001 90.3649 93.2152 89.9955 0.3631
+ 90.1497 90.1021 90.7025 89.8559 0.1703
</pre></div>
</div>
<div class="admonition note">
@@ -584,7 +582,7 @@ 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 7.473 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.532 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download 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 b9bfd39..390949d 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -410,8 +410,8 @@ pip install <span class="nv">tflite</span><span class="o">==</span><span class="
<span class="n">image_url</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">repo_base</span><span class="p">,</span> <span class="n">img_name</span><span class="p">)</span>
<span class="n">img_path</span> <span class="o">=</span> <span class="n">download_testdata</span><span class="p">(</span><span class="n">image_url</span><span class="p">,</span> <span class="n">img_name</span><span class="p">,</span> <span class="n">module</span><span class="o">=</span><span class="s2">"data"</span><span class="p">)</span>
<span class="n">image</span> <span class="o">=</span> <span class="n">Image</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">img_path</span><span class="p">)</span><span class="o">.</span><span class="n">resize</span><span class="p">((</span><span class="n">im_height</span><span class="p">,</span> <span class="n">im_width</span><span class="p">))</span>
- <span class="n">x</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">image</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">"uint8"</span><span class="p">)</span>
- <span class="n">data</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.reshape.html#numpy.reshape" title="View documentation for numpy.reshape"><span class="n">np</span><span class="o">.</span><span class="n">reshape</span></a><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">im_height</span><span class="p">,</span> <span class [...]
+ <span class="n">x</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">image</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">"uint8"</span><span class="p">)</span>
+ <span class="n">data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">im_height</span><span class="p">,</span> <span class="n">im_width</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span>
<span class="k">return</span> <span class="n">data</span>
@@ -476,7 +476,7 @@ pip install <span class="nv">tflite</span><span class="o">==</span><span class="
<span class="n">rt_mod</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="s2">"input"</span><span class="p">,</span> <span class="n">data</span><span class="p">)</span>
<span class="n">rt_mod</span><span class="o">.</span><span class="n">run</span><span class="p">()</span>
<span class="n">tvm_res</span> <span class="o">=</span> <span class="n">rt_mod</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span><span class="o">.</span><span class="n">numpy</span><span class="p">()</span>
- <span class="n">tvm_pred</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.squeeze.html#numpy.squeeze" title="View documentation for numpy.squeeze"><span class="n">np</span><span class="o">.</span><span class="n">squeeze</span></a><span class="p">(</span><span class="n">tvm_res</span><span class="p">)</span><span class="o">.</span><span class="n">argsort</span><span class="p">()[</span><span class="o">-</span><span class="mi">5</span><spa [...]
+ <span class="n">tvm_pred</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">squeeze</span><span class="p">(</span><span class="n">tvm_res</span><span class="p">)</span><span class="o">.</span><span class="n">argsort</span><span class="p">()[</span><span class="o">-</span><span class="mi">5</span><span class="p">:][::</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
<span class="k">return</span> <span class="n">tvm_pred</span><span class="p">,</span> <span class="n">rt_mod</span>
</pre></div>
</div>
@@ -485,7 +485,7 @@ pip install <span class="nv">tflite</span><span class="o">==</span><span class="
<h2>TFLite inference<a class="headerlink" href="#tflite-inference" title="Permalink to this headline">¶</a></h2>
<p>Run TFLite inference on the quantized model.</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">tflite_res</span> <span class="o">=</span> <span class="n">run_tflite_model</span><span class="p">(</span><span class="n">tflite_model_buf</span><span class="p">,</span> <span class="n">data</span><span class="p">)</span>
-<span class="n">tflite_pred</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.squeeze.html#numpy.squeeze" title="View documentation for numpy.squeeze"><span class="n">np</span><span class="o">.</span><span class="n">squeeze</span></a><span class="p">(</span><span class="n">tflite_res</span><span class="p">)</span><span class="o">.</span><span class="n">argsort</span><span class="p">()[</span><span class="o">-</span><span class="mi">5</span><s [...]
+<span class="n">tflite_pred</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">squeeze</span><span class="p">(</span><span class="n">tflite_res</span><span class="p">)</span><span class="o">.</span><span class="n">argsort</span><span class="p">()[</span><span class="o">-</span><span class="mi">5</span><span class="p">:][::</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
</pre></div>
</div>
</div>
@@ -540,7 +540,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
<p class="sphx-glr-script-out">Out:</p>
<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)
- 121.1093 120.9318 126.7829 119.3034 1.0425
+ 117.5013 117.4614 119.8671 116.2796 0.6565
</pre></div>
</div>
<div class="admonition note">
@@ -568,7 +568,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 1.357 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 59.415 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download 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 9727d6b..72922a6 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -480,7 +480,7 @@ 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 15.693 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 12.105 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download 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_sparse.html b/docs/how_to/deploy_models/deploy_sparse.html
index f7e7ae9..99351c9 100644
--- a/docs/how_to/deploy_models/deploy_sparse.html
+++ b/docs/how_to/deploy_models/deploy_sparse.html
@@ -456,7 +456,7 @@ a relay graph that we can optimize and deploy.</p>
<span class="n">dummy_input</span> <span class="o">=</span> <span class="n">tf</span><span class="o">.</span><span class="n">keras</span><span class="o">.</span><span class="n">Input</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="n">seq_len</span><span class="p">],</span> <span class="n">batch_size</span><span class="o">=</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">dtype</span> [...]
<span class="n">dummy_out</span> <span class="o">=</span> <span class="n">model</span><span class="p">(</span><span class="n">dummy_input</span><span class="p">)</span> <span class="c1"># Propagate shapes through the keras model.</span>
<span class="k">if</span> <span class="n">report_runtime</span><span class="p">:</span>
- <span class="n">np_input</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">[</span><span class="n">batch_size< [...]
+ <span class="n">np_input</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">[</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">seq_len</span><span class="p">],</span> <span class="n">low</span><span class="o">=</span><span class="mi">0</span><span c [...]
<span class="s2">"int32"</span>
<span class="p">)</span>
<span class="n">start</span> <span class="o">=</span> <span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span>
@@ -538,7 +538,7 @@ tensors instead of sparse aware kernels.</p>
<span class="k">with</span> <span class="n">relay</span><span class="o">.</span><span class="n">build_config</span><span class="p">(</span><span class="n">opt_level</span><span class="o">=</span><span class="mi">3</span><span class="p">):</span>
<span class="n">lib</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">mod</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="n">target</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="n">params</span><span class="p">)</span>
<span class="n">input_shape</span> <span class="o">=</span> <span class="n">shape_dict</span><span class="p">[</span><span class="s2">"input_1"</span><span class="p">]</span>
- <span class="n">dummy_data</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">input_shape</span><span class="p">,</ [...]
+ <span class="n">dummy_data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">input_shape</span><span class="p">,</span> <span class="n">low</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">high</span><span class="o">=</span><span class= [...]
<span class="n">m</span> <span class="o">=</span> <a href="../../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="View documentation for tvm.contrib.graph_executor.GraphModule"><span class="n">graph_executor</span><span class="o">.</span><span class="n">GraphModule</span></a><span class="p">(</span><span class="n">lib</span><span class="p">[</span><span class="s2">"default"</span><span class="p">](</span><span class="n">dev</span><span [...]
<span class="n">m</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">dummy_data</span><span class="p">)</span>
@@ -576,19 +576,19 @@ the rest of the tensor. Once the sparse weights are in BSR format,
<cite>relay.dense</cite> operations with <cite>relay.sparse_dense</cite> calls that can be
run faster.</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">random_bsr_matrix</span><span class="p">(</span><span class="n">M</span><span class="p">,</span> <span class="n">N</span><span class="p">,</span> <span class="n">BS_R</span><span class="p">,</span> <span class="n">BS_C</span><span class="p">,</span> <span class="n">density</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span c [...]
- <span class="n">Y</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.</span><span class="n">zeros</span></a><span class="p">((</span><span class="n">M</span><span class="p">,</span> <span class="n">N</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">)</span>
+ <span class="n">Y</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">M</span><span class="p">,</span> <span class="n">N</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">)</span>
<span class="k">assert</span> <span class="n">M</span> <span class="o">%</span> <span class="n">BS_R</span> <span class="o">==</span> <span class="mi">0</span>
<span class="k">assert</span> <span class="n">N</span> <span class="o">%</span> <span class="n">BS_C</span> <span class="o">==</span> <span class="mi">0</span>
<span class="n">nnz</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">density</span> <span class="o">*</span> <span class="n">M</span> <span class="o">*</span> <span class="n">N</span><span class="p">)</span>
<span class="n">num_blocks</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">nnz</span> <span class="o">/</span> <span class="p">(</span><span class="n">BS_R</span> <span class="o">*</span> <span class="n">BS_C</span><span class="p">))</span> <span class="o">+</span> <span class="mi">1</span>
- <span class="n">candidate_blocks</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.asarray.html#numpy.asarray" title="View documentation for numpy.asarray"><span class="n">np</span><span class="o">.</span><span class="n">asarray</span></a><span class="p">(</span><span class="nb">list</span><span class="p">(</span><span class="n">itertools</span><span class="o">.</span><span class="n">product</span><span class="p">(</span><span class="nb"> [...]
+ <span class="n">candidate_blocks</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">asarray</span><span class="p">(</span><span class="nb">list</span><span class="p">(</span><span class="n">itertools</span><span class="o">.</span><span class="n">product</span><span class="p">(</span><span class="nb">range</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">M</span><span class="p">,</span> <span [...]
<span class="k">assert</span> <span class="n">candidate_blocks</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">==</span> <span class="n">M</span> <span class="o">//</span> <span class="n">BS_R</span> <span class="o">*</span> <span class="n">N</span> <span class="o">//</span> <span class="n">BS_C</span>
<span class="n">chosen_blocks</span> <span class="o">=</span> <span class="n">candidate_blocks</span><span class="p">[</span>
- <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.choice.html#numpy.random.choice" title="View documentation for numpy.random.choice"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">choice</span></a><span class="p">(</span><span class="n">candidate_blocks</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</spa [...]
+ <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">candidate_blocks</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">size</span><span class="o">=</span><span class="n">num_blocks</span><span class="p">,</span> <span class="n">replace</span><span class="o">=</span> [...]
<span class="p">]</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">chosen_blocks</span><span class="p">)):</span>
<span class="n">r</span><span class="p">,</span> <span class="n">c</span> <span class="o">=</span> <span class="n">chosen_blocks</span><span class="p">[</span><span class="n">i</span><span class="p">]</span>
- <span class="n">Y</span><span class="p">[</span><span class="n">r</span> <span class="p">:</span> <span class="n">r</span> <span class="o">+</span> <span class="n">BS_R</span><span class="p">,</span> <span class="n">c</span> <span class="p">:</span> <span class="n">c</span> <span class="o">+</span> <span class="n">BS_C</span><span class="p">]</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uni [...]
+ <span class="n">Y</span><span class="p">[</span><span class="n">r</span> <span class="p">:</span> <span class="n">r</span> <span class="o">+</span> <span class="n">BS_R</span><span class="p">,</span> <span class="n">c</span> <span class="p">:</span> <span class="n">c</span> <span class="o">+</span> <span class="n">BS_C</span><span class="p">]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span [...]
<span class="n">s</span> <span class="o">=</span> <a href="https://docs.scipy.org/doc/scipy-1.8.0/html-scipyorg/reference/generated/scipy.sparse.bsr_matrix.html#scipy.sparse.bsr_matrix" title="View documentation for scipy.sparse.bsr_matrix"><span class="n">sp</span><span class="o">.</span><span class="n">bsr_matrix</span></a><span class="p">(</span><span class="n">Y</span><span class="p">,</span> <span class="n">blocksize</span><span class="o">=</span><span class="p">(</span><span cl [...]
<span class="k">assert</span> <span class="n">s</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">shape</span> <span class="o">==</span> <span class="p">(</span><span class="n">num_blocks</span><span class="p">,</span> <span class="n">BS_R</span><span class="p">,</span> <span class="n">BS_C</span><span class="p">)</span>
<span class="k">assert</span> <span class="n">s</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">size</span> <span class="o">>=</span> <span class="n">nnz</span>
diff --git a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
index 254387f..89762de 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -415,23 +415,24 @@ 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]
- 3%|2 | 3429/132723 [00:00<00:03, 34284.23KB/s]
- 7%|6 | 9221/132723 [00:00<00:02, 48183.38KB/s]
- 13%|#3 | 17510/132723 [00:00<00:01, 64026.44KB/s]
- 20%|#9 | 26061/132723 [00:00<00:01, 72504.40KB/s]
- 26%|##6 | 34648/132723 [00:00<00:01, 77322.07KB/s]
- 33%|###2 | 43158/132723 [00:00<00:01, 79964.48KB/s]
- 39%|###8 | 51713/132723 [00:00<00:00, 81787.95KB/s]
- 45%|####5 | 60298/132723 [00:00<00:00, 83077.59KB/s]
- 52%|#####1 | 68606/132723 [00:00<00:00, 77049.32KB/s]
- 58%|#####8 | 77191/132723 [00:01<00:00, 79619.96KB/s]
- 64%|######4 | 85225/132723 [00:01<00:00, 60282.83KB/s]
- 71%|####### | 93761/132723 [00:01<00:00, 66334.34KB/s]
- 77%|#######7 | 102232/132723 [00:01<00:00, 71044.58KB/s]
- 84%|########3 | 110849/132723 [00:01<00:00, 75098.62KB/s]
- 90%|######### | 119478/132723 [00:01<00:00, 78195.46KB/s]
- 97%|#########6| 128120/132723 [00:01<00:00, 80525.00KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 74132.61KB/s]
+ 4%|4 | 5784/132723 [00:00<00:02, 57824.20KB/s]
+ 10%|# | 13456/132723 [00:00<00:01, 68924.54KB/s]
+ 16%|#6 | 21317/132723 [00:00<00:01, 73343.70KB/s]
+ 22%|##2 | 29258/132723 [00:00<00:01, 75736.20KB/s]
+ 28%|##7 | 37134/132723 [00:00<00:01, 76816.16KB/s]
+ 34%|###3 | 44816/132723 [00:00<00:01, 76465.41KB/s]
+ 40%|###9 | 52463/132723 [00:00<00:01, 76412.72KB/s]
+ 45%|####5 | 60111/132723 [00:00<00:00, 76418.72KB/s]
+ 51%|#####1 | 67754/132723 [00:00<00:00, 76380.90KB/s]
+ 57%|#####6 | 75393/132723 [00:01<00:00, 66557.80KB/s]
+ 62%|######2 | 82636/132723 [00:01<00:00, 68184.47KB/s]
+ 68%|######8 | 90369/132723 [00:01<00:00, 70776.77KB/s]
+ 74%|#######4 | 98288/132723 [00:01<00:00, 66511.84KB/s]
+ 80%|#######9 | 106034/132723 [00:01<00:00, 69491.96KB/s]
+ 86%|########5 | 113970/132723 [00:01<00:00, 72253.90KB/s]
+ 92%|#########1| 121997/132723 [00:01<00:00, 74543.36KB/s]
+ 98%|#########7| 130018/132723 [00:01<00:00, 76184.16KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 72971.63KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -471,7 +472,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
</pre></div>
</div>
<img alt="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" />
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 32.591 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 20.596 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download 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 5d83fac..ef1148d 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -300,16 +300,16 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>11:03.474</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:30.202</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>03:12.191</strong>: <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></li>
-<li><p><strong>02:32.591</strong>: <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></li>
-<li><p><strong>02:01.357</strong>: <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></li>
-<li><p><strong>01:15.693</strong>: <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></li>
-<li><p><strong>01:07.473</strong>: <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></li>
-<li><p><strong>00:30.507</strong>: <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></li>
-<li><p><strong>00:23.429</strong>: <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></li>
-<li><p><strong>00:00.233</strong>: <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></li>
+<li><p><strong>03:05.334</strong>: <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></li>
+<li><p><strong>02:20.596</strong>: <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></li>
+<li><p><strong>01:59.415</strong>: <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></li>
+<li><p><strong>01:12.105</strong>: <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></li>
+<li><p><strong>01:03.532</strong>: <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></li>
+<li><p><strong>00:27.048</strong>: <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></li>
+<li><p><strong>00:21.977</strong>: <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></li>
+<li><p><strong>00:00.195</strong>: <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></li>
</ul>
</div>
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 0eeaa68..220ae95 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -381,10 +381,10 @@ to show that any datatype can be used in the BYODT framework.</p>
<p>Now, we create random inputs to feed into this program using numpy:</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
-<a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.seed.html#numpy.random.seed" title="View documentation for numpy.random.seed"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">seed</span></a><span class="p">(</span><span class="mi">23</span><span class="p">)</span> <span class="c1"># for reproducibility</span>
+<span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">seed</span><span class="p">(</span><span class="mi">23</span><span class="p">)</span> <span class="c1"># for reproducibility</span>
-<span class="n">x_input</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.rand.html#numpy.random.rand" title="View documentation for numpy.random.rand"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span></a><span class="p">(</span><span class="mi">3</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</sp [...]
-<span class="n">y_input</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.rand.html#numpy.random.rand" title="View documentation for numpy.random.rand"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span></a><span class="p">(</span><span class="mi">3</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</sp [...]
+<span class="n">x_input</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">3</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">"float32"</span><span class="p">)</span>
+<span class="n">y_input</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">3</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">"float32"</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x: </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">x_input</span><span class="p">))</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"y: </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">y_input</span><span class="p">))</span>
</pre></div>
@@ -579,16 +579,16 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">real_dst</span> <span class="o">=</span> <span class="n">download_testdata</span><span class="p">(</span><span class="n">url</span><span class="p">,</span> <span class="n">dst</span><span class="p">,</span> <span class="n">module</span><span class="o">=</span><span class="s2">"data"</span><span class="p">)</span>
<span class="n">img</span> <span class="o">=</span> <span class="n">Image</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">real_dst</span><span class="p">)</span><span class="o">.</span><span class="n">resize</span><span class="p">((</span><span class="mi">224</span><span class="p">,</span> <span class="mi">224</span><span class="p">))</span>
<span class="c1"># CoreML's standard model image format is BGR</span>
- <span class="n">img_bgr</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">img</span><span class="p">)[:,</span> <span class="p">:,</span> <span class="p">::</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
- <span class="n">img</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.transpose.html#numpy.transpose" title="View documentation for numpy.transpose"><span class="n">np</span><span class="o">.</span><span class="n">transpose</span></a><span class="p">(</span><span class="n">img_bgr</span><span class="p">,</span> <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span [...]
- <span class="k">return</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.asarray.html#numpy.asarray" title="View documentation for numpy.asarray"><span class="n">np</span><span class="o">.</span><span class="n">asarray</span></a><span class="p">(</span><span class="n">img</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="s2">"float32"</span><span class="p">)</span>
+ <span class="n">img_bgr</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">img</span><span class="p">)[:,</span> <span class="p">:,</span> <span class="p">::</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
+ <span class="n">img</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">transpose</span><span class="p">(</span><span class="n">img_bgr</span><span class="p">,</span> <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">))[</span><span class="n">np</span><span class="o">.</span><span class="n">newaxis</span><span class="p">,</spa [...]
+ <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">asarray</span><span class="p">(</span><span class="n">img</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="s2">"float32"</span><span class="p">)</span>
<span class="n">module</span><span class="p">,</span> <span class="n">params</span> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip59767a97-0ad8-4929-badf-08459abfeb60 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.zip5ae111cf-f869-4d47-beea-9eb16a4ed0aa 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>
@@ -739,7 +739,7 @@ where the minimum representable custom datatype value is implemented using calls
<span class="c1"># Again, note that the output using 32-bit myfloat exactly the same as 32-bit floats,</span>
<span class="c1"># because myfloat is exactly a float!</span>
-<a href="https://numpy.org/doc/stable/reference/generated/numpy.testing.assert_array_equal.html#numpy.testing.assert_array_equal" title="View documentation for numpy.testing.assert_array_equal"><span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_array_equal</span></a><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="n">result_myfloat</span><span class="p">)</span>
+<span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_array_equal</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="n">result_myfloat</span><span class="p">)</span>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
diff --git a/docs/how_to/extend_tvm/low_level_custom_pass.html b/docs/how_to/extend_tvm/low_level_custom_pass.html
index 7d6d5c7..550230f 100644
--- a/docs/how_to/extend_tvm/low_level_custom_pass.html
+++ b/docs/how_to/extend_tvm/low_level_custom_pass.html
@@ -375,8 +375,8 @@ our customized lowering pass to manipulate the IR directly instead of using sche
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@main = primfn(a_1: handle, b_1: handle, c_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {c: Buffer(c_2: Pointer(float32), float32, [128], []),
- a: Buffer(a_2: Pointer(float32), float32, [128], []),
+ buffers = {a: Buffer(a_2: Pointer(float32), float32, [128], []),
+ c: Buffer(c_2: Pointer(float32), float32, [128], []),
b: Buffer(b_2: Pointer(float32), float32, [128], [])}
buffer_map = {a_1: a, b_1: b, c_1: c} {
for (i: int32, 0, 128) {
@@ -484,8 +484,8 @@ called after each phase is done.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@main = primfn(a_1: handle, b_1: handle, c_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {c: Buffer(c_2: Pointer(float32), float32, [128], []),
- a: Buffer(a_2: Pointer(float32), float32, [128], []),
+ buffers = {a: Buffer(a_2: Pointer(float32), float32, [128], []),
+ c: Buffer(c_2: Pointer(float32), float32, [128], []),
b: Buffer(b_2: Pointer(float32), float32, [128], [])}
buffer_map = {a_1: a, b_1: b, c_1: c} {
for (i.outer: int32, 0, 16) {
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index b0def19..94faae0 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -300,12 +300,12 @@
<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>00:38.832</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:37.861</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:35.231</strong>: <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></li>
-<li><p><strong>00:02.301</strong>: <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></li>
-<li><p><strong>00:01.090</strong>: <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></li>
-<li><p><strong>00:00.211</strong>: <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></li>
+<li><p><strong>00:34.387</strong>: <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></li>
+<li><p><strong>00:02.238</strong>: <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></li>
+<li><p><strong>00:01.035</strong>: <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></li>
+<li><p><strong>00:00.201</strong>: <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></li>
</ul>
</div>
diff --git a/docs/how_to/extend_tvm/use_pass_infra.html b/docs/how_to/extend_tvm/use_pass_infra.html
index 212ca47..2dd2d51 100644
--- a/docs/how_to/extend_tvm/use_pass_infra.html
+++ b/docs/how_to/extend_tvm/use_pass_infra.html
@@ -365,7 +365,7 @@ will be used by various optimizations of the examples in this tutorial.
Similarly, users can write a tir primitive function and apply the tir passes.</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">example</span><span class="p">():</span>
<span class="n">shape</span> <span class="o">=</span> <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">64</span><span class="p">,</span> <span class="mi">54</span><span class="p">,</span> <span class="mi">54</span><span class="p">)</span>
- <span class="n">c_data</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.empty.html#numpy.empty" title="View documentation for numpy.empty"><span class="n">np</span><span class="o">.</span><span class="n">empty</span></a><span class="p">(</span><span class="n">shape</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">"float32"</span><span class="p">)</span>
+ <span class="n">c_data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">empty</span><span class="p">(</span><span class="n">shape</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">"float32"</span><span class="p">)</span>
<span class="n">c</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">const</span><span class="p">(</span><span class="n">c_data</span><span class="p">)</span>
<span class="n">weight</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">var</span><span class="p">(</span><span class="s2">"weight"</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="mi">64</span><span class="p">,</span> <span class="mi">64</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">3</span><span class [...]
<span class="n">x</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">var</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <span class="n">relay</span><span class="o">.</span><span class="n">TensorType</span><span class="p">((</span><span class="mi">1</span><span class="p">,</span> <span class="mi">64</span><span class="p">,</span> <span class="mi">56</span><span class="p">,</span> <span class= [...]
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index adc165b..58499e9 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -486,10 +486,10 @@ profile the execution time of each passes.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6184us [6184us] (44.54%; 44.54%)
-FoldScaleAxis: 7700us [2us] (55.46%; 55.46%)
- FoldConstant: 7698us [1637us] (55.44%; 99.97%)
- InferType: 6061us [6061us] (43.65%; 78.73%)
+InferType: 5947us [5947us] (45.45%; 45.45%)
+FoldScaleAxis: 7137us [2us] (54.55%; 54.55%)
+ FoldConstant: 7135us [1499us] (54.53%; 99.97%)
+ InferType: 5636us [5636us] (43.07%; 78.98%)
</pre></div>
</div>
</div>
@@ -512,10 +512,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 5808us [5808us] (44.75%; 44.75%)
-FoldScaleAxis: 7172us [2us] (55.25%; 55.25%)
- FoldConstant: 7169us [1502us] (55.24%; 99.97%)
- InferType: 5667us [5667us] (43.66%; 79.04%)
+InferType: 5707us [5707us] (44.45%; 44.45%)
+FoldScaleAxis: 7132us [2us] (55.55%; 55.55%)
+ FoldConstant: 7131us [1488us] (55.54%; 99.98%)
+ InferType: 5643us [5643us] (43.95%; 79.14%)
</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 b884f18..3bc44be 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -523,18 +523,18 @@ coopertively fetch dependent data from global memory.</p>
latency of convolution.</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">func</span> <span class="o">=</span> <a href="../../reference/api/python/driver.html#tvm.build" title="View documentation for tvm.build"><span class="n">tvm</span><span class="o">.</span><span class="n">build</span></a><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="p">[</span><span class="n">A</span><span class="p">,</span> <span class="n">W</span><sp [...]
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">cuda</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
-<span class="n">a_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">in_size</span><span cla [...]
-<span class="n">w_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">kernel</span><span clas [...]
+<span class="n">a_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">in_size</span><span class="p">,</span> <span class="n">in_size</span><span class="p">,</span> <span class="n">in_channel</span><span class="p">,</span> <span class="n">batch</span><span class= [...]
+<span class="n">w_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">kernel</span><span class="p">,</span> <span class="n">kernel</span><span class="p">,</span> <span class="n">in_channel</span><span class="p">,</span> <span class="n">out_channel</span><span cl [...]
<span class="n">a</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">a_np</span><span class="p">,</span> <span class="n">dev</span><span class="p">)</span>
<span class="n">w</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">w_np</span><span class="p">,</span> <span class="n">dev</span><span class="p">)</span>
-<span class="n">b</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.</span> [...]
+<span class="n">b</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">out_size</span><span class="p">,</span> <span class="n">out_si [...]
<span class="n">func</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="n">evaluator</span> <span class="o">=</span> <span class="n">func</span><span class="o">.</span><span class="n">time_evaluator</span><span class="p">(</span><span class="n">func</span><span class="o">.</span><span class="n">entry_name</span><span class="p">,</span> <span class="n">dev</span><span class="p">,</span> <span class="n">number</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<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>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 37.199587 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 39.902019 ms
</pre></div>
</div>
<div class="sphx-glr-footer class 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 be4dc76..b204090 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -684,8 +684,8 @@ The only thing we should do is to make sure all threads in a warp can call Tenso
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@main = primfn(A_1: handle, W_1: handle, Conv_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {Conv: Buffer(Conv_2: Pointer(float32), float32, [25690112], []),
- A: Buffer(A_2: Pointer(float16), float16, [12845056], []),
+ buffers = {A: Buffer(A_2: Pointer(float16), float16, [12845056], []),
+ Conv: Buffer(Conv_2: Pointer(float32), float32, [25690112], []),
W: Buffer(W_2: Pointer(float16), float16, [1179648], [])}
buffer_map = {A_1: A, W_1: W, Conv_1: Conv} {
attr [IterVar(blockIdx.z: int32, (nullptr), "ThreadIndex", "blockIdx.z")] "thread_extent" = 196;
@@ -866,17 +866,17 @@ be able to run on our build server</p>
<span class="k">if</span> <a href="../../reference/api/python/contrib.html#tvm.contrib.nvcc.have_tensorcore" title="View documentation for tvm.contrib.nvcc.have_tensorcore"><span class="n">nvcc</span><span class="o">.</span><span class="n">have_tensorcore</span></a><span class="p">(</span><span class="n">dev</span><span class="o">.</span><span class="n">compute_version</span><span class="p">):</span>
<span class="k">with</span> <a href="../../reference/api/python/ir.html#tvm.transform.PassContext" title="View documentation for tvm.transform.PassContext"><span class="n">tvm</span><span class="o">.</span><span class="n">transform</span><span class="o">.</span><span class="n">PassContext</span></a><span class="p">(</span><span class="n">config</span><span class="o">=</span><span class="p">{</span><span class="s2">"tir.UnrollLoop"</span><span class="p">:</span> <span class= [...]
<span class="n">func</span> <span class="o">=</span> <a href="../../reference/api/python/driver.html#tvm.build" title="View documentation for tvm.build"><span class="n">tvm</span><span class="o">.</span><span class="n">build</span></a><span class="p">(</span><span class="n">s</span><span class="p">,</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">Conv</span><span class="p">],</span> < [...]
- <span class="n">a_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">data_shape</span><span class="p">)</span><s [...]
- <span class="n">w_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">kernel_shape</span><span class="p">)</span> [...]
+ <span class="n">a_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">data_shape</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">A</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span>
+ <span class="n">w_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">kernel_shape</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">W</span><span class="o">.</span><span class="n">dtype</span><span class="p"> [...]
<span class="n">a</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">a_np</span><span class="p">,</span> <span class="n">dev</span><span class="p">)</span>
<span class="n">w</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">w_np</span><span class="p">,</span> <span class="n">dev</span><span class="p">)</span>
- <span class="n">c</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.</s [...]
+ <span class="n">c</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">output_shape</span><span class="p">,</span> <span class="n" [...]
<span class="n">evaluator</span> <span class="o">=</span> <span class="n">func</span><span class="o">.</span><span class="n">time_evaluator</span><span class="p">(</span><span class="n">func</span><span class="o">.</span><span class="n">entry_name</span><span class="p">,</span> <span class="n">dev</span><span class="p">,</span> <span class="n">number</span><span class="o">=</span><span class="mi">10</span><span class="p">)</span>
<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>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 10.582005 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 10.024482 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 b6d68e4..b8a99d3 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -392,8 +392,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="n">target</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
<span class="c1"># Random generated tensor for testing</span>
-<span class="n">a</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.rand.html#numpy.random.rand" title="View documentation for numpy.random.rand"><span class="n">numpy</s [...]
-<span class="n">b</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.rand.html#numpy.random.rand" title="View documentation for numpy.random.rand"><span class="n">numpy</s [...]
+<span class="n">a</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">numpy</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="n">M</span> [...]
+<span class="n">b</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">numpy</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="n">K</span> [...]
<span class="n">np_repeat</span> <span class="o">=</span> <span class="mi">100</span>
<span class="n">np_runing_time</span> <span class="o">=</span> <span class="n">timeit</span><span class="o">.</span><span class="n">timeit</span><span class="p">(</span>
@@ -409,7 +409,7 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Numpy running time: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><span class="n">np_runing_time</span> <span class="o">/</span> <span class="n">np_repeat</span><span class="p">))</span>
-<span class="n">answer</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.dot.html#numpy.dot" title="View documentation for numpy.dot"><span class="n">numpy</span><span class="o">.</span><span class="n">dot</span></a><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>
+<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>
<span class="c1"># Algorithm</span>
<span class="n">k</span> <span class="o">=</span> <a href="../../reference/api/python/te.html#tvm.te.reduce_axis" title="View documentation for tvm.te.reduce_axis"><span class="n">te</span><span class="o">.</span><span class="n">reduce_axis</span></a><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">K</span><span class="p">),</span> <span class="s2">"k"</span><span class="p">)</span>
@@ -422,7 +422,7 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="n">func</span> <span class="o">=</span> <a href="../../reference/api/python/driver.html#tvm.build" title="View documentation for tvm.build"><span class="n">tvm</span><span class="o">.</span><span class="n">build</span></a><span class="p">(</span><span class="n">s</span><span class="p">,</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= [...]
<span class="k">assert</span> <span class="n">func</span>
-<span class="n">c</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">numpy</span><span class="o">.</sp [...]
+<span class="n">c</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">numpy</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">M</span><span class="p">,</span> <span class="n">N</span><s [...]
<span class="n">func</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="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">answer</span><span class="p">,</span> <span class="n">rtol</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">)</span>
@@ -431,8 +431,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019487
-Baseline: 3.498123
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017994
+Baseline: 3.368371
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -482,7 +482,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="n">func</span> <span class="o">=</span> <a href="../../reference/api/python/driver.html#tvm.build" title="View documentation for tvm.build"><span class="n">tvm</span><span class="o">.</span><span class="n">build</span></a><span class="p">(</span><span class="n">s</span><span class="p">,</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= [...]
<span class="k">assert</span> <span class="n">func</span>
-<span class="n">c</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">numpy</span><span class="o">.</sp [...]
+<span class="n">c</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">numpy</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">M</span><span class="p">,</span> <span class="n">N</span><s [...]
<span class="n">func</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="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">answer</span><span class="p">,</span> <span class="n">rtol</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">)</span>
@@ -493,7 +493,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.329103
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.299226
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -552,7 +552,7 @@ vastly.</p>
<span class="n">func</span> <span class="o">=</span> <a href="../../reference/api/python/driver.html#tvm.build" title="View documentation for tvm.build"><span class="n">tvm</span><span class="o">.</span><span class="n">build</span></a><span class="p">(</span><span class="n">s</span><span class="p">,</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= [...]
<span class="k">assert</span> <span class="n">func</span>
-<span class="n">c</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">numpy</span><span class="o">.</sp [...]
+<span class="n">c</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">numpy</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">M</span><span class="p">,</span> <span class="n">N</span><s [...]
<span class="n">func</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="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">answer</span><span class="p">,</span> <span class="n">rtol</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">)</span>
@@ -561,7 +561,7 @@ vastly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.354727
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.334333
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -614,7 +614,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="n">func</span> <span class="o">=</span> <a href="../../reference/api/python/driver.html#tvm.build" title="View documentation for tvm.build"><span class="n">tvm</span><span class="o">.</span><span class="n">build</span></a><span class="p">(</span><span class="n">s</span><span class="p">,</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= [...]
<span class="k">assert</span> <span class="n">func</span>
-<span class="n">c</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">numpy</span><span class="o">.</sp [...]
+<span class="n">c</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">numpy</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">M</span><span class="p">,</span> <span class="n">N</span><s [...]
<span class="n">func</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="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">answer</span><span class="p">,</span> <span class="n">rtol</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">)</span>
@@ -623,7 +623,7 @@ the access pattern for A matrix is more cache friendly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.148588
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.115858
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -698,7 +698,7 @@ flattening.</p>
<span class="n">func</span> <span class="o">=</span> <a href="../../reference/api/python/driver.html#tvm.build" title="View documentation for tvm.build"><span class="n">tvm</span><span class="o">.</span><span class="n">build</span></a><span class="p">(</span><span class="n">s</span><span class="p">,</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= [...]
<span class="k">assert</span> <span class="n">func</span>
-<span class="n">c</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">numpy</span><span class="o">.</sp [...]
+<span class="n">c</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">numpy</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">M</span><span class="p">,</span> <span class="n">N</span><s [...]
<span class="n">func</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="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">answer</span><span class="p">,</span> <span class="n">rtol</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">)</span>
@@ -707,7 +707,7 @@ flattening.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111834
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110707
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -785,7 +785,7 @@ write to C when all the block results are ready.</p>
<span class="n">func</span> <span class="o">=</span> <a href="../../reference/api/python/driver.html#tvm.build" title="View documentation for tvm.build"><span class="n">tvm</span><span class="o">.</span><span class="n">build</span></a><span class="p">(</span><span class="n">s</span><span class="p">,</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= [...]
<span class="k">assert</span> <span class="n">func</span>
-<span class="n">c</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">numpy</span><span class="o">.</sp [...]
+<span class="n">c</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">numpy</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">M</span><span class="p">,</span> <span class="n">N</span><s [...]
<span class="n">func</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="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">answer</span><span class="p">,</span> <span class="n">rtol</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">)</span>
@@ -794,7 +794,7 @@ write to C when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.112383
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111014
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -875,7 +875,7 @@ write to C when all the block results are ready.</p>
<span class="n">func</span> <span class="o">=</span> <a href="../../reference/api/python/driver.html#tvm.build" title="View documentation for tvm.build"><span class="n">tvm</span><span class="o">.</span><span class="n">build</span></a><span class="p">(</span><span class="n">s</span><span class="p">,</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= [...]
<span class="k">assert</span> <span class="n">func</span>
-<span class="n">c</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">numpy</span><span class="o">.</sp [...]
+<span class="n">c</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">numpy</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">M</span><span class="p">,</span> <span class="n">N</span><s [...]
<span class="n">func</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="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">answer</span><span class="p">,</span> <span class="n">rtol</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">)</span>
@@ -885,7 +885,7 @@ write to C when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.148875
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144690
</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 e8388ba..08580af 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -300,11 +300,11 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:36.534</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.799</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:33.806</strong>: <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></li>
-<li><p><strong>00:01.512</strong>: <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></li>
-<li><p><strong>00:01.217</strong>: <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></li>
+<li><p><strong>00:32.190</strong>: <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></li>
+<li><p><strong>00:01.438</strong>: <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></li>
+<li><p><strong>00:01.171</strong>: <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></li>
</ul>
</div>
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 439ca8d..0163c0e 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -300,14 +300,14 @@
<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>04:56.995</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>04:53.221</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:21.763</strong>: <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></li>
-<li><p><strong>01:20.596</strong>: <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></li>
-<li><p><strong>00:40.553</strong>: <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></li>
-<li><p><strong>00:16.852</strong>: <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></li>
-<li><p><strong>00:08.749</strong>: <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></li>
-<li><p><strong>00:08.482</strong>: <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></li>
+<li><p><strong>02:20.441</strong>: <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></li>
+<li><p><strong>01:19.767</strong>: <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></li>
+<li><p><strong>00:40.193</strong>: <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></li>
+<li><p><strong>00:15.743</strong>: <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></li>
+<li><p><strong>00:08.728</strong>: <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></li>
+<li><p><strong>00:08.348</strong>: <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></li>
</ul>
</div>
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 9b8f305..da0ee79 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
@@ -464,217 +464,42 @@ cooperative fetching, unrolling and operator fusion.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Lowered TIR:
@main = primfn(data_1: handle, kernel_1: handle, bias_1: handle, compute_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {compute: Buffer(compute_2: Pointer(float32), float32, [25088], []),
+ buffers = {data: Buffer(data_2: Pointer(float32), float32, [25088], []),
+ compute: Buffer(compute_2: Pointer(float32), float32, [25088], []),
bias: Buffer(bias_2: Pointer(float32), float32, [512], []),
- data: Buffer(data_2: Pointer(float32), float32, [25088], []),
kernel: Buffer(kernel_2: Pointer(float32), float32, [2359296], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 56;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
allocate(conv2d_nchw: Pointer(local float32), float32, [2]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [216]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [768]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
conv2d_nchw_1[1] = 0f32
for (rc.outer.outer: int32, 0, 64) {
- let cse_var_1: int32 = (rc.outer.outer*72)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- if @tir.likely((threadIdx.x_1 < 216), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [216], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[((((((rc.outer.outer*392) + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7) [...]
+ for (ry.outer.outer: int32, 0, 3) {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ for (ax0.ax1.fused.ax2.fused.ax3.fused.inner.s: int32, 0, 6) {
+ if @tir.likely((threadIdx.x_1 < 12), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[((threadIdx.x_1*6) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s), 9))) && (floormod(((threadIdx.x_1*6) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s), 9) [...]
+ }
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 28), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 84), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 140), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 168), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 196), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 224), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 280), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 308), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 336), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 364), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 392), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 420), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 448), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 476), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 532), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 560), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 7) {
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 16)) < 48), dtype=bool) {
+ kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*112) + threadIdx.x_2)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*14) + floordiv(threadIdx.x_2, 8)), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*112) + threadIdx.x_2), 24), 3)*9)) + (ry.outer.outer*3)) + floormod(((ax0.ax1.fu [...]
+ }
+ }
+ for (rc.outer.inner: int32, 0, 8) {
+ for (rx.outer.inner: int32, 0, 3) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + rx.outer.inner) + 384)]))
+ }
}
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2304)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2305)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2306)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2307)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2308)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2309)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2310)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2311)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2312)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2313)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2314)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2315)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 30)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 30)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2316)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 31)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 31)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2317)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 32)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 32)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2318)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 33)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 33)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2319)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 34)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 34)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2320)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 35)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 35)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2321)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2322)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2323)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2324)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 57)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 57)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2325)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 58)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 58)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2326)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 59)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 59)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2327)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 60)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 60)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2328)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 61)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 61)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2329)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 62)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 62)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2330)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2331)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2332)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2333)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2334)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2335)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2336)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2337)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2338)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 89)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 89)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2339)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2340)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2341)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2342)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 111)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 111)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2343)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 112)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 112)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2344)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 113)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 113)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2345)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 114)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 114)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2346)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 115)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 115)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2347)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 116)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 116)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2348)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2349)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2350)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2351)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 138)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 138)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2352)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 139)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 139)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2353)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2354)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 141)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 141)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2355)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 142)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 142)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2356)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 143)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 143)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2357)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2358)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2359)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2360)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2361)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2362)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2363)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2364)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2365)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 170)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 170)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2366)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2367)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2368)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2369)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2370)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2371)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2372)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2373)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2374)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2375)]))
}
}
- compute[(((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*7)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*64) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*7)) + floormod(blockIdx.x, 7)) + 1568)] = max((conv2d_nchw_1[1] + bias[(((floordiv(blockIdx.x, 7)*64) + floordiv(threadIdx.x, 7)) + 32)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (floordiv(threadIdx.x, 7)*49)) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*32) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*1568) + (floordiv(threadIdx.x, 7)*49)) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x, 7)) + 784)] = max((conv2d_nchw_1[1] + bias[(((floordiv(blockIdx.x, 7)*32) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
}
}
</pre></div>
@@ -686,11 +511,11 @@ cooperative fetching, unrolling and operator fusion.</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">func</span> <span class="o">=</span> <a href="../../reference/api/python/driver.html#tvm.build" title="View documentation for tvm.build"><span class="n">tvm</span><span class="o">.</span><span class="n">build</span></a><span class="p">(</span><span class="n">sch</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">target</span><span class="p">)</span>
<span class="c1"># Check correctness</span>
-<span class="n">data_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">N</span><span class= [...]
-<span class="n">weight_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">CO</span><span cla [...]
-<span class="n">bias_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="mi">1</span><span class [...]
+<span class="n">data_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">N</span><span class="p">,</span> <span class="n">CI</span><span class="p">,</span> <span class="n">H</span><span class="p">,</span> <span class="n">W</span><span class="p">))</span><span cl [...]
+<span class="n">weight_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">CO</span><span class="p">,</span> <span class="n">CI</span><span class="p">,</span> <span class="n">KH</span><span class="p">,</span> <span class="n">KW</span><span class="p">))</span><sp [...]
+<span class="n">bias_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">CO</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">))</span><span [...]
<span class="n">conv_np</span> <span class="o">=</span> <span class="n">conv2d_nchw_python</span><span class="p">(</span><span class="n">data_np</span><span class="p">,</span> <span class="n">weight_np</span><span class="p">,</span> <span class="n">strides</span><span class="p">,</span> <span class="n">padding</span><span class="p">)</span>
-<span class="n">out_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.maximum.html#numpy.maximum" title="View documentation for numpy.maximum"><span class="n">np</span><span class="o">.</span><span class="n">maximum</span></a><span class="p">(</span><span class="n">conv_np</span> <span class="o">+</span> <span class="n">bias_np</span><span class="p">,</span> <span class="mf">0.0</span><span class="p">)</span>
+<span class="n">out_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">maximum</span><span class="p">(</span><span class="n">conv_np</span> <span class="o">+</span> <span class="n">bias_np</span><span class="p">,</span> <span class="mf">0.0</span><span class="p">)</span>
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">cuda</span><span class="p">()</span>
<span class="n">data_tvm</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">data_np</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="n">dev</span><span class="p">)</span>
@@ -700,18 +525,18 @@ cooperative fetching, unrolling and operator fusion.</p>
<span class="n">func</span><span class="p">(</span><span class="n">data_tvm</span><span class="p">,</span> <span class="n">weight_tvm</span><span class="p">,</span> <span class="n">bias_tvm</span><span class="p">,</span> <span class="n">out_tvm</span><span class="p">)</span>
<span class="c1"># Check results</span>
-<a href="https://numpy.org/doc/stable/reference/generated/numpy.testing.assert_allclose.html#numpy.testing.assert_allclose" title="View documentation for numpy.testing.assert_allclose"><span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span></a><span class="p">(</span><span class="n">out_np</span><span class="p">,</span> <span class="n">out_tvm</span><span class="o">.</span><span class="n">numpy</span><s [...]
+<span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">out_np</span><span class="p">,</span> <span class="n">out_tvm</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">rtol</span><span class="o">=</span><span class="mf">1e-3</span><span class="p">)</span>
<span class="c1"># Evaluate execution time</span>
<span class="n">evaluator</span> <span class="o">=</span> <span class="n">func</span><span class="o">.</span><span class="n">time_evaluator</span><span class="p">(</span><span class="n">func</span><span class="o">.</span><span class="n">entry_name</span><span class="p">,</span> <span class="n">dev</span><span class="p">,</span> <span class="n">min_repeat_ms</span><span class="o">=</span><span class="mi">500</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span>
<span class="s2">"Execution time of this operator: </span><span class="si">%.3f</span><span class="s2"> ms"</span>
- <span class="o">%</span> <span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.median.html#numpy.median" title="View documentation for numpy.median"><span class="n">np</span><span class="o">.</span><span class="n">median</span></a><span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">data_tvm</span><span class="p">,</span> <span class="n">weight_tvm</span><span class="p">,</span> <span class="n">bias_tvm</spa [...]
+ <span class="o">%</span> <span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">median</span><span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">data_tvm</span><span class="p">,</span> <span class="n">weight_tvm</span><span class="p">,</span> <span class="n">bias_tvm</span><span class="p">,</span> <span class="n">out_tvm</span><span class="p">)</span><span class="o">.</span><span class="n">results</span><sp [...]
<span class="p">)</span>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.333 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.395 ms
</pre></div>
</div>
</div>
@@ -743,34 +568,34 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=32)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -790,14 +615,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=6)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 0)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -815,188 +640,36 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[2];
- __shared__ float pad_temp_shared[216];
- __shared__ float kernel_shared[4608];
+ __shared__ float pad_temp_shared[72];
+ __shared__ float kernel_shared[768];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 216) {
- pad_temp_shared[((int)threadIdx.x)] = (((((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1568) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2240) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2464) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2688) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2912) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3136) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3360) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3584) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3808) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4256) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
- if (((int)threadIdx.x) < 128) {
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4480) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ for (int ax0_ax1_fused_ax2_fused_ax3_fused_inner_s = 0; ax0_ax1_fused_ax2_fused_ax3_fused_inner_s < 6; ++ax0_ax1_fused_ax2_fused_ax3_fused_inner_s) {
+ if (((int)threadIdx.x) < 12) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s) % 9))) && ((((((int)threadIdx.x) * 6) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + (ax0_ax [...]
+ }
+ }
+ for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 7; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 4)) < 48) {
+ kernel_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 112) + ((int)threadIdx.x))] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 14) + (((int)threadIdx.x) >> 3)) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 112) + ((int)threadIdx.x)) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 112) + ((int)threadIdx.x)) % 3))];
+ }
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
+ for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + rx_outer_inner) + 384)]));
+ }
+ }
}
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2304)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2305)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2306)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2307)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2308)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2309)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2310)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2311)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2312)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2313)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2314)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2315)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 30)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 30)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2316)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 31)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 31)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2317)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 32)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 32)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2318)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 33)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 33)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2319)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 34)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 34)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2320)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 35)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 35)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2321)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2322)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2323)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2324)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 57)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 57)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2325)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 58)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 58)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2326)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 59)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 59)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2327)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 60)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 60)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2328)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 61)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 61)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2329)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 62)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 62)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2330)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2331)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2332)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2333)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2334)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2335)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2336)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2337)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2338)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 89)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 89)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2339)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2340)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2341)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2342)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 111)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 111)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2343)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 112)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 112)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2344)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 113)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 113)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2345)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 114)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 114)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2346)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 115)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 115)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2347)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 116)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 116)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2348)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2349)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2350)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2351)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 138)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 138)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2352)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 139)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 139)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2353)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 140)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 140)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2354)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 141)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 141)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2355)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 142)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 142)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2356)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 143)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 143)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2357)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2358)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2359)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2360)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2361)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2362)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2363)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2364)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2365)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 170)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 170)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2366)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2367)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2368)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2369)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2370)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2371)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2372)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2373)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2374)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2375)]));
}
- compute[((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 7)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 7)) + (((int)blockIdx.x) % 7)) + 1568)] = max((conv2d_nchw[1] + bias[((((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) / 7)) + 32)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7)) + 784)] = max((conv2d_nchw[1] + bias[((((((int)blockIdx.x) / 7) * 32) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
}
</pre></div>
</div>
@@ -1033,7 +706,7 @@ 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> ( 2 minutes 21.763 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 20.441 seconds)</p>
<div class="sphx-glr-footer class 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 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_arm.html b/docs/how_to/tune_with_autoscheduler/tune_network_arm.html
index 8234814..87e9f0f 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_arm.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_arm.html
@@ -836,7 +836,7 @@ so we can read the log file and load the best schedules.</p>
<span class="c1"># Create graph executor</span>
<span class="n">dev</span> <span class="o">=</span> <span class="n">remote</span><span class="o">.</span><span class="n">cpu</span><span class="p">()</span>
<span class="n">module</span> <span class="o">=</span> <a href="../../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="View documentation for tvm.contrib.graph_executor.GraphModule"><span class="n">graph_executor</span><span class="o">.</span><span class="n">GraphModule</span></a><span class="p">(</span><span class="n">rlib</span><span class="p">[</span><span class="s2">"default"</span><span class="p">](</span><span class="n">dev</span [...]
- <span class="n">data_tvm</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">((</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><sp [...]
+ <span class="n">data_tvm</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">((</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class= [...]
<span class="n">module</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="s2">"data"</span><span class="p">,</span> <span class="n">data_tvm</span><span class="p">)</span>
<span class="c1"># Evaluate</span>
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 3c26fe9..9416026 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -863,7 +863,7 @@ so we can read the log file and load the best schedules.</p>
<span class="c1"># Create graph executor</span>
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">target</span><span class="p">),</span> <span class="mi">0</span><span class="p">)</span>
<span class="n">module</span> <span class="o">=</span> <a href="../../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="View documentation for tvm.contrib.graph_executor.GraphModule"><span class="n">graph_executor</span><span class="o">.</span><span class="n">GraphModule</span></a><span class="p">(</span><span class="n">lib</span><span class="p">[</span><span class="s2">"default"</span><span class="p">](</span><span class="n">dev</span><spa [...]
-<span class="n">data_tvm</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">((</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span c [...]
+<span class="n">data_tvm</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">((</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n"> [...]
<span class="n">module</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="s2">"data"</span><span class="p">,</span> <span class="n">data_tvm</span><span class="p">)</span>
<span class="c1"># Evaluate</span>
@@ -876,7 +876,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.9322 9.9368 9.9573 9.9026 0.0226
+ 10.0901 10.0769 10.1200 10.0735 0.0212
</pre></div>
</div>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_mali.html b/docs/how_to/tune_with_autoscheduler/tune_network_mali.html
index 6ab599a..2b8db11 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_mali.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_mali.html
@@ -764,7 +764,7 @@ and do more analyses later.</p></li>
<span class="n">remote</span><span class="o">.</span><span class="n">upload</span><span class="p">(</span><span class="n">path_lib</span><span class="p">)</span>
<span class="n">loaded_lib</span> <span class="o">=</span> <span class="n">remote</span><span class="o">.</span><span class="n">load_module</span><span class="p">(</span><span class="n">filename</span><span class="p">)</span>
<span class="n">module</span> <span class="o">=</span> <a href="../../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="View documentation for tvm.contrib.graph_executor.GraphModule"><span class="n">graph_executor</span><span class="o">.</span><span class="n">GraphModule</span></a><span class="p">(</span><span class="n">loaded_lib</span><span class="p">[</span><span class="s2">"default"</span><span class="p">](</span><span class="n">dev [...]
- <span class="n">data</span> <span class="o">=</span> <span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">input_shape</span>< [...]
+ <span class="n">data</span> <span class="o">=</span> <span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">input_shape</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">dtype</span><span class="p">)</span>
<span class="n">data_tvm</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">data</span><span class="p">)</span>
<span class="n">module</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="s2">"data"</span><span class="p">,</span> <span class="n">data_tvm</span><span class="p">)</span>
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 4e015e5..2fa4113 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -882,7 +882,7 @@ so we can read the log file and load the best schedules.</p>
<span class="c1"># Create graph executor</span>
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">target</span><span class="p">),</span> <span class="mi">0</span><span class="p">)</span>
<span class="n">module</span> <span class="o">=</span> <a href="../../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="View documentation for tvm.contrib.graph_executor.GraphModule"><span class="n">graph_executor</span><span class="o">.</span><span class="n">GraphModule</span></a><span class="p">(</span><span class="n">lib</span><span class="p">[</span><span class="s2">"default"</span><span class="p">](</span><span class="n">dev</span><spa [...]
-<span class="n">data_tvm</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">((</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span c [...]
+<span class="n">data_tvm</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">((</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n"> [...]
<span class="n">module</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="s2">"data"</span><span class="p">,</span> <span class="n">data_tvm</span><span class="p">)</span>
<span class="c1"># Evaluate</span>
@@ -895,7 +895,7 @@ 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)
- 771.1824 773.7858 774.1353 765.6259 3.9316
+ 763.3909 764.9626 768.9731 756.2370 5.3169
</pre></div>
</div>
</div>
@@ -917,7 +917,7 @@ 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 20.596 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.767 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download 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 19a42fb..24543b5 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -401,14 +401,14 @@ See the <cite>tvm.auto_scheduler.measure.py</cite> for more details.</p>
<span class="n">density</span> <span class="o">=</span> <span class="mf">0.6</span>
<span class="c1"># Generate the test data with numpy</span>
-<span class="n">X_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.randn.html#numpy.random.randn" title="View documentation for numpy.random.randn"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randn</span></a><span class="p">(</span><span class="n">M</span><span class="p">,</span> <span class="n">K</span><span class="p">)</span><span class="o">.</span>< [...]
-<span class="n">X_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.maximum.html#numpy.maximum" title="View documentation for numpy.maximum"><span class="n">np</span><span class="o">.</span><span class="n">maximum</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.</span><span class="n" [...]
+<span class="n">X_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randn</span><span class="p">(</span><span class="n">M</span><span class="p">,</span> <span class="n">K</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">"float32"</span><span class="p">)</span>
+<span class="n">X_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">maximum</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">M</span><span class="p">,</span> <span class="n">K</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="s2">"float32"</span><span class="p">),</span> <span class="n [...]
<span class="n">W_sp_np</span> <span class="o">=</span> <span class="n">random_bsr_matrix</span><span class="p">(</span><span class="n">N</span><span class="p">,</span> <span class="n">K</span><span class="p">,</span> <span class="n">BS_R</span><span class="p">,</span> <span class="n">BS_C</span><span class="p">,</span> <span class="n">density</span><span class="o">=</span><span class="n">density</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span cla [...]
<span class="n">W_np</span> <span class="o">=</span> <span class="n">W_sp_np</span><span class="o">.</span><span class="n">todense</span><span class="p">()</span>
<span class="n">Y_np</span> <span class="o">=</span> <span class="n">X_np</span> <span class="o">@</span> <span class="n">W_np</span><span class="o">.</span><span class="n">T</span> <span class="c1"># Process the matrix multiplication</span>
-<span class="n">B_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.randn.html#numpy.random.randn" title="View documentation for numpy.random.randn"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randn</span></a><span class="p">(</span><span class="n">M</span><span class="p">,</span> <span class="n">N</span><span class="p">)</span><span class="o">.</span>< [...]
+<span class="n">B_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randn</span><span class="p">(</span><span class="n">M</span><span class="p">,</span> <span class="n">N</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">"float32"</span><span class="p">)</span>
<span class="n">Y_np</span> <span class="o">=</span> <span class="n">Y_np</span> <span class="o">+</span> <span class="n">B_np</span> <span class="c1"># Bias add</span>
-<span class="n">Y_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.maximum.html#numpy.maximum" title="View documentation for numpy.maximum"><span class="n">np</span><span class="o">.</span><span class="n">maximum</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.</span><span class="n" [...]
+<span class="n">Y_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">maximum</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">M</span><span class="p">,</span> <span class="n">N</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="s2">"float32"</span><span class="p">),</span> <span class="n [...]
</pre></div>
</div>
</div>
@@ -593,81 +593,32 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Lowered TIR:
@main = primfn(placeholder_5: handle, placeholder_6: handle, placeholder_7: handle, placeholder_8: handle, placeholder_9: handle, compute_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {placeholder_3: Buffer(placeholder_10: Pointer(float32), float32, [32768], []),
+ buffers = {placeholder_4: Buffer(placeholder_10: Pointer(float32), float32, [32768], []),
placeholder_2: Buffer(placeholder_11: Pointer(int32), int32, [4916], []),
- placeholder_1: Buffer(placeholder_12: Pointer(float32), float32, [78656], []),
+ placeholder_3: Buffer(placeholder_12: Pointer(float32), float32, [65536], []),
+ placeholder: Buffer(placeholder_13: Pointer(int32), int32, [33], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], []),
- placeholder_4: Buffer(placeholder_13: Pointer(int32), int32, [33], []),
- placeholder: Buffer(placeholder_14: Pointer(float32), float32, [65536], [])}
- buffer_map = {compute_1: compute, placeholder_9: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_5: placeholder_3, placeholder_8: placeholder_4} {
- 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, 4) {
- for (i.inner.init: int32, 0, 32) {
- let cse_var_1: int32 = ((i.outer.inner*512) + (i.inner.init*16))
- {
- 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
- }
+ placeholder_1: Buffer(placeholder_14: Pointer(float32), float32, [78656], [])}
+ buffer_map = {placeholder_8: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_9: placeholder_3, compute_1: compute, placeholder_5: placeholder_4} {
+ for (i0.outer.i1.outer.fused: int32, 0, 512) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [128]), storage_scope = global {
+ for (i.inner.init: int32, 0, 8) {
+ for (j.init: int32, 0, 16) {
+ compute_4: Buffer(compute_3, float32, [128], [])[((i.inner.init*16) + j.init)] = 0f32
}
- for (elem_idx: int32, 0, (placeholder_4[(i0.outer.i1.outer.fused + 1)] - placeholder_4[i0.outer.i1.outer.fused])) {
- for (i.inner: int32, 0, 32) {
- let cse_var_19: int32 = (elem_idx*16)
- let cse_var_18: int32 = ((i.outer.inner*8192) + (i.inner*256))
- let cse_var_17: int32 = ((i.outer.inner*512) + (i.inner*16))
- let cse_var_16: int32 = (cse_var_17 + 1)
- let cse_var_15: int32 = (cse_var_17 + 11)
- let cse_var_14: int32 = (cse_var_17 + 12)
- let cse_var_13: int32 = (cse_var_17 + 13)
- let cse_var_12: int32 = (cse_var_17 + 14)
- let cse_var_11: int32 = (cse_var_17 + 15)
- let cse_var_10: int32 = (cse_var_17 + 2)
- let cse_var_9: int32 = (cse_var_17 + 3)
- let cse_var_8: int32 = (cse_var_17 + 4)
- let cse_var_7: int32 = (cse_var_17 + 5)
- let cse_var_6: int32 = (cse_var_17 + 6)
- let cse_var_5: int32 = (cse_var_17 + 7)
- let cse_var_4: int32 = (cse_var_17 + 8)
- let cse_var_3: int32 = (cse_var_17 + 9)
- let cse_var_2: int32 = (cse_var_17 + 10)
- {
- compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_1[((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 1)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 2)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 3)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 4)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 5)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 6)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 7)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 8)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 9)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 10)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 11)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 12)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 13)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 14)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_1[(((placeholder_4[i0.outer.i1.outer.fused]*16) + cse_var_19) + 15)]*max(placeholder_3[(cse_var_18 + placeholder_2[(placeholder_4[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder[(cse_var_1 + 1)] - placeholder[cse_var_1])) {
+ for (i.inner: int32, 0, 8) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ let cse_var_2: int32 = ((i.inner*16) + j)
+ compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_1[(((placeholder[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder_4[(((floordiv(i0.outer.i1.outer.fused, 32)*2048) + (i.inner*256)) + placeholder_2[(placeholder[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
- for (i0.inner: int32, 0, 128) {
- let cse_var_20: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*16))
- compute[ramp(cse_var_20, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder[ramp(cse_var_20, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 8) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute[ramp(cse_var_4, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_3[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -699,14 +650,14 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="nb">print</span><span class="p">(</span>
<span class="s2">"Execution time of this operator: </span><span class="si">%.3f</span><span class="s2"> ms"</span>
<span class="o">%</span> <span class="p">(</span>
- <a href="https://numpy.org/doc/stable/reference/generated/numpy.median.html#numpy.median" title="View documentation for numpy.median"><span class="n">np</span><span class="o">.</span><span class="n">median</span></a><span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">X_tvm</span><span class="p">,</span> <span class="n">W_data_tvm</span><span class="p">,</span> <span class="n">W_indices_tvm</span><span class="p">,</span> <span class="n"> [...]
+ <span class="n">np</span><span class="o">.</span><span class="n">median</span><span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">X_tvm</span><span class="p">,</span> <span class="n">W_data_tvm</span><span class="p">,</span> <span class="n">W_indices_tvm</span><span class="p">,</span> <span class="n">W_indptr_tvm</span><span class="p">,</span> <span class="n">B_tvm</span><span class="p">,</span> <span class="n">Y_tvm</span><span class=" [...]
<span class="o">*</span> <span class="mi">1000</span>
<span class="p">)</span>
<span class="p">)</span>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.730 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.537 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 345eba8..3837aef 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<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>00:44.982</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:44.251</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:44.095</strong>: <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></li>
-<li><p><strong>00:00.233</strong>: <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></li>
-<li><p><strong>00:00.220</strong>: <a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></li>
-<li><p><strong>00:00.217</strong>: <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></li>
-<li><p><strong>00:00.216</strong>: <a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></li>
+<li><p><strong>00:43.353</strong>: <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></li>
+<li><p><strong>00:00.239</strong>: <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></li>
+<li><p><strong>00:00.223</strong>: <a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></li>
+<li><p><strong>00:00.220</strong>: <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></li>
+<li><p><strong>00:00.216</strong>: <a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></li>
</ul>
</div>
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 7c3fc25..af009b9 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1142,8 +1142,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
-No: 6 GFLOPS: 109.82/109.82 result: MeasureResult(costs=(0.0021079240625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7039425373077393, timestamp=1648107564.920924) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
-No: 7 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+No: 6 GFLOPS: 103.69/103.69 result: MeasureResult(costs=(0.0022325490625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5873916149139404, timestamp=1648113806.2056143) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+No: 7 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1266,7 +1266,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
-No: 8 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1389,7 +1389,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
-No: 9 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1512,7 +1512,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
-No: 10 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/103.69 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
@@ -1530,7 +1530,7 @@ No: 10 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
-No: 11 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1653,7 +1653,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
-No: 12 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1776,7 +1776,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
-No: 13 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1899,7 +1899,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
-No: 14 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2022,7 +2022,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
-No: 15 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2145,7 +2145,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
-No: 16 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2268,7 +2268,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
-No: 17 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2391,7 +2391,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
-No: 18 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2514,7 +2514,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
-No: 19 GFLOPS: 0.00/109.82 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/103.69 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 721, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 685, in run_through_rpc
@@ -2602,7 +2602,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007fe9db845fa2
+ 12: 0x00007fa0cb8d9fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2667,7 +2667,7 @@ Traceback (most recent call last):
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
-No: 20 GFLOPS: 143.28/143.28 result: MeasureResult(costs=(0.00161575352,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4582786560058594, timestamp=1648107591.5020921) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+No: 20 GFLOPS: 143.52/143.52 result: MeasureResult(costs=(0.0016130478870967741,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3990607261657715, timestamp=1648113832.552889) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2685,8 +2685,8 @@ and measure running time.</p>
<span class="n">func</span> <span class="o">=</span> <a href="../../reference/api/python/driver.html#tvm.build" title="View documentation for tvm.build"><span class="n">tvm</span><span class="o">.</span><span class="n">build</span></a><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="n">arg_bufs</span><span class="p">)</span>
<span class="c1"># check correctness</span>
-<span class="n">a_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">N</span><span class="p" [...]
-<span class="n">w_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">CO</span><span class="p [...]
+<span class="n">a_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">N</span><span class="p">,</span> <span class="n">CI</span><span class="p">,</span> <span class="n">H</span><span class="p">,</span> <span class="n">W</span><span class="p">))</span><span class [...]
+<span class="n">w_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">CO</span><span class="p">,</span> <span class="n">CI</span><span class="p">,</span> <span class="n">KH</span><span class="p">,</span> <span class="n">KW</span><span class="p">))</span><span cl [...]
<span class="n">c_np</span> <span class="o">=</span> <span class="n">conv2d_nchw_python</span><span class="p">(</span><span class="n">a_np</span><span class="p">,</span> <span class="n">w_np</span><span class="p">,</span> <span class="n">strides</span><span class="p">,</span> <span class="n">padding</span><span class="p">)</span>
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">cuda</span><span class="p">()</span>
@@ -2706,7 +2706,7 @@ and measure running time.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
-Time cost of this operator: 0.002058
+Time cost of this operator: 0.002014
</pre></div>
</div>
<div class="sphx-glr-footer class 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/tune_with_autotvm/tune_relay_arm.html b/docs/how_to/tune_with_autotvm/tune_relay_arm.html
index a23013b..33eed1d 100644
--- a/docs/how_to/tune_with_autotvm/tune_relay_arm.html
+++ b/docs/how_to/tune_with_autotvm/tune_relay_arm.html
@@ -643,7 +643,7 @@ We will introduce a more sophisticated tuning scheduler in the future.</p>
<span class="c1"># upload parameters to device</span>
<span class="n">dev</span> <span class="o">=</span> <span class="n">remote</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">target</span><span class="p">),</span> <span class="mi">0</span><span class="p">)</span>
<span class="n">module</span> <span class="o">=</span> <a href="../../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="View documentation for tvm.contrib.graph_executor.GraphModule"><span class="n">runtime</span><span class="o">.</span><span class="n">GraphModule</span></a><span class="p">(</span><span class="n">rlib</span><span class="p">[</span><span class="s2">"default"</span><span class="p">](</span><span class="n">dev</span><s [...]
- <span class="n">data_tvm</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">((</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform" [...]
+ <span class="n">data_tvm</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">((</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span cl [...]
<span class="n">module</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="s2">"data"</span><span class="p">,</span> <span class="n">data_tvm</span><span class="p">)</span>
<span class="c1"># evaluate</span>
diff --git a/docs/how_to/tune_with_autotvm/tune_relay_cuda.html b/docs/how_to/tune_with_autotvm/tune_relay_cuda.html
index 669d275..a2ff4b0 100644
--- a/docs/how_to/tune_with_autotvm/tune_relay_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_relay_cuda.html
@@ -545,7 +545,7 @@ We will introduce a more sophisticated tuning scheduler in the future.</p>
<span class="c1"># load parameters</span>
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">target</span><span class="p">),</span> <span class="mi">0</span><span class="p">)</span>
<span class="n">module</span> <span class="o">=</span> <a href="../../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="View documentation for tvm.contrib.graph_executor.GraphModule"><span class="n">runtime</span><span class="o">.</span><span class="n">GraphModule</span></a><span class="p">(</span><span class="n">lib</span><span class="p">[</span><span class="s2">"default"</span><span class="p">](</span><span class="n">dev</span><sp [...]
- <span class="n">data_tvm</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">((</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform" [...]
+ <span class="n">data_tvm</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">((</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span cl [...]
<span class="n">module</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="s2">"data"</span><span class="p">,</span> <span class="n">data_tvm</span><span class="p">)</span>
<span class="c1"># evaluate</span>
diff --git a/docs/how_to/tune_with_autotvm/tune_relay_mobile_gpu.html b/docs/how_to/tune_with_autotvm/tune_relay_mobile_gpu.html
index 007e4e3..b4218b8 100644
--- a/docs/how_to/tune_with_autotvm/tune_relay_mobile_gpu.html
+++ b/docs/how_to/tune_with_autotvm/tune_relay_mobile_gpu.html
@@ -635,7 +635,7 @@ We will introduce a more sophisticated tuning scheduler in the future.</p>
<span class="c1"># upload parameters to device</span>
<span class="n">dev</span> <span class="o">=</span> <span class="n">remote</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">target</span><span class="p">),</span> <span class="mi">0</span><span class="p">)</span>
<span class="n">module</span> <span class="o">=</span> <a href="../../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="View documentation for tvm.contrib.graph_executor.GraphModule"><span class="n">runtime</span><span class="o">.</span><span class="n">GraphModule</span></a><span class="p">(</span><span class="n">rlib</span><span class="p">[</span><span class="s2">"default"</span><span class="p">](</span><span class="n">dev</span><s [...]
- <span class="n">data_tvm</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">((</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform" [...]
+ <span class="n">data_tvm</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">((</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span cl [...]
<span class="n">module</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="s2">"data"</span><span class="p">,</span> <span class="n">data_tvm</span><span class="p">)</span>
<span class="c1"># evaluate</span>
diff --git a/docs/how_to/tune_with_autotvm/tune_relay_x86.html b/docs/how_to/tune_with_autotvm/tune_relay_x86.html
index 50f2f67..723723a 100644
--- a/docs/how_to/tune_with_autotvm/tune_relay_x86.html
+++ b/docs/how_to/tune_with_autotvm/tune_relay_x86.html
@@ -502,7 +502,7 @@ latency of one operator closer to its actual latency during end-to-end inference
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">evaluate_performance</span><span class="p">(</span><span class="n">lib</span><span class="p">,</span> <span class="n">data_shape</span><span class="p">):</span>
<span class="c1"># upload parameters to device</span>
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">cpu</span><span class="p">()</span>
- <span class="n">data_tvm</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">((</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><sp [...]
+ <span class="n">data_tvm</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">((</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class= [...]
<span class="n">module</span> <span class="o">=</span> <a href="../../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="View documentation for tvm.contrib.graph_executor.GraphModule"><span class="n">runtime</span><span class="o">.</span><span class="n">GraphModule</span></a><span class="p">(</span><span class="n">lib</span><span class="p">[</span><span class="s2">"default"</span><span class="p">](</span><span class="n">dev</span><span c [...]
<span class="n">module</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="n">input_name</span><span class="p">,</span> <span class="n">data_tvm</span><span class="p">)</span>
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index bb6e62c..1c58698 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -380,7 +380,7 @@ fill parameters with random numbers.</p>
<span class="n">relay_mod</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">IRModule</span><span class="o">.</span><span class="n">from_expr</span><span class="p">(</span><span class="n">f</span><span class="p">)</span>
<span class="n">relay_mod</span> <span class="o">=</span> <a href="../../reference/api/python/relay/transform.html#tvm.relay.transform.InferType" title="View documentation for tvm.relay.transform.InferType"><span class="n">tvm</span><span class="o">.</span><span class="n">relay</span><span class="o">.</span><span class="n">transform</span><span class="o">.</span><span class="n">InferType</span></a><span class="p">()(</span><span class="n">relay_mod</span><span class="p">)</span>
-<span class="n">weight_sample</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.rand.html#numpy.random.rand" title="View documentation for numpy.random.rand"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span></a><span class="p">(</span>
+<span class="n">weight_sample</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span>
<span class="n">weight_shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">weight_shape</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">weight_shape</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="n">weight_shape</span><span class="p">[</span><span class="mi">3</span><span class="p">]</span>
<span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">"float32"</span><span class="p">)</span>
<span class="n">params</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"weight"</span><span class="p">:</span> <span class="n">weight_sample</span><span class="p">}</span>
@@ -553,10 +553,10 @@ 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
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 314.4 98.752 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.073 0.965 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.283 (1, 1, 10, 10, 3) 1 1
-Total_time - 318.374 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.3 98.73 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.076 0.979 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.915 0.291 (1, 1, 10, 10, 3) 1 1
+Total_time - 314.29 - - - -
</pre></div>
</div>
</div>
@@ -608,10 +608,10 @@ 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
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 82.95 96.888 (1, 6, 10, 10, 1) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.74 2.032 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.925 1.08 (1, 1, 10, 10, 3) 1 1
-Total_time - 85.614 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.6 96.778 (1, 6, 10, 10, 1) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.77 2.125 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.914 1.097 (1, 1, 10, 10, 3) 1 1
+Total_time - 83.284 - - - -
</pre></div>
</div>
<div class="sphx-glr-footer class 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_tflite.html b/docs/how_to/work_with_microtvm/micro_tflite.html
index 769b8e4..b4b0241 100644
--- a/docs/how_to/work_with_microtvm/micro_tflite.html
+++ b/docs/how_to/work_with_microtvm/micro_tflite.html
@@ -647,7 +647,7 @@ to stand in for an attached microcontroller.</p>
<span class="c1"># The model consumes a single float32 value and returns a predicted sine value. To pass the</span>
<span class="c1"># input value we construct a tvm.nd.array object with a single contrived number as input. For</span>
<span class="c1"># this model values of 0 to 2Pi are acceptable.</span>
- <span class="n">graph_mod</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="n">input_tensor</span><span class="p">,</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/genera [...]
+ <span class="n">graph_mod</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="n">input_tensor</span><span class="p">,</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span [...]
<span class="n">graph_mod</span><span class="o">.</span><span class="n">run</span><span class="p">()</span>
<span class="n">tvm_output</span> <span class="o">=</span> <span class="n">graph_mod</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span><span class="o">.</span><span class="n">numpy</span><span class="p">()</span>
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 be9d869..6a28da9 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<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>00:45.039</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>00:44.148</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:40.865</strong>: <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></li>
-<li><p><strong>00:03.554</strong>: <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></li>
-<li><p><strong>00:00.208</strong>: <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></li>
-<li><p><strong>00:00.208</strong>: <a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></li>
-<li><p><strong>00:00.204</strong>: <a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></li>
+<li><p><strong>00:40.053</strong>: <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></li>
+<li><p><strong>00:03.482</strong>: <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></li>
+<li><p><strong>00:00.207</strong>: <a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></li>
+<li><p><strong>00:00.204</strong>: <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></li>
+<li><p><strong>00:00.201</strong>: <a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_relay/build_gcn.html b/docs/how_to/work_with_relay/build_gcn.html
index 764cc51..a6a2603 100644
--- a/docs/how_to/work_with_relay/build_gcn.html
+++ b/docs/how_to/work_with_relay/build_gcn.html
@@ -610,7 +610,7 @@ this method is temporary and will be updated in next few weeks when we have spar
<span class="c1"># Normalization w.r.t. node degrees</span>
<span class="n">degs</span> <span class="o">=</span> <span class="p">[</span><span class="n">g</span><span class="o">.</span><span class="n">in_degree</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">g</span><span class="o">.</span><span class="n">number_of_nodes</span><span class="p">())]</span>
- <span class="n">params</span><span class="p">[</span><span class="s2">"norm"</span><span class="p">]</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.power.html#numpy.power" title="View documentation for numpy.power"><span class="n">np</span><span class="o">.</span><span class="n">power</span></a><span class="p">(</span><span class="n">degs</span><span class="p">,</span> <span class="o">-</span><span class="mf">0.5</span><span [...]
+ <span class="n">params</span><span class="p">[</span><span class="s2">"norm"</span><span class="p">]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">power</span><span class="p">(</span><span class="n">degs</span><span class="p">,</span> <span class="o">-</span><span class="mf">0.5</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">"float32"</sp [...]
<span class="n">params</span><span class="p">[</span><span class="s2">"norm"</span><span class="p">]</span> <span class="o">=</span> <span class="n">params</span><span class="p">[</span><span class="s2">"norm"</span><span class="p">]</span><span class="o">.</span><span class="n">reshape</span><span class="p">((</span><span class="n">params</span><span class="p">[</span><span class="s2">"norm"</span><span class="p">]</span><span class="o">.</span><span cl [...]
<span class="k">return</span> <span class="n">params</span>
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 8469b95..9fc0f86 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -300,11 +300,11 @@
<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>00:04.234</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:04.344</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.544</strong>: <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></li>
-<li><p><strong>00:01.470</strong>: <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></li>
-<li><p><strong>00:00.220</strong>: <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></li>
+<li><p><strong>00:02.477</strong>: <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></li>
+<li><p><strong>00:01.661</strong>: <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></li>
+<li><p><strong>00:00.206</strong>: <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></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_relay/using_external_lib.html b/docs/how_to/work_with_relay/using_external_lib.html
index 4c12e38..505ed7d 100644
--- a/docs/how_to/work_with_relay/using_external_lib.html
+++ b/docs/how_to/work_with_relay/using_external_lib.html
@@ -392,7 +392,7 @@ By setting the logging level to DEBUG, the result of Relay graph compilation wil
<span class="n">lib</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">build_module</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">net</span><span class="p">,</span> <span class="n">target</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="n">params</span><span class="p">)</span>
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="n">target</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
-<span class="n">data</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p" [...]
+<span class="n">data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">data_shape</span><span class="p">)</span><span class="o">.</span><span class="n">astype</spa [...]
<span class="n">module</span> <span class="o">=</span> <a href="../../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="View documentation for tvm.contrib.graph_executor.GraphModule"><span class="n">runtime</span><span class="o">.</span><span class="n">GraphModule</span></a><span class="p">(</span><span class="n">lib</span><span class="p">[</span><span class="s2">"default"</span><span class="p">](</span><span class="n">dev</span><span class [...]
<span class="n">module</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="s2">"data"</span><span class="p">,</span> <span class="n">data</span><span class="p">)</span>
<span class="n">module</span><span class="o">.</span><span class="n">run</span><span class="p">()</span>
@@ -812,7 +812,7 @@ To do that, all we need to do is to append the option ” -libs=cudnn” to the
<span class="n">lib</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">build_module</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">net</span><span class="p">,</span> <span class="n">target</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="n">params</span><span class="p">)</span>
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="n">target</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
-<span class="n">data</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p" [...]
+<span class="n">data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">data_shape</span><span class="p">)</span><span class="o">.</span><span class="n">astype</spa [...]
<span class="n">module</span> <span class="o">=</span> <a href="../../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="View documentation for tvm.contrib.graph_executor.GraphModule"><span class="n">runtime</span><span class="o">.</span><span class="n">GraphModule</span></a><span class="p">(</span><span class="n">lib</span><span class="p">[</span><span class="s2">"default"</span><span class="p">](</span><span class="n">dev</span><span class [...]
<span class="n">module</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="s2">"data"</span><span class="p">,</span> <span class="n">data</span><span class="p">)</span>
<span class="n">module</span><span class="o">.</span><span class="n">run</span><span class="p">()</span>
diff --git a/docs/how_to/work_with_schedules/extern_op.html b/docs/how_to/work_with_schedules/extern_op.html
index eed40ae..cd8443c 100644
--- a/docs/how_to/work_with_schedules/extern_op.html
+++ b/docs/how_to/work_with_schedules/extern_op.html
@@ -397,12 +397,12 @@ We can further mix schedulable TVM calls that add a bias term to the result.</p>
<p>We can verify that the result matches what we expected.</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">cpu</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
<span class="n">f</span> <span class="o">=</span> <a href="../../reference/api/python/driver.html#tvm.build" title="View documentation for tvm.build"><span class="n">tvm</span><span class="o">.</span><span class="n">build</span></a><span class="p">(</span><span class="n">s</span><span class="p">,</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">D</span><span class="p">,</span> <span class="n"> [...]
-<span class="n">a</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n" [...]
-<span class="n">b</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n" [...]
-<span class="n">d</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.</span> [...]
+<span class="n">a</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</sp [...]
+<span class="n">b</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</sp [...]
+<span class="n">d</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">n</span><span class="p">,</span> <span class="n">m</span><span [...]
<span class="n">bb</span> <span class="o">=</span> <span class="mf">10.0</span>
<span class="n">f</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">d</span><span class="p">,</span> <span class="n">bb</span><span class="p">)</span>
-<span class="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">d</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.dot.html#numpy.dot" title="View documentation for numpy.dot"><span class="n">np</span><span class="o">.</span><span class="n">dot</span></a><span class="p">(</ [...]
+<span class="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">d</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">np</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</sp [...]
</pre></div>
</div>
</div>
@@ -442,8 +442,8 @@ with TVM.</p>
<span class="p">)</span>
<span class="n">s</span> <span class="o">=</span> <a href="../../reference/api/python/te.html#tvm.te.create_schedule" title="View documentation for tvm.te.create_schedule"><span class="n">te</span><span class="o">.</span><span class="n">create_schedule</span></a><span class="p">(</span><span class="n">B</span><span class="o">.</span><span class="n">op</span><span class="p">)</span>
<span class="n">f</span> <span class="o">=</span> <a href="../../reference/api/python/driver.html#tvm.build" title="View documentation for tvm.build"><span class="n">tvm</span><span class="o">.</span><span class="n">build</span></a><span class="p">(</span><span class="n">s</span><span class="p">,</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="s2">"llvm"</span><span class="p">)</span>
-<span class="n">a</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n" [...]
-<span class="n">b</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n" [...]
+<span class="n">a</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</sp [...]
+<span class="n">b</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</sp [...]
<span class="n">f</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">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">b</span><span class="o">.</span><span class="n">numpy</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="o">+</span> <span class="mi">1</span><span class="p">,</span> <span class="n">rtol</span><span class="o">=</ [...]
</pre></div>
diff --git a/docs/how_to/work_with_schedules/reduction.html b/docs/how_to/work_with_schedules/reduction.html
index d44182f..2e27207 100644
--- a/docs/how_to/work_with_schedules/reduction.html
+++ b/docs/how_to/work_with_schedules/reduction.html
@@ -608,10 +608,10 @@ extern "C" __global__ void __launch_bounds__(512) default_function_ker
<p>Verify the correctness of result kernel by comparing it to numpy.</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">nn</span> <span class="o">=</span> <span class="mi">128</span>
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">cuda</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
-<span class="n">a</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n" [...]
-<span class="n">b</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.</span> [...]
+<span class="n">a</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</sp [...]
+<span class="n">b</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">nn</span><span class="p">,</span> <span class="n">dtype</span>< [...]
<span class="n">fcuda</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">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.sum.html#numpy.sum" title="View documentation for numpy.sum"><span class="n">np</span><span class="o">.</span><span class="n">sum</span></a><span class="p">(</ [...]
+<span class="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">np</span><span class="o">.</span><span class="n">sum</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">axis< [...]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/work_with_schedules/scan.html b/docs/how_to/work_with_schedules/scan.html
index 3fc65be..d8eff11 100644
--- a/docs/how_to/work_with_schedules/scan.html
+++ b/docs/how_to/work_with_schedules/scan.html
@@ -425,11 +425,11 @@ numpy to verify the correctness of the result.</p>
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">cuda</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
<span class="n">n</span> <span class="o">=</span> <span class="mi">1024</span>
<span class="n">m</span> <span class="o">=</span> <span class="mi">10</span>
-<span class="n">a_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">m</span><span class="p" [...]
+<span class="n">a_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">m</span><span class="p">,</span> <span class="n">n</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">s_scan</span><spa [...]
<span class="n">a</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">a_np</span><span class="p">,</span> <span class="n">dev</span><span class="p">)</span>
-<span class="n">b</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.</span> [...]
+<span class="n">b</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">m</span><span class="p">,</span> <span class="n">n</span><span [...]
<span class="n">fscan</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">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.cumsum.html#numpy.cumsum" title="View documentation for numpy.cumsum"><span class="n">np</span><span class="o">.</span><span class="n">cumsum</span></a><span c [...]
+<span class="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">np</span><span class="o">.</span><span class="n">cumsum</span><span class="p">(</span><span class="n">a_np</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0 [...]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/work_with_schedules/schedule_primitives.html b/docs/how_to/work_with_schedules/schedule_primitives.html
index a79a825..c54a7ed 100644
--- a/docs/how_to/work_with_schedules/schedule_primitives.html
+++ b/docs/how_to/work_with_schedules/schedule_primitives.html
@@ -385,13 +385,13 @@ schedule computes tensor in a serial manner in a row-major order.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(float32), float32, [(stride: int32*m: int32)], [], type="auto"),
- A: Buffer(A_2: Pointer(float32), float32, [(stride_1: int32*m)], [], type="auto"),
+ buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*m: int32)], [], type="auto"),
+ C: Buffer(C_2: Pointer(float32), float32, [(stride_1: int32*m)], [], type="auto"),
B: Buffer(B_2: Pointer(float32), float32, [(stride_2: int32*m)], [], type="auto")}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (i: int32, 0, m) {
for (j: int32, 0, n: int32) {
- C[((i*stride) + (j*stride_3: int32))] = (A[((i*stride_1) + (j*stride_4: int32))]*B[((i*stride_2) + (j*stride_5: int32))])
+ C[((i*stride_1) + (j*stride_3: int32))] = (A[((i*stride) + (j*stride_4: int32))]*B[((i*stride_2) + (j*stride_5: int32))])
}
}
}
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 5261fff..8623073 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -300,16 +300,16 @@
<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>00:05.985</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:05.933</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.277</strong>: <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></li>
-<li><p><strong>00:01.053</strong>: <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></li>
-<li><p><strong>00:00.777</strong>: <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></li>
-<li><p><strong>00:00.765</strong>: <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></li>
-<li><p><strong>00:00.347</strong>: <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></li>
-<li><p><strong>00:00.265</strong>: <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></li>
-<li><p><strong>00:00.252</strong>: <a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></li>
-<li><p><strong>00:00.248</strong>: <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></li>
+<li><p><strong>00:02.178</strong>: <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></li>
+<li><p><strong>00:01.196</strong>: <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></li>
+<li><p><strong>00:00.808</strong>: <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></li>
+<li><p><strong>00:00.743</strong>: <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></li>
+<li><p><strong>00:00.321</strong>: <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></li>
+<li><p><strong>00:00.235</strong>: <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></li>
+<li><p><strong>00:00.226</strong>: <a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></li>
+<li><p><strong>00:00.225</strong>: <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></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index a75d404..76e870f 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -499,8 +499,8 @@ such placeholder can be put to let TVM automatically bind the inferred value for
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@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, [65536], []),
- C: Buffer(C_2: Pointer(float32), float32, [524288], []),
+ buffers = {C: Buffer(C_2: Pointer(float32), float32, [524288], []),
+ A: Buffer(A_2: Pointer(float32), float32, [65536], []),
B: Buffer(B_2: Pointer(float32), float32, [32768], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (i: int32, 0, 1024) {
@@ -548,8 +548,8 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
A: Buffer(A_2: Pointer(float32), float32, [65536], []),
B: Buffer(B_2: Pointer(float32), float32, [32768], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpi8h9kn87/input0.cc'
-source_filename = "/tmp/tmpi8h9kn87/input0.cc"
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpz09omo2l/input0.cc'
+source_filename = "/tmp/tmpz09omo2l/input0.cc"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-pc-linux-gnu"
@@ -656,11 +656,11 @@ ensure our implementation is correct.</p>
<span class="n">dtype</span> <span class="o">=</span> <span class="n">A</span><span class="o">.</span><span class="n">dtype</span>
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="s2">"cpu"</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
-<span class="n">a</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">get_const_tuple</span><span class="p">(</span><spa [...]
-<span class="n">b</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">get_const_tuple</span><span class="p">(</span><spa [...]
-<span class="n">c</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.</span> [...]
+<span class="n">a</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">get_const_tuple</span><span class="p">(</span><span class="n">A</span><span class="o">.</span><span class="n">shape</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</ [...]
+<span class="n">b</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">get_const_tuple</span><span class="p">(</span><span class="n">B</span><span class="o">.</span><span class="n">shape</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</ [...]
+<span class="n">c</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">get_const_tuple</span><span class="p">(</span><span class="n">C [...]
<span class="n">func</span><span class="p">(</span><a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">dev</span><span class="p">),</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View doc [...]
-<span class="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.dot.html#numpy.dot" title="View documentation for numpy.dot"><span class="n">np</span><span class="o">.</span><span class="n">dot</span></a><span class="p">(</ [...]
+<span class="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="o">.</span><span class="n">T</span><sp [...]
</pre></div>
</div>
</div>
@@ -762,11 +762,11 @@ due to the tiling.</p>
<span class="n">s</span><span class="p">[</span><span class="n">C</span><span class="p">]</span><span class="o">.</span><span class="n">pragma</span><span class="p">(</span><span class="n">yo</span><span class="p">,</span> <span class="s2">"import_llvm"</span><span class="p">,</span> <span class="n">gemv_impl</span><span class="p">())</span>
<span class="n">func</span> <span class="o">=</span> <a href="../../reference/api/python/driver.html#tvm.build" title="View documentation for tvm.build"><span class="n">tvm</span><span class="o">.</span><span class="n">build</span></a><span class="p">(</span><span class="n">s</span><span class="p">,</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= [...]
-<span class="n">a</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">get_const_tuple</span><span class="p">(</span><spa [...]
-<span class="n">b</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">get_const_tuple</span><span class="p">(</span><spa [...]
-<span class="n">c</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.</span> [...]
+<span class="n">a</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">get_const_tuple</span><span class="p">(</span><span class="n">A</span><span class="o">.</span><span class="n">shape</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</ [...]
+<span class="n">b</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">get_const_tuple</span><span class="p">(</span><span class="n">B</span><span class="o">.</span><span class="n">shape</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</ [...]
+<span class="n">c</span> <span class="o">=</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">get_const_tuple</span><span class="p">(</span><span class="n">C [...]
<span class="n">func</span><span class="p">(</span><a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">dev</span><span class="p">),</span> <a href="../../reference/api/python/ndarray.html#tvm.nd.array" title="View doc [...]
-<span class="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.dot.html#numpy.dot" title="View documentation for numpy.dot"><span class="n">np</span><span class="o">.</span><span class="n">dot</span></a><span class="p">(</ [...]
+<span class="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="o">.</span><span class="n">T</span><sp [...]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/work_with_schedules/tuple_inputs.html b/docs/how_to/work_with_schedules/tuple_inputs.html
index b27543d..827dbda 100644
--- a/docs/how_to/work_with_schedules/tuple_inputs.html
+++ b/docs/how_to/work_with_schedules/tuple_inputs.html
@@ -371,15 +371,15 @@ together in the next schedule procedure.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@main = primfn(A0_1: handle, A1_1: handle, B_2: handle, B_3: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {B_1: Buffer(B_4: Pointer(float32), float32, [(stride: int32*m: int32)], [], type="auto"),
- B: Buffer(B_5: Pointer(float32), float32, [(stride_1: int32*m)], [], type="auto"),
- A0: Buffer(A0_2: Pointer(float32), float32, [(stride_2: int32*m)], [], type="auto"),
+ buffers = {B: Buffer(B_4: Pointer(float32), float32, [(stride: int32*m: int32)], [], type="auto"),
+ A0: Buffer(A0_2: Pointer(float32), float32, [(stride_1: int32*m)], [], type="auto"),
+ B_1: Buffer(B_5: Pointer(float32), float32, [(stride_2: int32*m)], [], type="auto"),
A1: Buffer(A1_2: Pointer(float32), float32, [(stride_3: int32*m)], [], type="auto")}
buffer_map = {A0_1: A0, A1_1: A1, B_2: B, B_3: B_1} {
for (i: int32, 0, m) {
for (j: int32, 0, n: int32) {
- B[((i*stride_1) + (j*stride_4: int32))] = (A0[((i*stride_2) + (j*stride_5: int32))] + 2f32)
- B_1[((i*stride) + (j*stride_6: int32))] = (A1[((i*stride_3) + (j*stride_7: int32))]*3f32)
+ B[((i*stride) + (j*stride_4: int32))] = (A0[((i*stride_1) + (j*stride_5: int32))] + 2f32)
+ B_1[((i*stride_2) + (j*stride_6: int32))] = (A1[((i*stride_3) + (j*stride_7: int32))]*3f32)
}
}
}
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index d2418e8..6c8d26e 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1713,7 +1713,7 @@ Can be the a function or the function name.</p></li>
<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">
@@ -1750,7 +1750,7 @@ the initial naive schedule (state).</p>
<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>
diff --git a/docs/reference/api/python/ndarray.html b/docs/reference/api/python/ndarray.html
index 1317597..81b4b7c 100644
--- a/docs/reference/api/python/ndarray.html
+++ b/docs/reference/api/python/ndarray.html
@@ -411,7 +411,7 @@ Please use <cite>numpy</cite> instead.</p>
<dd class="field-odd"><p><strong>np_arr</strong> – The corresponding numpy array.</p>
</dd>
<dt class="field-even">Return type</dt>
-<dd class="field-even"><p><a class="reference external" href="https://numpy.org/doc/stable/reference/generated/numpy.ndarray.html#numpy.ndarray" title="(in NumPy v1.22)">numpy.ndarray</a></p>
+<dd class="field-even"><p>numpy.ndarray</p>
</dd>
</dl>
</dd></dl>
@@ -456,7 +456,7 @@ Please use <cite>numpy</cite> instead.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
-<li><p><strong>arr</strong> (<a class="reference external" href="https://numpy.org/doc/stable/reference/generated/numpy.ndarray.html#numpy.ndarray" title="(in NumPy v1.22)"><em>numpy.ndarray</em></a>) – The array to be copied from</p></li>
+<li><p><strong>arr</strong> (<em>numpy.ndarray</em>) – The array to be copied from</p></li>
<li><p><strong>device</strong> (<a class="reference internal" href="runtime.html#tvm.runtime.Device" title="tvm.runtime.Device"><em>Device</em></a><em>, </em><em>optional</em>) – The device device to create the array</p></li>
</ul>
</dd>
diff --git a/docs/reference/api/python/relay/image.html b/docs/reference/api/python/relay/image.html
index 8dee430..b912d8c 100644
--- a/docs/reference/api/python/relay/image.html
+++ b/docs/reference/api/python/relay/image.html
@@ -403,7 +403,7 @@ transformation is then applied on the sampling grid.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
-<li><p><strong>value</strong> (<em>Union</em><em>[</em><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.10)"><em>bool</em></a><em>, </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.10)"><em>int</em></a><em>, </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.10)"><em>float</em></a><em>, </em><a [...]
+<li><p><strong>value</strong> (<em>Union</em><em>[</em><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.10)"><em>bool</em></a><em>, </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.10)"><em>int</em></a><em>, </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.10)"><em>float</em></a><em>, </em><e [...]
<li><p><strong>dtype</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a><em>, </em><em>optional</em>) – The data type of the resulting constant.</p></li>
</ul>
</dd>
diff --git a/docs/reference/api/python/relay/index.html b/docs/reference/api/python/relay/index.html
index da02e5f..34aab16 100644
--- a/docs/reference/api/python/relay/index.html
+++ b/docs/reference/api/python/relay/index.html
@@ -1382,7 +1382,7 @@ When type_annotation is a str, we will create a scalar variable.</p></li>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
-<li><p><strong>value</strong> (<em>Union</em><em>[</em><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.10)"><em>bool</em></a><em>, </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.10)"><em>int</em></a><em>, </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.10)"><em>float</em></a><em>, </em><a [...]
+<li><p><strong>value</strong> (<em>Union</em><em>[</em><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.10)"><em>bool</em></a><em>, </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.10)"><em>int</em></a><em>, </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.10)"><em>float</em></a><em>, </em><e [...]
<li><p><strong>dtype</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a><em>, </em><em>optional</em>) – The data type of the resulting constant.</p></li>
</ul>
</dd>
diff --git a/docs/reference/api/python/relay/nn.html b/docs/reference/api/python/relay/nn.html
index acd55f2..cc28bac 100644
--- a/docs/reference/api/python/relay/nn.html
+++ b/docs/reference/api/python/relay/nn.html
@@ -1262,7 +1262,7 @@ using a fast bitserial algorithm.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
-<li><p><strong>value</strong> (<em>Union</em><em>[</em><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.10)"><em>bool</em></a><em>, </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.10)"><em>int</em></a><em>, </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.10)"><em>float</em></a><em>, </em><a [...]
+<li><p><strong>value</strong> (<em>Union</em><em>[</em><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.10)"><em>bool</em></a><em>, </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.10)"><em>int</em></a><em>, </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.10)"><em>float</em></a><em>, </em><e [...]
<li><p><strong>dtype</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a><em>, </em><em>optional</em>) – The data type of the resulting constant.</p></li>
</ul>
</dd>
diff --git a/docs/reference/api/python/topi.html b/docs/reference/api/python/topi.html
index d48d7cf..a6df0d9 100644
--- a/docs/reference/api/python/topi.html
+++ b/docs/reference/api/python/topi.html
@@ -1437,7 +1437,7 @@ outside the interval are clipped to the interval edges.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
-<li><p><strong>vector</strong> (<a class="reference external" href="https://numpy.org/doc/stable/reference/generated/numpy.ndarray.html#numpy.ndarray" title="(in NumPy v1.22)"><em>numpy.ndarray</em></a>) – Const input array</p></li>
+<li><p><strong>vector</strong> (<em>numpy.ndarray</em>) – Const input array</p></li>
<li><p><strong>name</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a><em>, </em><em>optional</em>) – The name of output op</p></li>
</ul>
</dd>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 4757c70..b443ef6 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/f36829563/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 c7280bf..c7cac2a 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/f36829563/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 726baa7..62f7030 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/f36829563/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 191308c..5e1743a 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/f36829563/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 7c31136..ec5d4d7 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/f36829563/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 428185b..970760d 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/f36829563/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 7b702bf..9c5bf2b 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/f36829563/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 2f1919e..99c4cce 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/f36829563/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/web/src/runtime.ts#L1134">runtime.ts:1134</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/f36829563/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 3f4f3ec..9252c34 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/f36829563/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 5c3afb7..3820ede 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/f36829563/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 9cbcbad..4c7cdd4 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/f36829563/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 a000baa..5748faf 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/f36829563/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 84fa4ee..bb897dc 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/f36829563/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 e649e4b..b29a4b4 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/f36829563/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 55968cc..77b10e5 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/f36829563/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 365a910..a50af01 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/f36829563/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 49ae559..d06e87d 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/f36829563/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 280b815..b74c45d 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/f36829563/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 91f70a7..fd0edaf 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/f36829563/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 67b0f0b..fba91f5 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/f36829563/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 179deef..318f2fb 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/f36829563/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/web/src/runtime.ts#L1356">runtime.ts:1356</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/f36829563/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 f451db5..68fde93 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/f36829563/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 9a2a694..3bc7800 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/f36829563/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 92fb11e..bb315f8 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/f36829563/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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/f36829563/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd52e63a/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 4c8ceea..d5dd18e 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 2b7f27e..bcd37fb 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -300,10 +300,10 @@
<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>00:20.364</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:19.697</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:20.147</strong>: <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></li>
-<li><p><strong>00:00.217</strong>: <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></li>
+<li><p><strong>00:19.490</strong>: <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></li>
+<li><p><strong>00:00.208</strong>: <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></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/autotvm/tune_relay_vta.html b/docs/topic/vta/tutorials/autotvm/tune_relay_vta.html
index 07de67d..4eb11bd 100644
--- a/docs/topic/vta/tutorials/autotvm/tune_relay_vta.html
+++ b/docs/topic/vta/tutorials/autotvm/tune_relay_vta.html
@@ -710,17 +710,17 @@ the <code class="docutils literal notranslate"><span class="pre">`TARGET</span><
<span class="n">m</span> <span class="o">=</span> <a href="../../../../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="View documentation for tvm.contrib.graph_executor.GraphModule"><span class="n">graph_executor</span><span class="o">.</span><span class="n">GraphModule</span></a><span class="p">(</span><span class="n">lib</span><span class="p">[</span><span class="s2">"default"</span><span class="p">](</span><span class="n">ctx</ [...]
<span class="c1"># upload parameters to device</span>
- <span class="n">image</span> <span class="o">=</span> <a href="../../../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">((</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.unifo [...]
+ <span class="n">image</span> <span class="o">=</span> <a href="../../../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">((</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span [...]
<span class="n">m</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="s2">"data"</span><span class="p">,</span> <span class="n">image</span><span class="p">)</span>
<span class="c1"># evaluate</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Evaluate inference time cost..."</span><span class="p">)</span>
<span class="n">timer</span> <span class="o">=</span> <span class="n">m</span><span class="o">.</span><span class="n">module</span><span class="o">.</span><span class="n">time_evaluator</span><span class="p">(</span><span class="s2">"run"</span><span class="p">,</span> <span class="n">ctx</span><span class="p">,</span> <span class="n">number</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">repeat</span><span class="o">=</sp [...]
<span class="n">tcost</span> <span class="o">=</span> <span class="n">timer</span><span class="p">()</span>
- <span class="n">prof_res</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">tcost</span><span class="o">.</span><span class="n">results</span><span class="p">)</span> <span class="o">*</span> <span class="mi">1000</span> <span class="c1"># convert to [...]
+ <span class="n">prof_res</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">tcost</span><span class="o">.</span><span class="n">results</span><span class="p">)</span> <span class="o">*</span> <span class="mi">1000</span> <span class="c1"># convert to millisecond</span>
<span class="nb">print</span><span class="p">(</span>
<span class="s2">"Mean inference time (std dev): </span><span class="si">%.2f</span><span class="s2"> ms (</span><span class="si">%.2f</span><span class="s2"> ms)"</span>
- <span class="o">%</span> <span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.mean.html#numpy.mean" title="View documentation for numpy.mean"><span class="n">np</span><span class="o">.</span><span class="n">mean</span></a><span class="p">(</span><span class="n">prof_res</span><span class="p">),</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.std.html#numpy.std" title="View documentation for numpy.std"><span class="n">n [...]
+ <span class="o">%</span> <span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="n">prof_res</span><span class="p">),</span> <span class="n">np</span><span class="o">.</span><span class="n">std</span><span class="p">(</span><span class="n">prof_res</span><span class="p">))</span>
<span class="p">)</span>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 66d49c8..70ce701 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -539,7 +539,7 @@ 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 21.76s!
+resnet18_v1 inference graph built in 20.96s!
</pre></div>
</div>
</div>
@@ -563,11 +563,11 @@ and an input test image.</p>
<span class="n">image</span> <span class="o">=</span> <span class="n">Image</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">image_fn</span><span class="p">)</span><span class="o">.</span><span class="n">resize</span><span class="p">((</span><span class="mi">224</span><span class="p">,</span> <span class="mi">224</span><span class="p">))</span>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.imshow.html#matplotlib.pyplot.imshow" title="View documentation for matplotlib.pyplot.imshow"><span class="n">plt</span><span class="o">.</span><span class="n">imshow</span></a><span class="p">(</span><span class="n">image</span><span class="p">)</span>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.show.html#matplotlib.pyplot.show" title="View documentation for matplotlib.pyplot.show"><span class="n">plt</span><span class="o">.</span><span class="n">show</span></a><span class="p">()</span>
-<span class="n">image</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">image</span><span class="p">)</span> <span class="o">-</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy. [...]
-<span class="n">image</span> <span class="o">/=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">([</span><span class="mf">58.395</span><span class="p">,</span> <span class="mf">57.12</span><span class="p">,</span> <span class="mf">57.375</span><span class="p">])</span>
+<span class="n">image</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">image</span><span class="p">)</span> <span class="o">-</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">123.0</span><span class="p">,</span> <span class="mf">117.0</span><span class="p">,</span> <span class="mf">104.0</span><span class="p">])</span>
+<span class="n">image</span> <span class="o">/=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">58.395</span><span class="p">,</span> <span class="mf">57.12</span><span class="p">,</span> <span class="mf">57.375</span><span class="p">])</span>
<span class="n">image</span> <span class="o">=</span> <span class="n">image</span><span class="o">.</span><span class="n">transpose</span><span class="p">((</span><span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">))</span>
-<span class="n">image</span> <span class="o">=</span> <span class="n">image</span><span class="p">[</span><a href="https://numpy.org/doc/stable/reference/constants.html#numpy.newaxis" title="View documentation for numpy.newaxis"><span class="n">np</span><span class="o">.</span><span class="n">newaxis</span></a><span class="p">,</span> <span class="p">:]</span>
-<span class="n">image</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.repeat.html#numpy.repeat" title="View documentation for numpy.repeat"><span class="n">np</span><span class="o">.</span><span class="n">repeat</span></a><span class="p">(</span><span class="n">image</span><span class="p">,</span> <span class="n">env</span><span class="o">.</span><span class="n">BATCH</span><span class="p">,</span> <span class="n">axis</span><span class="o" [...]
+<span class="n">image</span> <span class="o">=</span> <span class="n">image</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">newaxis</span><span class="p">,</span> <span class="p">:]</span>
+<span class="n">image</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">repeat</span><span class="p">(</span><span class="n">image</span><span class="p">,</span> <span class="n">env</span><span class="o">.</span><span class="n">BATCH</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="c1"># Set the network parameters and inputs</span>
<span class="n">m</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="o">**</span><span class="n">params</span><span class="p">)</span>
@@ -591,7 +591,7 @@ and an input test image.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="se">\t</span><span class="si">{:<16}</span><span class="s2">: </span><span class="si">{:>16}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="o">//</span> <span class="p">(</span><span class="n">num</span> <span class="o">*</span> [...]
<span class="k">else</span><span class="p">:</span>
<span class="n">tcost</span> <span class="o">=</span> <span class="n">timer</span><span class="p">()</span>
- <span class="n">std</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.std.html#numpy.std" title="View documentation for numpy.std"><span class="n">np</span><span class="o">.</span><span class="n">std</span></a><span class="p">(</span><span class="n">tcost</span><span class="o">.</span><span class="n">results</span><span class="p">)</span> <span class="o">*</span> <span class="mi">1000</span>
+ <span class="n">std</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">std</span><span class="p">(</span><span class="n">tcost</span><span class="o">.</span><span class="n">results</span><span class="p">)</span> <span class="o">*</span> <span class="mi">1000</span>
<span class="n">mean</span> <span class="o">=</span> <span class="n">tcost</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span class="mi">1000</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="se">\n</span><span class="s2">Performed inference in </span><span class="si">%.2f</span><span class="s2">ms (std = </span><span class="si">%.2f</span><span class="s2">) for </span><span class="si">%d</span><span class="s2"> samples"</span> <span class="o">%</span> <span class="p">(</span><span class="n">mean</span><span class="p">,</span> <span class="n">std</span><span class="p">,</s [...]
<span class="nb">print</span><span class="p">(</span><span class="s2">"Average per sample inference time: </span><span class="si">%.2f</span><span class="s2">ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">mean</span> <span class="o">/</span> <span class="n">env</span><span class="o">.</span><span class="n">BATCH</span><span class="p">))</span>
@@ -599,7 +599,7 @@ and an input test image.</p>
<span class="c1"># Get classification results</span>
<span class="n">tvm_output</span> <span class="o">=</span> <span class="n">m</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <a href="../../../../reference/api/python/ndarray.html#tvm.nd.empty" title="View documentation for tvm.nd.empty"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">empty</span></a><span class="p">((</span><span cla [...]
<span class="k">for</span> <span class="n">b</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">env</span><span class="o">.</span><span class="n">BATCH</span><span class="p">):</span>
- <span class="n">top_categories</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.argsort.html#numpy.argsort" title="View documentation for numpy.argsort"><span class="n">np</span><span class="o">.</span><span class="n">argsort</span></a><span class="p">(</span><span class="n">tvm_output</span><span class="o">.</span><span class="n">numpy</span><span class="p">()[</span><span class="n">b</span><span class="p">])</span>
+ <span class="n">top_categories</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argsort</span><span class="p">(</span><span class="n">tvm_output</span><span class="o">.</span><span class="n">numpy</span><span class="p">()[</span><span class="n">b</span><span class="p">])</span>
<span class="c1"># Report top-5 classification results</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="se">\n</span><span class="si">{}</span><span class="s2"> prediction for sample </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">b</span><span class="p">))</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="se">\t</span><span class="s2">#1:"</span><span class="p">,</span> <span class="n">synset</span><span class="p">[</span><span class="n">top_categories</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]])</span>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_detection.html b/docs/topic/vta/tutorials/frontend/deploy_detection.html
index 133ff9a..c5e4f35 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -557,7 +557,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:439: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 15.78s!
+yolov3-tiny inference graph built in 14.40s!
</pre></div>
</div>
</div>
@@ -575,8 +575,8 @@ Download test image</p>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.imshow.html#matplotlib.pyplot.imshow" title="View documentation for matplotlib.pyplot.imshow"><span class="n">plt</span><span class="o">.</span><span class="n">imshow</span></a><span class="p">(</span><span class="n">data</span><span class="p">)</span>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.show.html#matplotlib.pyplot.show" title="View documentation for matplotlib.pyplot.show"><span class="n">plt</span><span class="o">.</span><span class="n">show</span></a><span class="p">()</span>
<span class="n">data</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">transpose</span><span class="p">((</span><span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">))</span>
-<span class="n">data</span> <span class="o">=</span> <span class="n">data</span><span class="p">[</span><a href="https://numpy.org/doc/stable/reference/constants.html#numpy.newaxis" title="View documentation for numpy.newaxis"><span class="n">np</span><span class="o">.</span><span class="n">newaxis</span></a><span class="p">,</span> <span class="p">:]</span>
-<span class="n">data</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.repeat.html#numpy.repeat" title="View documentation for numpy.repeat"><span class="n">np</span><span class="o">.</span><span class="n">repeat</span></a><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">env</span><span class="o">.</span><span class="n">BATCH</span><span class="p">,</span> <span class="n">axis</span><span class="o">= [...]
+<span class="n">data</span> <span class="o">=</span> <span class="n">data</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">newaxis</span><span class="p">,</span> <span class="p">:]</span>
+<span class="n">data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">repeat</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">env</span><span class="o">.</span><span class="n">BATCH</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="c1"># Set the network parameters and inputs</span>
<span class="n">m</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="s2">"data"</span><span class="p">,</span> <span class="n">data</span><span class="p">)</span>
@@ -599,7 +599,7 @@ Download test image</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="se">\t</span><span class="si">{:<16}</span><span class="s2">: </span><span class="si">{:>16}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="o">//</span> <span class="p">(</span><span class="n">num</span> <span class="o">*</span> [...]
<span class="k">else</span><span class="p">:</span>
<span class="n">tcost</span> <span class="o">=</span> <span class="n">timer</span><span class="p">()</span>
- <span class="n">std</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.std.html#numpy.std" title="View documentation for numpy.std"><span class="n">np</span><span class="o">.</span><span class="n">std</span></a><span class="p">(</span><span class="n">tcost</span><span class="o">.</span><span class="n">results</span><span class="p">)</span> <span class="o">*</span> <span class="mi">1000</span>
+ <span class="n">std</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">std</span><span class="p">(</span><span class="n">tcost</span><span class="o">.</span><span class="n">results</span><span class="p">)</span> <span class="o">*</span> <span class="mi">1000</span>
<span class="n">mean</span> <span class="o">=</span> <span class="n">tcost</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span class="mi">1000</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="se">\n</span><span class="s2">Performed inference in </span><span class="si">%.2f</span><span class="s2">ms (std = </span><span class="si">%.2f</span><span class="s2">) for </span><span class="si">%d</span><span class="s2"> samples"</span> <span class="o">%</span> <span class="p">(</span><span class="n">mean</span><span class="p">,</span> <span class="n">std</span><span class="p">,</s [...]
<span class="nb">print</span><span class="p">(</span><span class="s2">"Average per sample inference time: </span><span class="si">%.2f</span><span class="s2">ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">mean</span> <span class="o">/</span> <span class="n">env</span><span class="o">.</span><span class="n">BATCH</span><span class="p">))</span>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index b05c6be..193d2b3 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -300,10 +300,10 @@
<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>01:30.035</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:27.808</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:47.963</strong>: <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></li>
-<li><p><strong>00:42.071</strong>: <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></li>
+<li><p><strong>00:46.678</strong>: <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></li>
+<li><p><strong>00:41.130</strong>: <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></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/matrix_multiply.html b/docs/topic/vta/tutorials/matrix_multiply.html
index 8a9b615..5c48ab5 100644
--- a/docs/topic/vta/tutorials/matrix_multiply.html
+++ b/docs/topic/vta/tutorials/matrix_multiply.html
@@ -825,8 +825,8 @@ interpreted.</p></li>
<span class="n">ctx</span> <span class="o">=</span> <span class="n">remote</span><span class="o">.</span><span class="n">ext_dev</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
<span class="c1"># Initialize the A and B arrays randomly in the int range of (-128, 128]</span>
-<span class="n">A_orig</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.randint.html#numpy.random.randint" title="View documentation for numpy.random.randint"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span></a><span class="p">(</span><span class="o">-</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span cla [...]
-<span class="n">B_orig</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.randint.html#numpy.random.randint" title="View documentation for numpy.random.randint"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span></a><span class="p">(</span><span class="o">-</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span cla [...]
+<span class="n">A_orig</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="o">-</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">o</span> <span class="o">*</span> <span class="n">env</span><s [...]
+<span class="n">B_orig</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="o">-</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">m</span> <span class="o">*</span> <span class="n">env</span><s [...]
<span class="c1"># Apply packing to the A and B arrays from a 2D to a 4D packed layout</span>
<span class="n">A_packed</span> <span class="o">=</span> <span class="n">A_orig</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="n">o</span><span class="p">,</span> <span class="n">env</span><span class="o">.</span><span class="n">BATCH</span><span class="p">,</span> <span class="n">n</span><span class="p">,</span> <span class="n">env</span><span class="o">.</span><span class="n">BLOCK_IN</span><span class="p">)</span><span class="o">.</spa [...]
@@ -835,7 +835,7 @@ interpreted.</p></li>
<span class="c1"># Format the input/output arrays with tvm.nd.array to the DLPack standard</span>
<span class="n">A_nd</span> <span class="o">=</span> <a href="../../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">A_packed</span><span class="p">,</span> <span class="n">ctx</span><span class="p">)</span>
<span class="n">B_nd</span> <span class="o">=</span> <a href="../../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">B_packed</span><span class="p">,</span> <span class="n">ctx</span><span class="p">)</span>
-<span class="n">C_nd</span> <span class="o">=</span> <a href="../../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.< [...]
+<span class="n">C_nd</span> <span class="o">=</span> <a href="../../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">o</span><span class="p">,</span> <span class="n">m</span [...]
<span class="c1"># Clear stats</span>
<span class="k">if</span> <span class="n">env</span><span class="o">.</span><span class="n">TARGET</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">"sim"</span><span class="p">,</span> <span class="s2">"tsim"</span><span class="p">]:</span>
@@ -851,9 +851,9 @@ interpreted.</p></li>
<p>Compute the reference result with numpy and assert that the output of the
matrix multiplication indeed is correct</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="c1"># Compute reference result with numpy</span>
-<span class="n">C_ref</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.dot.html#numpy.dot" title="View documentation for numpy.dot"><span class="n">np</span><span class="o">.</span><span class="n">dot</span></a><span class="p">(</span><span class="n">A_orig</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">env</span><span class="o">.</span><span class="n">acc_dtype</span><span class="p">),</sp [...]
+<span class="n">C_ref</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">A_orig</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">env</span><span class="o">.</span><span class="n">acc_dtype</span><span class="p">),</span> <span class="n">B_orig</span><span class="o">.</span><span class="n">T</span><span class="o">.</span><span class="n">astype</ [...]
<span class="n">C_ref</span> <span class="o">=</span> <span class="n">C_ref</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="n">o</span><span class="p">,</span> <span class="n">env</span><span class="o">.</span><span class="n">BATCH</span><span class="p">,</span> <span class="n">m</span><span class="p">,</span> <span class="n">env</span><span class="o">.</span><span class="n">BLOCK_OUT</span><span class="p">)</span><span class="o">.</span>< [...]
-<a href="https://numpy.org/doc/stable/reference/generated/numpy.testing.assert_equal.html#numpy.testing.assert_equal" title="View documentation for numpy.testing.assert_equal"><span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_equal</span></a><span class="p">(</span><span class="n">C_ref</span><span class="p">,</span> <span class="n">C_nd</span><span class="o">.</span><span class="n">numpy</span><span class="p">() [...]
+<span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_equal</span><span class="p">(</span><span class="n">C_ref</span><span class="p">,</span> <span class="n">C_nd</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
<span class="c1"># Print stats</span>
<span class="k">if</span> <span class="n">env</span><span class="o">.</span><span class="n">TARGET</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">"sim"</span><span class="p">,</span> <span class="s2">"tsim"</span><span class="p">]:</span>
diff --git a/docs/topic/vta/tutorials/optimize/convolution_opt.html b/docs/topic/vta/tutorials/optimize/convolution_opt.html
index 98a806f..f4ed14d 100644
--- a/docs/topic/vta/tutorials/optimize/convolution_opt.html
+++ b/docs/topic/vta/tutorials/optimize/convolution_opt.html
@@ -1016,10 +1016,10 @@ ensure correctness.</p>
<span class="c1"># Initialize the data and kernel arrays randomly in the int range</span>
<span class="c1"># of (-128, 128] in NCHW layout</span>
-<span class="n">data_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.randint.html#numpy.random.randint" title="View documentation for numpy.random.randint"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span></a><span class="p">(</span><span class="o">-</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span cl [...]
+<span class="n">data_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="o">-</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">in_ [...]
<span class="n">data</span><span class="o">.</span><span class="n">dtype</span>
<span class="p">)</span>
-<span class="n">kernel_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.randint.html#numpy.random.randint" title="View documentation for numpy.random.randint"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span></a><span class="p">(</span>
+<span class="n">kernel_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span>
<span class="o">-</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">out_channels</span><span class="p">,</span> <span class="n">in_channels</span><span class="p">,</span> <span class="n">kernel_h</span><span class="p">,</span> <span class="n">kernel_w</span><span class="p">)</span>
<span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">kernel</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span>
@@ -1041,7 +1041,7 @@ ensure correctness.</p>
<span class="c1"># Format the input/output arrays with tvm.nd.array to the DLPack standard</span>
<span class="n">data_nd</span> <span class="o">=</span> <a href="../../../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">data_packed</span><span class="p">,</span> <span class="n">ctx</span><span class="p">)</span>
<span class="n">kernel_nd</span> <span class="o">=</span> <a href="../../../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">kernel_packed</span><span class="p">,</span> <span class="n">ctx</span><span class="p">)</span>
-<span class="n">res_nd</span> <span class="o">=</span> <a href="../../../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class=" [...]
+<span class="n">res_nd</span> <span class="o">=</span> <a href="../../../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">output_shape</span><span class="p">)</span><span cla [...]
<span class="c1"># Clear stats</span>
<span class="k">if</span> <span class="n">env</span><span class="o">.</span><span class="n">TARGET</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">"sim"</span><span class="p">,</span> <span class="s2">"tsim"</span><span class="p">]:</span>
@@ -1058,7 +1058,7 @@ ensure correctness.</p>
<span class="p">(</span><span class="n">pad_h</span><span class="p">,</span> <span class="n">pad_w</span><span class="p">),</span>
<span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">env</span><span class="o">.</span><span class="n">acc_dtype</span><span class="p">)</span>
<span class="n">res_ref</span> <span class="o">=</span> <span class="n">res_ref</span> <span class="o">>></span> <span class="n">env</span><span class="o">.</span><span class="n">INP_WIDTH</span>
-<span class="n">res_ref</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.clip.html#numpy.clip" title="View documentation for numpy.clip"><span class="n">np</span><span class="o">.</span><span class="n">clip</span></a><span class="p">(</span><span class="n">res_ref</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">inp_max</span><span class="p">)</span>
+<span class="n">res_ref</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">clip</span><span class="p">(</span><span class="n">res_ref</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">inp_max</span><span class="p">)</span>
<span class="n">res_ref</span> <span class="o">=</span> <span class="n">res_ref</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">res</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span>
<span class="n">res_ref</span> <span class="o">=</span> <span class="n">res_ref</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span>
<span class="p">(</span>
diff --git a/docs/topic/vta/tutorials/optimize/matrix_multiply_opt.html b/docs/topic/vta/tutorials/optimize/matrix_multiply_opt.html
index 89b44d4..99fc16b 100644
--- a/docs/topic/vta/tutorials/optimize/matrix_multiply_opt.html
+++ b/docs/topic/vta/tutorials/optimize/matrix_multiply_opt.html
@@ -467,8 +467,8 @@ Those include:</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@main = primfn(data_1: handle, weight_1: handle, res_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {res: Buffer(res_2: Pointer(int8), int8, [1024], []),
- data: Buffer(data_2: Pointer(int8), int8, [1024], []),
+ buffers = {data: Buffer(data_2: Pointer(int8), int8, [1024], []),
+ res: Buffer(res_2: Pointer(int8), int8, [1024], []),
weight: Buffer(weight_2: Pointer(int8), int8, [1048576], [])}
buffer_map = {data_1: data, weight_1: weight, res_1: res} {
allocate(data_buf: Pointer(global int8), int8, [1024]), storage_scope = global;
@@ -735,8 +735,8 @@ and mapping the shift, and clipping computation to the vector ALU.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@main = primfn(data_1: handle, weight_1: handle, res_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {data: Buffer(data_2: Pointer(int8), int8, [1024], []),
- res: Buffer(res_2: Pointer(int8), int8, [1024], []),
+ buffers = {res: Buffer(res_2: Pointer(int8), int8, [1024], []),
+ data: Buffer(data_2: Pointer(int8), int8, [1024], []),
weight: Buffer(weight_2: Pointer(int8), int8, [1048576], [])}
buffer_map = {data_1: data, weight_1: weight, res_1: res} {
@tir.vta.coproc_dep_push(3, 2, dtype=int32)
@@ -825,8 +825,8 @@ ensure correctness.</p>
<span class="n">ctx</span> <span class="o">=</span> <span class="n">remote</span><span class="o">.</span><span class="n">ext_dev</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
<span class="c1"># Initialize the data and weight arrays randomly in the int range of (-128, 128]</span>
-<span class="n">data_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.randint.html#numpy.random.randint" title="View documentation for numpy.random.randint"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span></a><span class="p">(</span><span class="o">-</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span cl [...]
-<span class="n">weight_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.randint.html#numpy.random.randint" title="View documentation for numpy.random.randint"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span></a><span class="p">(</span><span class="o">-</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span [...]
+<span class="n">data_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="o">-</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">in_ [...]
+<span class="n">weight_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="o">-</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">out_channels</span><span class="p">,</span> <span class="n" [...]
<span class="c1"># Apply packing to the data and weight arrays from a 2D to a 4D packed layout</span>
<span class="n">data_packed</span> <span class="o">=</span> <span class="n">data_np</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span>
@@ -839,7 +839,7 @@ ensure correctness.</p>
<span class="c1"># Format the input/output arrays with tvm.nd.array to the DLPack standard</span>
<span class="n">data_nd</span> <span class="o">=</span> <a href="../../../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">data_packed</span><span class="p">,</span> <span class="n">ctx</span><span class="p">)</span>
<span class="n">weight_nd</span> <span class="o">=</span> <a href="../../../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">weight_packed</span><span class="p">,</span> <span class="n">ctx</span><span class="p">)</span>
-<span class="n">res_nd</span> <span class="o">=</span> <a href="../../../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class=" [...]
+<span class="n">res_nd</span> <span class="o">=</span> <a href="../../../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">output_shape</span><span class="p">)</span><span cla [...]
<span class="c1"># Clear stats</span>
<span class="k">if</span> <span class="n">env</span><span class="o">.</span><span class="n">TARGET</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">"sim"</span><span class="p">,</span> <span class="s2">"tsim"</span><span class="p">]:</span>
@@ -849,14 +849,14 @@ ensure correctness.</p>
<span class="n">f</span><span class="p">(</span><span class="n">data_nd</span><span class="p">,</span> <span class="n">weight_nd</span><span class="p">,</span> <span class="n">res_nd</span><span class="p">)</span>
<span class="c1"># Verify against numpy implementation</span>
-<span class="n">res_ref</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.dot.html#numpy.dot" title="View documentation for numpy.dot"><span class="n">np</span><span class="o">.</span><span class="n">dot</span></a><span class="p">(</span><span class="n">data_np</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">env</span><span class="o">.</span><span class="n">acc_dtype</span><span class="p">),< [...]
+<span class="n">res_ref</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">data_np</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">env</span><span class="o">.</span><span class="n">acc_dtype</span><span class="p">),</span> <span class="n">weight_np</span><span class="o">.</span><span class="n">T</span><span class="o">.</span><span class="n">as [...]
<span class="n">res_ref</span> <span class="o">=</span> <span class="n">res_ref</span> <span class="o">>></span> <span class="n">env</span><span class="o">.</span><span class="n">INP_WIDTH</span>
-<span class="n">res_ref</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.clip.html#numpy.clip" title="View documentation for numpy.clip"><span class="n">np</span><span class="o">.</span><span class="n">clip</span></a><span class="p">(</span><span class="n">res_ref</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">inp_max</span><span class="p">)</span>
+<span class="n">res_ref</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">clip</span><span class="p">(</span><span class="n">res_ref</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">inp_max</span><span class="p">)</span>
<span class="n">res_ref</span> <span class="o">=</span> <span class="n">res_ref</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">res</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span>
<span class="n">res_ref</span> <span class="o">=</span> <span class="n">res_ref</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span>
<span class="n">batch_size</span> <span class="o">//</span> <span class="n">env</span><span class="o">.</span><span class="n">BATCH</span><span class="p">,</span> <span class="n">env</span><span class="o">.</span><span class="n">BATCH</span><span class="p">,</span> <span class="n">out_channels</span> <span class="o">//</span> <span class="n">env</span><span class="o">.</span><span class="n">BLOCK_OUT</span><span class="p">,</span> <span class="n">env</span><span class="o">.</span><sp [...]
<span class="p">)</span><span class="o">.</span><span class="n">transpose</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span>
-<a href="https://numpy.org/doc/stable/reference/generated/numpy.testing.assert_equal.html#numpy.testing.assert_equal" title="View documentation for numpy.testing.assert_equal"><span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_equal</span></a><span class="p">(</span><span class="n">res_ref</span><span class="p">,</span> <span class="n">res_nd</span><span class="o">.</span><span class="n">numpy</span><span class="p [...]
+<span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_equal</span><span class="p">(</span><span class="n">res_ref</span><span class="p">,</span> <span class="n">res_nd</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
<span class="c1"># Print stats</span>
<span class="k">if</span> <span class="n">env</span><span class="o">.</span><span class="n">TARGET</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">"sim"</span><span class="p">,</span> <span class="s2">"tsim"</span><span class="p">]:</span>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index 5ea014b..6d26aab 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -300,10 +300,10 @@
<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>00:03.592</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.549</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:03.038</strong>: <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></li>
-<li><p><strong>00:00.554</strong>: <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></li>
+<li><p><strong>00:02.987</strong>: <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></li>
+<li><p><strong>00:00.562</strong>: <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></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index 1298560..b3eea12 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -300,10 +300,10 @@
<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>00:01.091</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:01.035</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:00.564</strong>: <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></li>
-<li><p><strong>00:00.527</strong>: <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></li>
+<li><p><strong>00:00.526</strong>: <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></li>
+<li><p><strong>00:00.509</strong>: <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></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/vta_get_started.html b/docs/topic/vta/tutorials/vta_get_started.html
index 24551e0..136293a 100644
--- a/docs/topic/vta/tutorials/vta_get_started.html
+++ b/docs/topic/vta/tutorials/vta_get_started.html
@@ -538,8 +538,8 @@ primitives.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(int8), int8, [1024], []),
- A: Buffer(A_2: Pointer(int32), int32, [1024], []),
+ buffers = {A: Buffer(A_2: Pointer(int32), int32, [1024], []),
+ C: Buffer(C_2: Pointer(int8), int8, [1024], []),
B: Buffer(B_2: Pointer(int32), int32, [1024], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
allocate(A_buf: Pointer(global int32), int32, [1024]), storage_scope = global;
@@ -711,8 +711,8 @@ interpreted.</p></li>
<span class="n">ctx</span> <span class="o">=</span> <span class="n">remote</span><span class="o">.</span><span class="n">ext_dev</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
<span class="c1"># Initialize the A and B arrays randomly in the int range of (-128, 128]</span>
-<span class="n">A_orig</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.randint.html#numpy.random.randint" title="View documentation for numpy.random.randint"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span></a><span class="p">(</span><span class="o">-</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span cla [...]
-<span class="n">B_orig</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.randint.html#numpy.random.randint" title="View documentation for numpy.random.randint"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span></a><span class="p">(</span><span class="o">-</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span cla [...]
+<span class="n">A_orig</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="o">-</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">o</span> <span class="o">*</span> <span class="n">env</span><s [...]
+<span class="n">B_orig</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="o">-</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">o</span> <span class="o">*</span> <span class="n">env</span><s [...]
<span class="c1"># Apply packing to the A and B arrays from a 2D to a 4D packed layout</span>
<span class="n">A_packed</span> <span class="o">=</span> <span class="n">A_orig</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="n">o</span><span class="p">,</span> <span class="n">env</span><span class="o">.</span><span class="n">BATCH</span><span class="p">,</span> <span class="n">m</span><span class="p">,</span> <span class="n">env</span><span class="o">.</span><span class="n">BLOCK_OUT</span><span class="p">)</span><span class="o">.</sp [...]
@@ -721,7 +721,7 @@ interpreted.</p></li>
<span class="c1"># Format the input/output arrays with tvm.nd.array to the DLPack standard</span>
<span class="n">A_nd</span> <span class="o">=</span> <a href="../../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">A_packed</span><span class="p">,</span> <span class="n">ctx</span><span class="p">)</span>
<span class="n">B_nd</span> <span class="o">=</span> <a href="../../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">B_packed</span><span class="p">,</span> <span class="n">ctx</span><span class="p">)</span>
-<span class="n">C_nd</span> <span class="o">=</span> <a href="../../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.< [...]
+<span class="n">C_nd</span> <span class="o">=</span> <a href="../../../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">o</span><span class="p">,</span> <span class="n">m</span [...]
<span class="c1"># Invoke the module to perform the computation</span>
<span class="n">f</span><span class="p">(</span><span class="n">A_nd</span><span class="p">,</span> <span class="n">B_nd</span><span class="p">,</span> <span class="n">C_nd</span><span class="p">)</span>
@@ -735,7 +735,7 @@ matrix multiplication indeed is correct</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="c1"># Compute reference result with numpy</span>
<span class="n">C_ref</span> <span class="o">=</span> <span class="p">(</span><span class="n">A_orig</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">env</span><span class="o">.</span><span class="n">acc_dtype</span><span class="p">)</span> <span class="o">+</span> <span class="n">B_orig</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">env</span><span class="o">.</span><span class="n">acc_ [...]
<span class="n">C_ref</span> <span class="o">=</span> <span class="n">C_ref</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="n">o</span><span class="p">,</span> <span class="n">env</span><span class="o">.</span><span class="n">BATCH</span><span class="p">,</span> <span class="n">m</span><span class="p">,</span> <span class="n">env</span><span class="o">.</span><span class="n">BLOCK_OUT</span><span class="p">)</span><span class="o">.</span>< [...]
-<a href="https://numpy.org/doc/stable/reference/generated/numpy.testing.assert_equal.html#numpy.testing.assert_equal" title="View documentation for numpy.testing.assert_equal"><span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_equal</span></a><span class="p">(</span><span class="n">C_ref</span><span class="p">,</span> <span class="n">C_nd</span><span class="o">.</span><span class="n">numpy</span><span class="p">() [...]
+<span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_equal</span><span class="p">(</span><span class="n">C_ref</span><span class="p">,</span> <span class="n">C_nd</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Successful vector add test!"</span><span class="p">)</span>
</pre></div>
</div>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index 7b32e95..8a0541c 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -471,8 +471,8 @@ operator fusion.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Lowered TIR:
@main = primfn(A_1: handle, B_1: handle, C_1: handle, out_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {out: Buffer(out_2: Pointer(float32), float32, [1048576], []),
- C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
+ buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
+ out: Buffer(out_2: Pointer(float32), float32, [1048576], []),
A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
B: Buffer(B_2: Pointer(float32), float32, [1048576], [])}
buffer_map = {A_1: A, B_1: B, C_1: C, out_1: out} {
@@ -520,9 +520,9 @@ operator fusion.</p>
<h2>Check correctness and evaluate performance<a class="headerlink" href="#check-correctness-and-evaluate-performance" title="Permalink to this headline">¶</a></h2>
<p>We build the binary and check its correctness and performance.</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">func</span> <span class="o">=</span> <a href="../reference/api/python/driver.html#tvm.build" title="View documentation for tvm.build"><span class="n">tvm</span><span class="o">.</span><span class="n">build</span></a><span class="p">(</span><span class="n">sch</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">target</span><span class="p">)</span>
-<span class="n">a_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">N</span><span class="p" [...]
-<span class="n">b_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">L</span><span class="p" [...]
-<span class="n">c_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">N</span><span class="p" [...]
+<span class="n">a_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">N</span><span class="p">,</span> <span class="n">L</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span cl [...]
+<span class="n">b_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">M</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span cl [...]
+<span class="n">c_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">N</span><span class="p">,</span> <span class="n">M</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span cl [...]
<span class="n">out_np</span> <span class="o">=</span> <span class="n">a_np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">b_np</span><span class="p">)</span> <span class="o">+</span> <span class="n">c_np</span>
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">cpu</span><span class="p">()</span>
@@ -533,18 +533,18 @@ operator fusion.</p>
<span class="n">func</span><span class="p">(</span><span class="n">a_tvm</span><span class="p">,</span> <span class="n">b_tvm</span><span class="p">,</span> <span class="n">c_tvm</span><span class="p">,</span> <span class="n">out_tvm</span><span class="p">)</span>
<span class="c1"># Check results</span>
-<a href="https://numpy.org/doc/stable/reference/generated/numpy.testing.assert_allclose.html#numpy.testing.assert_allclose" title="View documentation for numpy.testing.assert_allclose"><span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span></a><span class="p">(</span><span class="n">out_np</span><span class="p">,</span> <span class="n">out_tvm</span><span class="o">.</span><span class="n">numpy</span><s [...]
+<span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">out_np</span><span class="p">,</span> <span class="n">out_tvm</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">rtol</span><span class="o">=</span><span class="mf">1e-3</span><span class="p">)</span>
<span class="c1"># Evaluate execution time.</span>
<span class="n">evaluator</span> <span class="o">=</span> <span class="n">func</span><span class="o">.</span><span class="n">time_evaluator</span><span class="p">(</span><span class="n">func</span><span class="o">.</span><span class="n">entry_name</span><span class="p">,</span> <span class="n">dev</span><span class="p">,</span> <span class="n">min_repeat_ms</span><span class="o">=</span><span class="mi">500</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span>
<span class="s2">"Execution time of this operator: </span><span class="si">%.3f</span><span class="s2"> ms"</span>
- <span class="o">%</span> <span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.median.html#numpy.median" title="View documentation for numpy.median"><span class="n">np</span><span class="o">.</span><span class="n">median</span></a><span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a_tvm</span><span class="p">,</span> <span class="n">b_tvm</span><span class="p">,</span> <span class="n">c_tvm</span><span cla [...]
+ <span class="o">%</span> <span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">median</span><span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a_tvm</span><span class="p">,</span> <span class="n">b_tvm</span><span class="p">,</span> <span class="n">c_tvm</span><span class="p">,</span> <span class="n">out_tvm</span><span class="p">)</span><span class="o">.</span><span class="n">results</span><span class="p [...]
<span class="p">)</span>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 94.036 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.338 ms
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index d0607af..aa0d50e 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -649,8 +649,8 @@ best config with the same argument.</p>
<span class="n">func</span> <span class="o">=</span> <a href="../reference/api/python/driver.html#tvm.build" title="View documentation for tvm.build"><span class="n">tvm</span><span class="o">.</span><span class="n">build</span></a><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="n">arg_bufs</span><span class="p">)</span>
<span class="c1"># check correctness</span>
-<span class="n">a_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">N</span><span class="p" [...]
-<span class="n">b_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">L</span><span class="p" [...]
+<span class="n">a_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">N</span><span class="p">,</span> <span class="n">L</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span cl [...]
+<span class="n">b_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">M</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span cl [...]
<span class="n">c_np</span> <span class="o">=</span> <span class="n">a_np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">b_np</span><span class="p">)</span>
<span class="n">c_tvm</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.empty" title="View documentation for tvm.nd.empty"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">empty</span></a><span class="p">(</span><span class="n">c_np</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span>
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index b864022..97abc6c 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -419,18 +419,18 @@ free to substitute this image for any of your choosing.</p>
<span class="c1"># Resize it to 224x224</span>
<span class="n">resized_image</span> <span class="o">=</span> <span class="n">Image</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">img_path</span><span class="p">)</span><span class="o">.</span><span class="n">resize</span><span class="p">((</span><span class="mi">224</span><span class="p">,</span> <span class="mi">224</span><span class="p">))</span>
-<span class="n">img_data</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.asarray.html#numpy.asarray" title="View documentation for numpy.asarray"><span class="n">np</span><span class="o">.</span><span class="n">asarray</span></a><span class="p">(</span><span class="n">resized_image</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">"float32"</span><span class [...]
+<span class="n">img_data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">asarray</span><span class="p">(</span><span class="n">resized_image</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">"float32"</span><span class="p">)</span>
<span class="c1"># Our input image is in HWC layout while ONNX expects CHW input, so convert the array</span>
-<span class="n">img_data</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.transpose.html#numpy.transpose" title="View documentation for numpy.transpose"><span class="n">np</span><span class="o">.</span><span class="n">transpose</span></a><span class="p">(</span><span class="n">img_data</span><span class="p">,</span> <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <sp [...]
+<span class="n">img_data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">transpose</span><span class="p">(</span><span class="n">img_data</span><span class="p">,</span> <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">))</span>
<span class="c1"># Normalize according to the ImageNet input specification</span>
-<span class="n">imagenet_mean</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">([</span><span class="mf">0.485</span><span class="p">,</span> <span class="mf">0.456</span><span class="p">,</span> <span class="mf">0.406</span><span class="p">])</span><span class="o">.</span><span c [...]
-<span class="n">imagenet_stddev</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">([</span><span class="mf">0.229</span><span class="p">,</span> <span class="mf">0.224</span><span class="p">,</span> <span class="mf">0.225</span><span class="p">])</span><span class="o">.</span><span [...]
+<span class="n">imagenet_mean</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">0.485</span><span class="p">,</span> <span class="mf">0.456</span><span class="p">,</span> <span class="mf">0.406</span><span class="p">])</span><span class="o">.</span><span class="n">reshape</span><span class="p">((</span><span class="mi">3</span><span class="p">,</span> <span class="mi">1</span><span class= [...]
+<span class="n">imagenet_stddev</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">0.229</span><span class="p">,</span> <span class="mf">0.224</span><span class="p">,</span> <span class="mf">0.225</span><span class="p">])</span><span class="o">.</span><span class="n">reshape</span><span class="p">((</span><span class="mi">3</span><span class="p">,</span> <span class="mi">1</span><span clas [...]
<span class="n">norm_img_data</span> <span class="o">=</span> <span class="p">(</span><span class="n">img_data</span> <span class="o">/</span> <span class="mi">255</span> <span class="o">-</span> <span class="n">imagenet_mean</span><span class="p">)</span> <span class="o">/</span> <span class="n">imagenet_stddev</span>
<span class="c1"># Add the batch dimension, as we are expecting 4-dimensional input: NCHW.</span>
-<span class="n">img_data</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.expand_dims.html#numpy.expand_dims" title="View documentation for numpy.expand_dims"><span class="n">np</span><span class="o">.</span><span class="n">expand_dims</span></a><span class="p">(</span><span class="n">norm_img_data</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
+<span class="n">img_data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">expand_dims</span><span class="p">(</span><span class="n">norm_img_data</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
</pre></div>
</div>
</div>
@@ -499,21 +499,21 @@ standard deviation.</p>
<span class="n">timing_number</span> <span class="o">=</span> <span class="mi">10</span>
<span class="n">timing_repeat</span> <span class="o">=</span> <span class="mi">10</span>
<span class="n">unoptimized</span> <span class="o">=</span> <span class="p">(</span>
- <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">timeit</span><span class="o">.</span><span class="n">Timer</span><span class="p">(</span><span class="k">lambda</span><span class="p">:</span> <span class="n">module</span><span class="o">.</span><span class="n">run</span><span class="p [...]
+ <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">timeit</span><span class="o">.</span><span class="n">Timer</span><span class="p">(</span><span class="k">lambda</span><span class="p">:</span> <span class="n">module</span><span class="o">.</span><span class="n">run</span><span class="p">())</span><span class="o">.</span><span class="n">repeat</span><span class="p">(</span><span class="n">repeat</span><span class="o">= [...]
<span class="o">*</span> <span class="mi">1000</span>
<span class="o">/</span> <span class="n">timing_number</span>
<span class="p">)</span>
<span class="n">unoptimized</span> <span class="o">=</span> <span class="p">{</span>
- <span class="s2">"mean"</span><span class="p">:</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.mean.html#numpy.mean" title="View documentation for numpy.mean"><span class="n">np</span><span class="o">.</span><span class="n">mean</span></a><span class="p">(</span><span class="n">unoptimized</span><span class="p">),</span>
- <span class="s2">"median"</span><span class="p">:</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.median.html#numpy.median" title="View documentation for numpy.median"><span class="n">np</span><span class="o">.</span><span class="n">median</span></a><span class="p">(</span><span class="n">unoptimized</span><span class="p">),</span>
- <span class="s2">"std"</span><span class="p">:</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.std.html#numpy.std" title="View documentation for numpy.std"><span class="n">np</span><span class="o">.</span><span class="n">std</span></a><span class="p">(</span><span class="n">unoptimized</span><span class="p">),</span>
+ <span class="s2">"mean"</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="n">unoptimized</span><span class="p">),</span>
+ <span class="s2">"median"</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">median</span><span class="p">(</span><span class="n">unoptimized</span><span class="p">),</span>
+ <span class="s2">"std"</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">std</span><span class="p">(</span><span class="n">unoptimized</span><span class="p">),</span>
<span class="p">}</span>
<span class="nb">print</span><span class="p">(</span><span class="n">unoptimized</span><span class="p">)</span>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 502.3556121200454, 'median': 502.6672408000195, 'std': 0.6008660766512958}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 491.822284560003, 'median': 491.5935040000022, 'std': 0.7063807555278793}
</pre></div>
</div>
</div>
@@ -535,8 +535,8 @@ for the model.</p>
<span class="c1"># Open the output and read the output tensor</span>
<span class="n">scores</span> <span class="o">=</span> <a href="https://docs.scipy.org/doc/scipy-1.8.0/html-scipyorg/reference/generated/scipy.special.softmax.html#scipy.special.softmax" title="View documentation for scipy.special.softmax"><span class="n">softmax</span></a><span class="p">(</span><span class="n">tvm_output</span><span class="p">)</span>
-<span class="n">scores</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.squeeze.html#numpy.squeeze" title="View documentation for numpy.squeeze"><span class="n">np</span><span class="o">.</span><span class="n">squeeze</span></a><span class="p">(</span><span class="n">scores</span><span class="p">)</span>
-<span class="n">ranks</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.argsort.html#numpy.argsort" title="View documentation for numpy.argsort"><span class="n">np</span><span class="o">.</span><span class="n">argsort</span></a><span class="p">(</span><span class="n">scores</span><span class="p">)[::</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
+<span class="n">scores</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">squeeze</span><span class="p">(</span><span class="n">scores</span><span class="p">)</span>
+<span class="n">ranks</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argsort</span><span class="p">(</span><span class="n">scores</span><span class="p">)[::</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
<span class="k">for</span> <span class="n">rank</span> <span class="ow">in</span> <span class="n">ranks</span><span class="p">[</span><span class="mi">0</span><span class="p">:</span><span class="mi">5</span><span class="p">]:</span>
<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><span class="n">labels</span><span class="p">[</span><span class="n">rank</span><span class="p">],</span> <span class="n">scores</span><span class="p">[</span><span class="n">rank</span><span class="p">]))</span>
</pre></div>
@@ -667,128 +667,129 @@ depending on the specifics of the model and the target platform.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<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: (0/10) | 0.00 s
-[Task 1/25] Current/Best: 12.79/ 16.05 GFLOPS | Progress: (4/10) | 5.35 s
-[Task 1/25] Current/Best: 8.31/ 16.08 GFLOPS | Progress: (8/10) | 8.08 s
-[Task 1/25] Current/Best: 10.24/ 17.31 GFLOPS | Progress: (10/10) | 10.42 s Done.
+[Task 1/25] Current/Best: 15.48/ 15.48 GFLOPS | Progress: (4/10) | 5.02 s
+[Task 1/25] Current/Best: 6.76/ 17.78 GFLOPS | Progress: (8/10) | 7.98 s
+[Task 1/25] Current/Best: 14.13/ 17.78 GFLOPS | Progress: (10/10) | 9.01 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 2/25] Current/Best: 6.70/ 23.09 GFLOPS | Progress: (4/10) | 2.01 s
-[Task 2/25] Current/Best: 12.77/ 23.09 GFLOPS | Progress: (8/10) | 3.36 s
-[Task 2/25] Current/Best: 22.48/ 23.09 GFLOPS | Progress: (10/10) | 4.10 s Done.
+[Task 2/25] Current/Best: 13.44/ 20.29 GFLOPS | Progress: (4/10) | 2.75 s
+[Task 2/25] Current/Best: 6.70/ 20.29 GFLOPS | Progress: (8/10) | 4.03 s
+[Task 2/25] Current/Best: 13.88/ 20.29 GFLOPS | Progress: (10/10) | 5.27 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 3/25] Current/Best: 21.49/ 21.49 GFLOPS | Progress: (4/10) | 3.02 s
-[Task 3/25] Current/Best: 13.81/ 21.49 GFLOPS | Progress: (8/10) | 5.00 s
-[Task 3/25] Current/Best: 15.00/ 21.49 GFLOPS | Progress: (10/10) | 5.92 s Done.
+[Task 3/25] Current/Best: 7.21/ 16.04 GFLOPS | Progress: (4/10) | 3.04 s
+[Task 3/25] Current/Best: 17.60/ 17.60 GFLOPS | Progress: (8/10) | 4.82 s
+[Task 3/25] Current/Best: 1.63/ 17.60 GFLOPS | Progress: (10/10) | 7.17 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 4/25] Current/Best: 11.02/ 13.63 GFLOPS | Progress: (4/10) | 3.89 s
-[Task 4/25] Current/Best: 11.75/ 15.79 GFLOPS | Progress: (8/10) | 8.59 s
-[Task 4/25] Current/Best: 16.02/ 16.02 GFLOPS | Progress: (10/10) | 9.68 s Done.
+[Task 4/25] Current/Best: 17.57/ 17.65 GFLOPS | Progress: (4/10) | 2.86 s
+[Task 4/25] Current/Best: 13.76/ 17.65 GFLOPS | Progress: (8/10) | 9.07 s
+[Task 4/25] Current/Best: 14.38/ 17.65 GFLOPS | Progress: (10/10) | 10.44 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 5/25] Current/Best: 6.22/ 19.41 GFLOPS | Progress: (4/10) | 2.53 s
-[Task 5/25] Current/Best: 13.74/ 19.41 GFLOPS | Progress: (8/10) | 4.75 s
-[Task 5/25] Current/Best: 13.47/ 19.41 GFLOPS | Progress: (10/10) | 5.83 s Done.
+[Task 5/25] Current/Best: 8.67/ 14.09 GFLOPS | Progress: (4/10) | 3.18 s
+[Task 5/25] Current/Best: 17.41/ 19.54 GFLOPS | Progress: (8/10) | 4.70 s
+[Task 5/25] Current/Best: 18.49/ 19.54 GFLOPS | Progress: (10/10) | 5.35 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 6/25] Current/Best: 19.82/ 19.82 GFLOPS | Progress: (4/10) | 3.12 s
-[Task 6/25] Current/Best: 14.73/ 19.82 GFLOPS | Progress: (8/10) | 6.99 s
-[Task 6/25] Current/Best: 4.35/ 19.82 GFLOPS | Progress: (10/10) | 9.15 s Done.
+[Task 6/25] Current/Best: 5.35/ 20.86 GFLOPS | Progress: (4/10) | 4.71 s
+[Task 6/25] Current/Best: 16.44/ 20.86 GFLOPS | Progress: (8/10) | 6.75 s
+[Task 6/25] Current/Best: 15.73/ 20.86 GFLOPS | Progress: (10/10) | 7.81 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 7/25] Current/Best: 16.34/ 18.67 GFLOPS | Progress: (4/10) | 4.08 s
-[Task 7/25] Current/Best: 20.82/ 20.82 GFLOPS | Progress: (8/10) | 5.98 s
-[Task 7/25] Current/Best: 12.76/ 20.82 GFLOPS | Progress: (10/10) | 7.20 s Done.
+[Task 7/25] Current/Best: 18.17/ 21.44 GFLOPS | Progress: (4/10) | 3.01 s
+[Task 7/25] Current/Best: 15.19/ 21.44 GFLOPS | Progress: (8/10) | 5.01 s
+[Task 7/25] Current/Best: 12.01/ 21.44 GFLOPS | Progress: (10/10) | 5.82 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 8/25] Current/Best: 2.91/ 21.37 GFLOPS | Progress: (4/10) | 14.12 s
-[Task 8/25] Current/Best: 22.41/ 22.41 GFLOPS | Progress: (8/10) | 17.09 s
-[Task 8/25] Current/Best: 12.68/ 22.41 GFLOPS | Progress: (10/10) | 18.14 s
+[Task 8/25] Current/Best: 8.37/ 13.28 GFLOPS | Progress: (4/10) | 14.76 s
+[Task 8/25] Current/Best: 15.65/ 15.65 GFLOPS | Progress: (8/10) | 17.13 s
+[Task 8/25] Current/Best: 3.86/ 15.65 GFLOPS | Progress: (10/10) | 19.49 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 9/25] Current/Best: 12.65/ 15.82 GFLOPS | Progress: (4/10) | 3.82 s
-[Task 9/25] Current/Best: 13.79/ 19.06 GFLOPS | Progress: (8/10) | 5.07 s
-[Task 9/25] Current/Best: 9.85/ 20.36 GFLOPS | Progress: (10/10) | 6.34 s Done.
+[Task 9/25] Current/Best: 9.87/ 20.51 GFLOPS | Progress: (4/10) | 3.95 s
+[Task 9/25] Current/Best: 11.48/ 20.51 GFLOPS | Progress: (8/10) | 7.21 s
+[Task 9/25] Current/Best: 14.55/ 20.51 GFLOPS | Progress: (10/10) | 8.04 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 10/25] Current/Best: 10.41/ 14.01 GFLOPS | Progress: (4/10) | 3.61 s
-[Task 10/25] Current/Best: 19.37/ 19.37 GFLOPS | Progress: (8/10) | 5.43 s
-[Task 10/25] Current/Best: 11.35/ 19.37 GFLOPS | Progress: (10/10) | 6.28 s Done.
+[Task 10/25] Current/Best: 13.70/ 22.11 GFLOPS | Progress: (4/10) | 3.36 s
+[Task 10/25] Current/Best: 14.13/ 22.11 GFLOPS | Progress: (8/10) | 5.36 s
+[Task 10/25] Current/Best: 15.26/ 22.11 GFLOPS | Progress: (10/10) | 6.22 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 11/25] Current/Best: 16.53/ 20.37 GFLOPS | Progress: (4/10) | 2.58 s
-[Task 11/25] Current/Best: 21.74/ 21.74 GFLOPS | Progress: (8/10) | 5.45 s
-[Task 11/25] Current/Best: 14.46/ 23.99 GFLOPS | Progress: (10/10) | 6.49 s Done.
+[Task 11/25] Current/Best: 17.32/ 18.28 GFLOPS | Progress: (4/10) | 5.25 s
+[Task 11/25] Current/Best: 24.35/ 24.35 GFLOPS | Progress: (8/10) | 8.50 s
+[Task 11/25] Current/Best: 5.95/ 24.35 GFLOPS | Progress: (10/10) | 9.64 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 12/25] Current/Best: 15.48/ 15.48 GFLOPS | Progress: (4/10) | 6.32 s
-[Task 12/25] Current/Best: 9.87/ 20.95 GFLOPS | Progress: (8/10) | 10.22 s
-[Task 12/25] Current/Best: 4.43/ 20.95 GFLOPS | Progress: (10/10) | 11.49 s Done.
+[Task 12/25] Current/Best: 18.09/ 22.89 GFLOPS | Progress: (4/10) | 3.59 s
+[Task 12/25] Current/Best: 17.99/ 22.89 GFLOPS | Progress: (8/10) | 8.59 s
+[Task 12/25] Current/Best: 12.67/ 22.89 GFLOPS | Progress: (10/10) | 9.53 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 13/25] Current/Best: 1.57/ 23.21 GFLOPS | Progress: (4/10) | 5.76 s
-[Task 13/25] Current/Best: 13.86/ 23.21 GFLOPS | Progress: (8/10) | 8.19 s
-[Task 13/25] Current/Best: 21.06/ 23.21 GFLOPS | Progress: (10/10) | 10.32 s Done.
+[Task 13/25] Current/Best: 14.32/ 22.69 GFLOPS | Progress: (4/10) | 2.87 s
+[Task 13/25] Current/Best: 1.57/ 22.69 GFLOPS | Progress: (8/10) | 7.66 s
+[Task 13/25] Current/Best: 6.01/ 22.69 GFLOPS | Progress: (10/10) | 8.70 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 14/25] Current/Best: 7.99/ 21.25 GFLOPS | Progress: (4/10) | 4.01 s
-[Task 14/25] Current/Best: 12.25/ 21.25 GFLOPS | Progress: (8/10) | 7.90 s
-[Task 14/25] Current/Best: 17.83/ 21.25 GFLOPS | Progress: (10/10) | 9.31 s
-[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
- Done.
+[Task 14/25] Current/Best: 20.30/ 20.30 GFLOPS | Progress: (4/10) | 7.99 s
+[Task 14/25] Current/Best: 15.41/ 20.30 GFLOPS | Progress: (8/10) | 12.85 s
+[Task 14/25] Current/Best: 15.51/ 20.30 GFLOPS | Progress: (10/10) | 13.62 s Done.
+
+[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
+[Task 15/25] Current/Best: 11.10/ 11.10 GFLOPS | Progress: (4/10) | 2.33 s
+[Task 15/25] Current/Best: 11.65/ 16.34 GFLOPS | Progress: (8/10) | 6.19 s
+[Task 15/25] Current/Best: 20.83/ 23.68 GFLOPS | Progress: (10/10) | 6.73 s Done.
-[Task 15/25] Current/Best: 14.61/ 14.61 GFLOPS | Progress: (4/10) | 3.75 s
-[Task 15/25] Current/Best: 10.00/ 14.61 GFLOPS | Progress: (8/10) | 8.20 s
-[Task 15/25] Current/Best: 6.05/ 14.61 GFLOPS | Progress: (10/10) | 9.00 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 16/25] Current/Best: 6.64/ 19.18 GFLOPS | Progress: (4/10) | 2.83 s
-[Task 16/25] Current/Best: 16.93/ 19.18 GFLOPS | Progress: (8/10) | 3.98 s
-[Task 16/25] Current/Best: 10.84/ 19.18 GFLOPS | Progress: (10/10) | 5.28 s Done.
+[Task 16/25] Current/Best: 11.18/ 18.58 GFLOPS | Progress: (4/10) | 3.07 s
+[Task 16/25] Current/Best: 3.06/ 19.72 GFLOPS | Progress: (8/10) | 5.92 s
+[Task 16/25] Current/Best: 18.46/ 19.72 GFLOPS | Progress: (10/10) | 6.52 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 17/25] Current/Best: 10.21/ 16.43 GFLOPS | Progress: (4/10) | 4.16 s
-[Task 17/25] Current/Best: 3.11/ 21.92 GFLOPS | Progress: (8/10) | 7.59 s
-[Task 17/25] Current/Best: 3.11/ 21.92 GFLOPS | Progress: (10/10) | 9.02 s Done.
+[Task 17/25] Current/Best: 18.59/ 23.37 GFLOPS | Progress: (4/10) | 2.61 s
+[Task 17/25] Current/Best: 9.27/ 23.37 GFLOPS | Progress: (8/10) | 5.49 s
+[Task 17/25] Current/Best: 20.74/ 23.37 GFLOPS | Progress: (10/10) | 6.75 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 18/25] Current/Best: 11.24/ 17.61 GFLOPS | Progress: (4/10) | 3.75 s
-[Task 18/25] Current/Best: 15.09/ 19.45 GFLOPS | Progress: (8/10) | 5.87 s
-[Task 18/25] Current/Best: 16.87/ 19.45 GFLOPS | Progress: (10/10) | 6.65 s Done.
+[Task 18/25] Current/Best: 17.41/ 18.28 GFLOPS | Progress: (4/10) | 2.46 s
+[Task 18/25] Current/Best: 13.93/ 18.28 GFLOPS | Progress: (8/10) | 4.65 s
+[Task 18/25] Current/Best: 12.43/ 18.28 GFLOPS | Progress: (10/10) | 5.97 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 19/25] Current/Best: 15.57/ 19.24 GFLOPS | Progress: (4/10) | 3.62 s
-[Task 19/25] Current/Best: 13.15/ 19.24 GFLOPS | Progress: (8/10) | 7.61 s
-[Task 19/25] Current/Best: 6.05/ 19.24 GFLOPS | Progress: (10/10) | 11.45 s Done.
+[Task 19/25] Current/Best: 8.55/ 11.21 GFLOPS | Progress: (4/10) | 4.38 s
+[Task 19/25] Current/Best: 10.94/ 19.29 GFLOPS | Progress: (8/10) | 6.92 s
+[Task 19/25] Current/Best: 4.39/ 19.29 GFLOPS | Progress: (10/10) | 13.55 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 20/25] Current/Best: 13.47/ 16.10 GFLOPS | Progress: (4/10) | 2.59 s
-[Task 20/25] Current/Best: 14.19/ 16.10 GFLOPS | Progress: (8/10) | 5.54 s
-[Task 20/25] Current/Best: 7.47/ 16.10 GFLOPS | Progress: (10/10) | 8.31 s
-[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 21/25] Current/Best: 16.37/ 16.57 GFLOPS | Progress: (4/10) | 2.89 s
-[Task 21/25] Current/Best: 5.36/ 16.57 GFLOPS | Progress: (8/10) | 4.86 s
-[Task 21/25] Current/Best: 3.14/ 16.57 GFLOPS | Progress: (10/10) | 5.97 s
-[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
- Done.
+[Task 20/25] Current/Best: 9.96/ 16.18 GFLOPS | Progress: (4/10) | 2.83 s Done.
-[Task 22/25] Current/Best: 19.20/ 19.20 GFLOPS | Progress: (4/10) | 2.76 s
-[Task 22/25] Current/Best: 4.46/ 19.20 GFLOPS | Progress: (8/10) | 5.65 s
-[Task 22/25] Current/Best: 10.73/ 19.20 GFLOPS | Progress: (10/10) | 6.37 s Done.
+[Task 20/25] Current/Best: 18.65/ 21.56 GFLOPS | Progress: (8/10) | 4.77 s
+[Task 20/25] Current/Best: 10.57/ 21.56 GFLOPS | Progress: (10/10) | 5.86 s
+[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
+[Task 21/25] Current/Best: 4.34/ 11.24 GFLOPS | Progress: (4/10) | 3.72 s
+[Task 21/25] Current/Best: 5.42/ 17.81 GFLOPS | Progress: (8/10) | 6.06 s
+[Task 21/25] Current/Best: 5.38/ 17.81 GFLOPS | Progress: (10/10) | 6.75 s
+[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
+[Task 22/25] Current/Best: 16.84/ 16.84 GFLOPS | Progress: (4/10) | 2.83 s
+[Task 22/25] Current/Best: 19.54/ 21.25 GFLOPS | Progress: (8/10) | 4.08 s
+[Task 22/25] Current/Best: 18.39/ 21.25 GFLOPS | Progress: (10/10) | 4.96 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 23/25] Current/Best: 10.49/ 22.47 GFLOPS | Progress: (4/10) | 3.92 s
-[Task 23/25] Current/Best: 11.88/ 22.47 GFLOPS | Progress: (8/10) | 7.58 s
-[Task 23/25] Current/Best: 18.73/ 22.47 GFLOPS | Progress: (10/10) | 8.42 s Done.
+[Task 23/25] Current/Best: 4.76/ 23.31 GFLOPS | Progress: (4/10) | 9.53 s
+[Task 23/25] Current/Best: 19.93/ 23.31 GFLOPS | Progress: (8/10) | 12.85 s
+[Task 23/25] Current/Best: 10.75/ 23.31 GFLOPS | Progress: (10/10) | 17.01 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 24/25] Current/Best: 7.95/ 7.95 GFLOPS | Progress: (4/10) | 1627.52 s
-[Task 24/25] Current/Best: 8.42/ 8.42 GFLOPS | Progress: (8/10) | 1646.31 s
-[Task 24/25] Current/Best: 9.88/ 9.88 GFLOPS | Progress: (10/10) | 1647.34 s
-[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 25/25] Current/Best: 5.71/ 8.55 GFLOPS | Progress: (4/10) | 23.22 s Done.
-
-[Task 25/25] Current/Best: 5.89/ 9.31 GFLOPS | Progress: (8/10) | 25.72 s
-[Task 25/25] Current/Best: 2.87/ 9.31 GFLOPS | Progress: (10/10) | 38.42 s
+[Task 24/25] Current/Best: 0.54/ 5.08 GFLOPS | Progress: (4/10) | 11.70 s
+[Task 24/25] Current/Best: 7.93/ 7.93 GFLOPS | Progress: (8/10) | 45.32 s
+[Task 24/25] Current/Best: 4.07/ 7.93 GFLOPS | Progress: (10/10) | 45.93 s
+[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
+ Done.
+ Done.
+
+[Task 25/25] Current/Best: 8.98/ 9.42 GFLOPS | Progress: (4/10) | 18.83 s
+[Task 25/25] Current/Best: 8.15/ 9.42 GFLOPS | Progress: (8/10) | 31.85 s
+[Task 25/25] Current/Best: 1.55/ 9.42 GFLOPS | Progress: (10/10) | 44.43 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -843,8 +844,8 @@ model using optimized operators to speed up our computations.</p>
<span class="n">tvm_output</span> <span class="o">=</span> <span class="n">module</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <a href="../reference/api/python/ndarray.html#tvm.nd.empty" title="View documentation for tvm.nd.empty"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">empty</span></a><span class="p">(</span><span class="n [...]
<span class="n">scores</span> <span class="o">=</span> <a href="https://docs.scipy.org/doc/scipy-1.8.0/html-scipyorg/reference/generated/scipy.special.softmax.html#scipy.special.softmax" title="View documentation for scipy.special.softmax"><span class="n">softmax</span></a><span class="p">(</span><span class="n">tvm_output</span><span class="p">)</span>
-<span class="n">scores</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.squeeze.html#numpy.squeeze" title="View documentation for numpy.squeeze"><span class="n">np</span><span class="o">.</span><span class="n">squeeze</span></a><span class="p">(</span><span class="n">scores</span><span class="p">)</span>
-<span class="n">ranks</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.argsort.html#numpy.argsort" title="View documentation for numpy.argsort"><span class="n">np</span><span class="o">.</span><span class="n">argsort</span></a><span class="p">(</span><span class="n">scores</span><span class="p">)[::</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
+<span class="n">scores</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">squeeze</span><span class="p">(</span><span class="n">scores</span><span class="p">)</span>
+<span class="n">ranks</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argsort</span><span class="p">(</span><span class="n">scores</span><span class="p">)[::</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
<span class="k">for</span> <span class="n">rank</span> <span class="ow">in</span> <span class="n">ranks</span><span class="p">[</span><span class="mi">0</span><span class="p">:</span><span class="mi">5</span><span class="p">]:</span>
<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><span class="n">labels</span><span class="p">[</span><span class="n">rank</span><span class="p">],</span> <span class="n">scores</span><span class="p">[</span><span class="n">rank</span><span class="p">]))</span>
</pre></div>
@@ -877,11 +878,11 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="n">timing_number</span> <span class="o">=</span> <span class="mi">10</span>
<span class="n">timing_repeat</span> <span class="o">=</span> <span class="mi">10</span>
<span class="n">optimized</span> <span class="o">=</span> <span class="p">(</span>
- <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">timeit</span><span class="o">.</span><span class="n">Timer</span><span class="p">(</span><span class="k">lambda</span><span class="p">:</span> <span class="n">module</span><span class="o">.</span><span class="n">run</span><span class="p [...]
+ <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">timeit</span><span class="o">.</span><span class="n">Timer</span><span class="p">(</span><span class="k">lambda</span><span class="p">:</span> <span class="n">module</span><span class="o">.</span><span class="n">run</span><span class="p">())</span><span class="o">.</span><span class="n">repeat</span><span class="p">(</span><span class="n">repeat</span><span class="o">= [...]
<span class="o">*</span> <span class="mi">1000</span>
<span class="o">/</span> <span class="n">timing_number</span>
<span class="p">)</span>
-<span class="n">optimized</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"mean"</span><span class="p">:</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.mean.html#numpy.mean" title="View documentation for numpy.mean"><span class="n">np</span><span class="o">.</span><span class="n">mean</span></a><span class="p">(</span><span class="n">optimized</span><span class="p">),</span> <span class="s2">"median"</span><span class=" [...]
+<span class="n">optimized</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"mean"</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="n">optimized</span><span class="p">),</span> <span class="s2">"median"</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">median</span><span class="p">(</span><span class="n">op [...]
<span class="nb">print</span><span class="p">(</span><span class="s2">"optimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><span class="n">optimized</span><span class="p">))</span>
@@ -889,8 +890,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 461.7602170999635, 'median': 461.64030329991874, 'std': 0.7627124855057924}
-unoptimized: {'mean': 502.3556121200454, 'median': 502.6672408000195, 'std': 0.6008660766512958}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 426.9575861800149, 'median': 426.7440630999772, 'std': 0.8836425172203678}
+unoptimized: {'mean': 491.822284560003, 'median': 491.5935040000022, 'std': 0.7063807555278793}
</pre></div>
</div>
</div>
@@ -904,7 +905,7 @@ 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> ( 34 minutes 35.781 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 7 minutes 57.497 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
<div class="sphx-glr-download 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 2079f90..dc85f74 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -478,11 +478,11 @@ compiler to relink them. Now <cite>func</cite> is a remote module object.</p>
<span class="c1"># create arrays on the remote device</span>
<span class="n">dev</span> <span class="o">=</span> <span class="n">remote</span><span class="o">.</span><span class="n">cpu</span><span class="p">()</span>
-<span class="n">a</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np [...]
-<span class="n">b</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.</span><sp [...]
+<span class="n">a</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span> [...]
+<span class="n">b</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="mi">1024</span><span class="p">,</span> <span class="n">dtype</span>< [...]
<span class="c1"># the function will run on the remote device</span>
<span class="n">func</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span>
-<a href="https://numpy.org/doc/stable/reference/generated/numpy.testing.assert_equal.html#numpy.testing.assert_equal" title="View documentation for numpy.testing.assert_equal"><span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_equal</span></a><span class="p">(</span><span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">a</span><span class="o">.</span [...]
+<span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_equal</span><span class="p">(</span><span class="n">b</span><span class="o">.</span><span class="n">numpy</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="o">+</span> <span class="mi">1</span><span class="p">)</span>
</pre></div>
</div>
<p>When you want to evaluate the performance of the kernel on the remote
@@ -496,7 +496,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.233e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.276e-07 secs/op
</pre></div>
</div>
</div>
@@ -542,10 +542,10 @@ make runtime -j4
<span class="c1"># run</span>
<span class="n">dev</span> <span class="o">=</span> <span class="n">remote</span><span class="o">.</span><span class="n">cl</span><span class="p">()</span>
- <span class="n">a</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n [...]
- <span class="n">b</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.</span [...]
+ <span class="n">a</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</s [...]
+ <span class="n">b</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="mi">1024</span><span class="p">,</span> <span class="n">dtype</sp [...]
<span class="n">func</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span>
- <a href="https://numpy.org/doc/stable/reference/generated/numpy.testing.assert_equal.html#numpy.testing.assert_equal" title="View documentation for numpy.testing.assert_equal"><span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_equal</span></a><span class="p">(</span><span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">a</span><span class="o">.</ [...]
+ <span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_equal</span><span class="p">(</span><span class="n">b</span><span class="o">.</span><span class="n">numpy</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="o">+</span> <span class="mi">1</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"OpenCL test passed!"</span><span class="p">)</span>
</pre></div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index f55e3f1..77d760d 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -458,18 +458,18 @@ we can schedule the following series of operations ending with <code class="code
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x200c3210)), stage(b, placeholder(b, 0xb96e170)), 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, 0xf52fec0)), stage(b, placeholder(b, 0x22dce1b0)), 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>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">func</span> <span class="o">=</span> <a href="../reference/api/python/driver.html#tvm.build" title="View documentation for tvm.build"><span class="n">tvm</span><span class="o">.</span><span class="n">build</span></a><span class="p">(</span><span class="n">sg</span><span class="p">,</span> <span class="p">[</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span [...]
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">cuda</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
-<span class="n">a_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">x</span><span class="p" [...]
-<span class="n">b_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">y</span><span class="p" [...]
-<span class="n">g_np</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.sum.html#numpy.sum" title="View documentation for numpy.sum"><span class="n">np</span><span class="o">.</span><span class="n">sum</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.add.html#numpy.add" title="View documentation for numpy.add"><span class="n">np</span><span class="o">.</span><span class="n">add</span></a><span c [...]
+<span class="n">a_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="n">y</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span cl [...]
+<span class="n">b_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">y</span><span class="p">,</span> <span class="n">y</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">b</span><span cla [...]
+<span class="n">g_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">a_np</span> <span class="o">+</span> <span class="n">b_np</span><span class="p">,</span> <span class="n">a_np</span> <span class="o">*</span> <span class="n">b_np</span><span class="p">)</span> <span class="o">/</span> <span [...]
<span class="n">a_nd</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">a_np</span><span class="p">,</span> <span class="n">dev</span><span class="p">)</span>
<span class="n">b_nd</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">b_np</span><span class="p">,</span> <span class="n">dev</span><span class="p">)</span>
-<span class="n">g_nd</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.</span> [...]
+<span class="n">g_nd</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">g_np</span><span class="o">.</span><span class="n">shape</span> [...]
<span class="n">func</span><span class="p">(</span><span class="n">a_nd</span><span class="p">,</span> <span class="n">b_nd</span><span class="p">,</span> <span class="n">g_nd</span><span class="p">)</span>
<span class="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">g_nd</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">g_np</span><span class="p">,</span> <span class="n">rtol</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">)</span>
</pre></div>
diff --git a/docs/tutorial/relay_quick_start.html b/docs/tutorial/relay_quick_start.html
index 708dffe..a647c8e 100644
--- a/docs/tutorial/relay_quick_start.html
+++ b/docs/tutorial/relay_quick_start.html
@@ -511,7 +511,7 @@ in this example. Then the machine code will be generated as the module library.<
<p>Now we can create graph executor and run the module on Nvidia GPU.</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="c1"># create random input</span>
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">cuda</span><span class="p">()</span>
-<span class="n">data</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span></a><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p" [...]
+<span class="n">data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">data_shape</span><span class="p">)</span><span class="o">.</span><span class="n">astype</spa [...]
<span class="c1"># create module</span>
<span class="n">module</span> <span class="o">=</span> <a href="../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="View documentation for tvm.contrib.graph_executor.GraphModule"><span class="n">graph_executor</span><span class="o">.</span><span class="n">GraphModule</span></a><span class="p">(</span><span class="n">lib</span><span class="p">[</span><span class="s2">"default"</span><span class="p">](</span><span class="n">dev</span><span c [...]
<span class="c1"># set input and parameters</span>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index 4678b79..e9bd4cd 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -300,20 +300,20 @@
<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>37:18.408</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>10:28.906</strong> total execution time for <strong>tutorial</strong> files:</p>
<ul class="simple">
-<li><p><strong>34:35.781</strong>: <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></li>
-<li><p><strong>01:04.130</strong>: <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></li>
-<li><p><strong>00:46.525</strong>: <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></li>
-<li><p><strong>00:26.723</strong>: <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></li>
-<li><p><strong>00:23.500</strong>: <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></li>
-<li><p><strong>00:00.715</strong>: <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></li>
-<li><p><strong>00:00.579</strong>: <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></li>
-<li><p><strong>00:00.220</strong>: <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></li>
-<li><p><strong>00:00.061</strong>: <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></li>
-<li><p><strong>00:00.059</strong>: <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></li>
-<li><p><strong>00:00.058</strong>: <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></li>
-<li><p><strong>00:00.057</strong>: <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></li>
+<li><p><strong>07:57.497</strong>: <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></li>
+<li><p><strong>01:00.132</strong>: <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></li>
+<li><p><strong>00:48.456</strong>: <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></li>
+<li><p><strong>00:25.617</strong>: <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></li>
+<li><p><strong>00:15.608</strong>: <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></li>
+<li><p><strong>00:00.696</strong>: <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></li>
+<li><p><strong>00:00.550</strong>: <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></li>
+<li><p><strong>00:00.201</strong>: <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></li>
+<li><p><strong>00:00.044</strong>: <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></li>
+<li><p><strong>00:00.039</strong>: <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></li>
+<li><p><strong>00:00.033</strong>: <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></li>
+<li><p><strong>00:00.031</strong>: <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></li>
</ul>
</div>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 8ca66dc..73d60d7 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -464,9 +464,9 @@ computation performed by numpy.</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="n">tgt</span><span class="o">.</span><span class="n">kind</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
<span class="n">n</span> <span class="o">=</span> <span class="mi">1024</span>
-<span class="n">a</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np [...]
-<span class="n">b</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n">np [...]
-<span class="n">c</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.</span><sp [...]
+<span class="n">a</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span> [...]
+<span class="n">b</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span> [...]
+<span class="n">c</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="n">dtype</span><span [...]
<span class="n">fadd</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="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">numpy</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="o">+</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
@@ -491,9 +491,9 @@ helper function to run a profile of the TVM generated code.</p>
<span class="k">def</span> <span class="nf">evaluate_addition</span><span class="p">(</span><span class="n">func</span><span class="p">,</span> <span class="n">target</span><span class="p">,</span> <span class="n">optimization</span><span class="p">,</span> <span class="n">log</span><span class="p">):</span>
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="n">target</span><span class="o">.</span><span class="n">kind</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
<span class="n">n</span> <span class="o">=</span> <span class="mi">32768</span>
- <span class="n">a</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n [...]
- <span class="n">b</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n [...]
- <span class="n">c</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.</span [...]
+ <span class="n">a</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</s [...]
+ <span class="n">b</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</s [...]
+ <span class="n">c</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="n">dtype</span>< [...]
<span class="n">evaluator</span> <span class="o">=</span> <span class="n">func</span><span class="o">.</span><span class="n">time_evaluator</span><span class="p">(</span><span class="n">func</span><span class="o">.</span><span class="n">entry_name</span><span class="p">,</span> <span class="n">dev</span><span class="p">,</span> <span class="n">number</span><span class="o">=</span><span class="mi">10</span><span class="p">)</span>
<span class="n">mean_time</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>
@@ -508,7 +508,7 @@ helper function to run a profile of the TVM generated code.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
-naive: 0.000006
+naive: 0.000007
</pre></div>
</div>
</div>
@@ -601,15 +601,15 @@ factor to be the number of threads on your CPU.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000025
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type="auto"),
- A: Buffer(A_2: Pointer(float32), float32, [(stride_1: int32*n)], [], type="auto"),
+ buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type="auto"),
+ C: Buffer(C_2: Pointer(float32), float32, [(stride_1: int32*n)], [], type="auto"),
B: Buffer(B_2: Pointer(float32), float32, [(stride_2: int32*n)], [], type="auto")}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (i.outer: int32, 0, floordiv((n + 3), 4)) "parallel" {
for (i.inner.s: int32, 0, 4) {
if @tir.likely((((i.outer*4) + i.inner.s) < n), dtype=bool) {
let cse_var_1: int32 = ((i.outer*4) + i.inner.s)
- C[(cse_var_1*stride)] = (A[(cse_var_1*stride_1)] + B[(cse_var_1*stride_2)])
+ C[(cse_var_1*stride_1)] = (A[(cse_var_1*stride)] + B[(cse_var_1*stride_2)])
}
}
}
@@ -631,10 +631,10 @@ factor to be the number of threads on your CPU.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 8.224830016843043e-06 1.0
- naive 5.8652e-06 0.7131089624939452
-parallel 6.9543e-06 0.8455250729509041
- vector 2.45668e-05 2.986906714143806
+ numpy 8.49431000460754e-06 1.0
+ naive 6.732e-06 0.7925305288302856
+parallel 7.070899999999999e-06 0.8324278247632302
+ vector 2.47126e-05 2.9093122321407185
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -723,9 +723,9 @@ will target compilation of the vector addition to GPUs.</p>
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="n">tgt_gpu</span><span class="o">.</span><span class="n">kind</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
<span class="n">n</span> <span class="o">=</span> <span class="mi">1024</span>
- <span class="n">a</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n [...]
- <span class="n">b</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n [...]
- <span class="n">c</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.</span [...]
+ <span class="n">a</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</s [...]
+ <span class="n">b</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</s [...]
+ <span class="n">c</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="n">dtype</span>< [...]
<span class="n">fadd</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="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">numpy</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="o">+</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p"> [...]
@@ -846,9 +846,9 @@ device, and verifies the correctness of the code.</p>
<span class="nb">print</span><span class="p">(</span><span class="n">fadd_cl</span><span class="o">.</span><span class="n">imported_modules</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">get_source</span><span class="p">())</span>
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">cl</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
<span class="n">n</span> <span class="o">=</span> <span class="mi">1024</span>
- <span class="n">a</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n [...]
- <span class="n">b</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.uniform.html#numpy.random.uniform" title="View documentation for numpy.random.uniform"><span class="n [...]
- <span class="n">c</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.</span [...]
+ <span class="n">a</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</s [...]
+ <span class="n">b</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</s [...]
+ <span class="n">c</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="n">dtype</span>< [...]
<span class="n">fadd_cl</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="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">numpy</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="o">+</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p"> [...]
</pre></div>
@@ -929,8 +929,8 @@ matrix multiplication.</p>
<span class="n">dev</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="n">target</span><span class="o">.</span><span class="n">kind</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
<span class="c1"># Random generated tensor for testing</span>
-<span class="n">a</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.rand.html#numpy.random.rand" title="View documentation for numpy.random.rand"><span class="n">numpy</span [...]
-<span class="n">b</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/random/generated/numpy.random.rand.html#numpy.random.rand" title="View documentation for numpy.random.rand"><span class="n">numpy</span [...]
+<span class="n">a</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">numpy</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="n">M</span><sp [...]
+<span class="n">b</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">numpy</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="n">K</span><sp [...]
<span class="c1"># Repeatedly perform a matrix multiplication to get a performance baseline</span>
<span class="c1"># for the default numpy implementation</span>
@@ -948,11 +948,11 @@ matrix multiplication.</p>
<span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Numpy running time: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><span class="n">np_running_time</span> <span class="o">/</span> <span class="n">np_repeat</span><span class="p">))</span>
-<span class="n">answer</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.dot.html#numpy.dot" title="View documentation for numpy.dot"><span class="n">numpy</span><span class="o">.</span><span class="n">dot</span></a><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>
+<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>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019760
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018267
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -969,7 +969,7 @@ optimizations.</p>
<span class="n">s</span> <span class="o">=</span> <a href="../reference/api/python/te.html#tvm.te.create_schedule" title="View documentation for tvm.te.create_schedule"><span class="n">te</span><span class="o">.</span><span class="n">create_schedule</span></a><span class="p">(</span><span class="n">C</span><span class="o">.</span><span class="n">op</span><span class="p">)</span>
<span class="n">func</span> <span class="o">=</span> <a href="../reference/api/python/driver.html#tvm.build" title="View documentation for tvm.build"><span class="n">tvm</span><span class="o">.</span><span class="n">build</span></a><span class="p">(</span><span class="n">s</span><span class="p">,</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="n" [...]
-<span class="n">c</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">numpy</span><span class="o">.</span> [...]
+<span class="n">c</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">numpy</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">M</span><span class="p">,</span> <span class="n">N</span><span [...]
<span class="n">func</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="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">answer</span><span class="p">,</span> <span class="n">rtol</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">)</span>
@@ -978,7 +978,7 @@ optimizations.</p>
<span class="n">func</span> <span class="o">=</span> <a href="../reference/api/python/driver.html#tvm.build" title="View documentation for tvm.build"><span class="n">tvm</span><span class="o">.</span><span class="n">build</span></a><span class="p">(</span><span class="n">s</span><span class="p">,</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 [...]
<span class="k">assert</span> <span class="n">func</span>
- <span class="n">c</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">numpy</span><span class="o">.</s [...]
+ <span class="n">c</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">numpy</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">M</span><span class="p">,</span> <span class="n">N</span>< [...]
<span class="n">func</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="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">answer</span><span class="p">,</span> <span class="n">rtol</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">)</span>
@@ -994,7 +994,7 @@ optimizations.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.552890
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.376311
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1007,8 +1007,8 @@ nested loops over the indices of the A and B matrices.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
- A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
B: Buffer(B_2: Pointer(float32), float32, [1048576], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (x: int32, 0, 1024) {
@@ -1060,7 +1060,7 @@ schedule.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.335310
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.289320
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1120,7 +1120,7 @@ already cache friendly from our previous optimizations.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.355306
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.326682
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
@@ -1175,11 +1175,11 @@ more cache friendly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.145115
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.116640
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
- C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
+ buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
+ A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
B: Buffer(B_2: Pointer(float32), float32, [1048576], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (x.outer: int32, 0, 32) {
@@ -1251,7 +1251,7 @@ optimized schedule.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.114273
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.110079
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
@@ -1325,7 +1325,7 @@ to `C</cite> when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.115233
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110906
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
@@ -1392,7 +1392,7 @@ of thread-level parallelization.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.149285
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.144534
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
@@ -1454,13 +1454,13 @@ working, we can compare the results.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.5528903428999996 1.0
- blocking 0.3353095335 0.09437655011505591
- vectorization 0.35530559790000005 0.10000466200991348
-loop permutation 0.1451150882 0.04084423502965524
- array packing 0.1142733002 0.032163475134649365
- block caching 0.11523314609999999 0.03243363430292151
- parallelization 0.1492849731 0.04201789492274285
+ none 3.3763106256999995 1.0
+ blocking 0.28932003700000003 0.08569117864859258
+ vectorization 0.3266819908 0.09675708991742135
+loop permutation 0.1166400076 0.03454658665353618
+ array packing 0.11007855660000002 0.032603207703135365
+ block caching 0.1109057242 0.03284819926099254
+ parallelization 0.14453447940000003 0.04280840699307226
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1492,7 +1492,7 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.130 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.132 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-tensor-expr-get-started-py">
<div class="sphx-glr-download 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>
diff --git a/docs/tutorial/tensor_ir_blitz_course.html b/docs/tutorial/tensor_ir_blitz_course.html
index bf553e4..dc2c356 100644
--- a/docs/tutorial/tensor_ir_blitz_course.html
+++ b/docs/tutorial/tensor_ir_blitz_course.html
@@ -452,8 +452,8 @@ class Module:
</pre></div>
</div>
<p>Prepare the input array and output array, then run the module.</p>
-<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">a</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.arange.html#numpy.arange" title="Vi [...]
-<span class="n">b</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.</span><sp [...]
+<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">a</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</sp [...]
+<span class="n">b</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="mi">8</span><span class="p">,))</span><span class="o">.</span><span [...]
<span class="n">mod</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="nb">print</span><span class="p">(</span><span class="n">a</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="n">b</span><span class="p">)</span>
@@ -568,8 +568,8 @@ class Module:
<p>After binding the threads, now build the IRModule with <code class="code docutils literal notranslate"><span class="pre">cuda</span></code> backends.</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">ctx</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">cuda</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
<span class="n">cuda_mod</span> <span class="o">=</span> <a href="../reference/api/python/driver.html#tvm.build" title="View documentation for tvm.build"><span class="n">tvm</span><span class="o">.</span><span class="n">build</span></a><span class="p">(</span><span class="n">sch</span><span class="o">.</span><span class="n">mod</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">cuda_a</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.arange.html#numpy.arange" title="View documentation for numpy.arange"><span class="n">np</span><span class="o">.</ [...]
-<span class="n">cuda_b</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.</spa [...]
+<span class="n">cuda_a</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="mi">8</span><span class="p">)</span><span class="o">.</span><sp [...]
+<span class="n">cuda_b</span> <span class="o">=</span> <a href="../reference/api/python/ndarray.html#tvm.nd.array" title="View documentation for tvm.nd.array"><span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="mi">8</span><span class="p">,))</span><span class="o">.</span>< [...]
<span class="n">cuda_mod</span><span class="p">(</span><span class="n">cuda_a</span><span class="p">,</span> <span class="n">cuda_b</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="n">cuda_a</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="n">cuda_b</span><span class="p">)</span>