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 2023/03/03 12:56:31 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@bc92a3ff665de14803d7c7d6dcac20e7fc8dbd1b)
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 acdba015e9 deploying docs (apache/tvm@bc92a3ff665de14803d7c7d6dcac20e7fc8dbd1b)
acdba015e9 is described below
commit acdba015e95a08973cfe02ec0ffc403e38e87430
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri Mar 3 12:56:21 2023 +0000
deploying docs (apache/tvm@bc92a3ff665de14803d7c7d6dcac20e7fc8dbd1b)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 336918 -> 333957 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 24568 -> 23827 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_adreno.rst.txt | 2 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 357 +++++---------------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 83 ++++-
.../tune_with_autotvm/sg_execution_times.rst.txt | 8 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 207 ++----------
.../work_with_microtvm/micro_autotune.rst.txt | 18 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 16 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 6 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 59 ++--
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 18 +-
.../tutorial/tensor_expr_get_started.rst.txt | 47 +--
docs/arch/benchmark.html | 5 +
docs/arch/convert_layout.html | 5 +
docs/arch/debugger.html | 5 +
docs/arch/device_target_interactions.html | 5 +
docs/arch/frontend/tensorflow.html | 5 +
docs/arch/hybrid_script.html | 5 +
docs/arch/index.html | 5 +
docs/arch/inferbound.html | 5 +
.../arch/introduction_to_module_serialization.html | 5 +
docs/arch/microtvm_design.html | 5 +
docs/arch/microtvm_project_api.html | 5 +
docs/arch/model_library_format.html | 5 +
docs/arch/pass_infra.html | 5 +
docs/arch/relay_intro.html | 5 +
docs/arch/relay_op_strategy.html | 5 +
docs/arch/runtime.html | 5 +
docs/arch/runtimes/vulkan.html | 5 +
docs/arch/security.html | 5 +
docs/arch/virtual_machine.html | 5 +
docs/commit_hash | 2 +-
docs/contribute/ci.html | 5 +
docs/contribute/code_guide.html | 5 +
docs/contribute/code_review.html | 5 +
docs/contribute/committer_guide.html | 5 +
docs/contribute/community.html | 5 +
docs/contribute/document.html | 5 +
docs/contribute/error_handling.html | 5 +
docs/contribute/git_howto.html | 5 +
docs/contribute/index.html | 5 +
docs/contribute/pull_request.html | 5 +
docs/contribute/release_process.html | 5 +
docs/dev/how_to/debugging_tvm.html | 5 +
docs/dev/how_to/how_to.html | 5 +
docs/dev/how_to/pytest_target_parametrization.html | 5 +
docs/dev/how_to/relay_add_op.html | 5 +
docs/dev/how_to/relay_add_pass.html | 5 +
docs/dev/how_to/relay_bring_your_own_codegen.html | 5 +
docs/dev/tutorial/codebase_walkthrough.html | 5 +
docs/dev/tutorial/index.html | 5 +
docs/errors.html | 5 +
docs/faq.html | 5 +
docs/genindex.html | 5 +
docs/how_to/compile_models/from_coreml.html | 5 +
docs/how_to/compile_models/from_darknet.html | 7 +-
docs/how_to/compile_models/from_keras.html | 7 +-
docs/how_to/compile_models/from_mxnet.html | 7 +-
docs/how_to/compile_models/from_oneflow.html | 17 +-
docs/how_to/compile_models/from_onnx.html | 5 +
docs/how_to/compile_models/from_paddle.html | 5 +
docs/how_to/compile_models/from_pytorch.html | 16 +-
docs/how_to/compile_models/from_tensorflow.html | 7 +-
docs/how_to/compile_models/from_tflite.html | 5 +
docs/how_to/compile_models/index.html | 5 +
docs/how_to/compile_models/sg_execution_times.html | 27 +-
docs/how_to/deploy/adreno.html | 5 +
docs/how_to/deploy/android.html | 5 +
docs/how_to/deploy/arm_compute_lib.html | 5 +
docs/how_to/deploy/bnns.html | 5 +
docs/how_to/deploy/cpp_deploy.html | 5 +
docs/how_to/deploy/hls.html | 5 +
docs/how_to/deploy/index.html | 5 +
docs/how_to/deploy/integrate.html | 5 +
docs/how_to/deploy/tensorrt.html | 5 +
docs/how_to/deploy/vitis_ai.html | 5 +
.../deploy_models/deploy_model_on_adreno.html | 7 +-
.../deploy_models/deploy_model_on_android.html | 7 +-
.../how_to/deploy_models/deploy_model_on_nano.html | 5 +
.../how_to/deploy_models/deploy_model_on_rasp.html | 5 +
.../deploy_object_detection_pytorch.html | 52 +--
docs/how_to/deploy_models/deploy_prequantized.html | 13 +-
.../deploy_models/deploy_prequantized_tflite.html | 9 +-
docs/how_to/deploy_models/deploy_quantized.html | 7 +-
docs/how_to/deploy_models/deploy_sparse.html | 5 +
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 40 ++-
docs/how_to/deploy_models/index.html | 5 +
docs/how_to/deploy_models/sg_execution_times.html | 25 +-
.../extend_tvm/bring_your_own_datatypes.html | 7 +-
docs/how_to/extend_tvm/index.html | 5 +
docs/how_to/extend_tvm/low_level_custom_pass.html | 5 +
docs/how_to/extend_tvm/sg_execution_times.html | 13 +-
docs/how_to/extend_tvm/use_pass_infra.html | 5 +
docs/how_to/extend_tvm/use_pass_instrument.html | 21 +-
docs/how_to/index.html | 5 +
docs/how_to/optimize_operators/index.html | 5 +
docs/how_to/optimize_operators/opt_conv_cuda.html | 7 +-
.../optimize_operators/opt_conv_tensorcore.html | 7 +-
docs/how_to/optimize_operators/opt_gemm.html | 21 +-
.../optimize_operators/sg_execution_times.html | 13 +-
docs/how_to/profile/index.html | 5 +
docs/how_to/profile/papi.html | 5 +
docs/how_to/tune_with_autoscheduler/index.html | 5 +
.../sg_execution_times.html | 19 +-
.../tune_conv2d_layer_cuda.html | 358 +++++----------------
.../tune_with_autoscheduler/tune_network_arm.html | 5 +
.../tune_with_autoscheduler/tune_network_cuda.html | 9 +-
.../tune_with_autoscheduler/tune_network_mali.html | 5 +
.../tune_with_autoscheduler/tune_network_x86.html | 9 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 88 ++++-
docs/how_to/tune_with_autotvm/index.html | 5 +
.../tune_with_autotvm/sg_execution_times.html | 13 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 212 +++---------
docs/how_to/tune_with_autotvm/tune_relay_arm.html | 5 +
docs/how_to/tune_with_autotvm/tune_relay_cuda.html | 5 +
.../tune_with_autotvm/tune_relay_mobile_gpu.html | 5 +
docs/how_to/tune_with_autotvm/tune_relay_x86.html | 5 +
docs/how_to/work_with_microtvm/index.html | 5 +
docs/how_to/work_with_microtvm/micro_aot.html | 5 +
docs/how_to/work_with_microtvm/micro_autotune.html | 23 +-
docs/how_to/work_with_microtvm/micro_ethosu.html | 5 +
.../work_with_microtvm/micro_mlperftiny.html | 5 +
docs/how_to/work_with_microtvm/micro_pytorch.html | 10 +-
docs/how_to/work_with_microtvm/micro_tflite.html | 5 +
docs/how_to/work_with_microtvm/micro_train.html | 21 +-
docs/how_to/work_with_microtvm/micro_tvmc.html | 5 +
.../work_with_microtvm/sg_execution_times.html | 17 +-
docs/how_to/work_with_relay/build_gcn.html | 5 +
docs/how_to/work_with_relay/index.html | 5 +
.../how_to/work_with_relay/sg_execution_times.html | 13 +-
.../how_to/work_with_relay/using_external_lib.html | 5 +
.../work_with_relay/using_pipeline_executor.html | 5 +
docs/how_to/work_with_relay/using_relay_viz.html | 5 +
docs/how_to/work_with_schedules/extern_op.html | 5 +
docs/how_to/work_with_schedules/index.html | 5 +
docs/how_to/work_with_schedules/intrin_math.html | 7 +-
docs/how_to/work_with_schedules/reduction.html | 5 +
docs/how_to/work_with_schedules/scan.html | 5 +
.../work_with_schedules/schedule_primitives.html | 5 +
.../work_with_schedules/sg_execution_times.html | 21 +-
docs/how_to/work_with_schedules/tedd.html | 5 +
docs/how_to/work_with_schedules/tensorize.html | 5 +
docs/how_to/work_with_schedules/tuple_inputs.html | 5 +
docs/index.html | 5 +
docs/install/docker.html | 5 +
docs/install/from_source.html | 5 +
docs/install/index.html | 5 +
docs/install/nnpack.html | 5 +
docs/py-modindex.html | 5 +
docs/reference/api/links.html | 5 +
docs/reference/api/python/auto_scheduler.html | 9 +-
docs/reference/api/python/autotvm.html | 5 +
docs/reference/api/python/contrib.html | 5 +
docs/reference/api/python/driver.html | 5 +
docs/reference/api/python/error.html | 5 +
docs/reference/api/python/graph_executor.html | 5 +
docs/reference/api/python/index.html | 5 +
docs/reference/api/python/ir.html | 5 +
docs/reference/api/python/micro.html | 5 +
docs/reference/api/python/ndarray.html | 5 +
docs/reference/api/python/relay/analysis.html | 5 +
docs/reference/api/python/relay/backend.html | 5 +
.../api/python/relay/dataflow_pattern.html | 5 +
docs/reference/api/python/relay/frontend.html | 5 +
docs/reference/api/python/relay/image.html | 5 +
docs/reference/api/python/relay/index.html | 5 +
docs/reference/api/python/relay/nn.html | 5 +
docs/reference/api/python/relay/testing.html | 5 +
docs/reference/api/python/relay/transform.html | 5 +
docs/reference/api/python/relay/vision.html | 5 +
docs/reference/api/python/rpc.html | 5 +
docs/reference/api/python/runtime.html | 5 +
docs/reference/api/python/target.html | 5 +
docs/reference/api/python/te.html | 5 +
docs/reference/api/python/tir.html | 5 +
docs/reference/api/python/topi.html | 5 +
docs/reference/api/python/vta/index.html | 5 +
.../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 +-
docs/reference/api/typedoc/classes/instance.html | 58 ++--
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 +-
.../api/typedoc/classes/runtimecontext.html | 22 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
docs/reference/api/typedoc/classes/tvmarray.html | 16 +-
docs/reference/api/typedoc/classes/tvmobject.html | 12 +-
.../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 | 124 +++----
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/reference/langref/hybrid_script.html | 5 +
docs/reference/langref/index.html | 5 +
docs/reference/langref/relay_adt.html | 5 +
docs/reference/langref/relay_expr.html | 5 +
docs/reference/langref/relay_op.html | 5 +
docs/reference/langref/relay_pattern.html | 5 +
docs/reference/langref/relay_type.html | 5 +
docs/reference/publications.html | 5 +
docs/search.html | 5 +
docs/searchindex.js | 2 +-
docs/topic/microtvm/index.html | 5 +
docs/topic/vta/dev/config.html | 5 +
docs/topic/vta/dev/hardware.html | 5 +
docs/topic/vta/dev/index.html | 5 +
docs/topic/vta/index.html | 5 +
docs/topic/vta/install.html | 5 +
docs/topic/vta/tutorials/autotvm/index.html | 5 +
.../vta/tutorials/autotvm/sg_execution_times.html | 11 +-
docs/topic/vta/tutorials/autotvm/tune_alu_vta.html | 5 +
.../vta/tutorials/autotvm/tune_relay_vta.html | 5 +
.../tutorials/frontend/deploy_classification.html | 7 +-
.../vta/tutorials/frontend/deploy_detection.html | 7 +-
docs/topic/vta/tutorials/frontend/index.html | 5 +
.../vta/tutorials/frontend/sg_execution_times.html | 11 +-
docs/topic/vta/tutorials/index.html | 5 +
docs/topic/vta/tutorials/matrix_multiply.html | 5 +
.../vta/tutorials/optimize/convolution_opt.html | 5 +
docs/topic/vta/tutorials/optimize/index.html | 5 +
.../tutorials/optimize/matrix_multiply_opt.html | 5 +
.../vta/tutorials/optimize/sg_execution_times.html | 11 +-
docs/topic/vta/tutorials/sg_execution_times.html | 11 +-
docs/topic/vta/tutorials/vta_get_started.html | 5 +
docs/tutorial/auto_scheduler_matmul_x86.html | 10 +-
docs/tutorial/autotvm_matmul_x86.html | 25 +-
docs/tutorial/autotvm_relay_x86.html | 275 ++++++++--------
docs/tutorial/cross_compilation_and_rpc.html | 7 +-
docs/tutorial/index.html | 5 +
docs/tutorial/install.html | 5 +
docs/tutorial/intro_topi.html | 7 +-
docs/tutorial/introduction.html | 5 +
docs/tutorial/relay_quick_start.html | 5 +
docs/tutorial/sg_execution_times.html | 23 +-
docs/tutorial/tensor_expr_get_started.html | 48 +--
docs/tutorial/tensor_ir_blitz_course.html | 5 +
docs/tutorial/tvmc_command_line_driver.html | 5 +
docs/tutorial/tvmc_python.html | 5 +
docs/tutorial/uma.html | 5 +
289 files changed, 2240 insertions(+), 1772 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index a7d0b269c0..b0c19c3436 100644
Binary files a/docs/_images/sphx_glr_micro_train_001.png and b/docs/_images/sphx_glr_micro_train_001.png differ
diff --git a/docs/_images/sphx_glr_micro_train_thumb.png b/docs/_images/sphx_glr_micro_train_thumb.png
index 9c19979ef3..475ea5ff8a 100644
Binary files a/docs/_images/sphx_glr_micro_train_thumb.png and b/docs/_images/sphx_glr_micro_train_thumb.png differ
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index a3f439af9a..fd9693c215 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -318,7 +318,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 23.423 seconds)
+ **Total running time of the script:** ( 1 minutes 18.904 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_keras.rst.txt b/docs/_sources/how_to/compile_models/from_keras.rst.txt
index d4b281f3a5..c27b36a73f 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -232,7 +232,7 @@ Look up prediction top 1 index in 1000 class synset.
.. code-block:: none
Relay top-1 id: 285, class name: Egyptian cat
-
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 975ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 976ms/step
Keras top-1 id: 285, class name: Egyptian cat
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 7c7f72861e..08ebc2bfa2 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -116,7 +116,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip4ac2ee4b-cbe1-4033-bfb7-e35b9acb4f8a from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip2a72abed-73a2-4253-8595-3432c282a687 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
diff --git a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
index 1e5f055966..f37c4d6c57 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -121,7 +121,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 50.9MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 55.7MB/s]
54%|#####4 | 22.5M/41.5M [00:00<00:00, 60.2MB/s]
68%|######8 | 28.4M/41.5M [00:00<00:00, 50.4MB/s]
81%|######## | 33.4M/41.5M [00:00<00:00, 43.6MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 54.9MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 45.7MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 43.6MB/s]
55%|#####4 | 22.8M/41.5M [00:00<00:00, 51.8MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 54.9MB/s]
96%|#########6| 40.0M/41.5M [00:00<00:00, 55.6MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 54.4MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index 44b607a81f..102ce0266a 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -101,7 +101,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#7 | 7.99M/44.7M [00:00<00:00, 55.2MB/s]
36%|###5 | 16.0M/44.7M [00:00<00:00, 68.1MB/s]
58%|#####8 | 26.1M/44.7M [00:00<00:00, 63.3MB/s]
72%|#######2 | 32.3M/44.7M [00:00<00:00, 53.2MB/s]
90%|########9 | 40.0M/44.7M [00:00<00:00, 59.9MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 58.3MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#8 | 8.12M/44.7M [00:00<00:00, 79.3MB/s]
38%|###8 | 17.2M/44.7M [00:00<00:00, 88.2MB/s]
58%|#####8 | 26.1M/44.7M [00:00<00:00, 88.1MB/s]
86%|########5 | 38.3M/44.7M [00:00<00:00, 86.4MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 81.7MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
index f9ba1d1f88..f2b3923649 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -424,7 +424,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 24.554 seconds)
+ **Total running time of the script:** ( 1 minutes 24.191 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 7b067f96a7..ff7d5b22ef 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**06:46.121** total execution time for **how_to_compile_models** files:
+**06:38.473** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:24.554 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:24.191 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:23.423 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:18.904 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:55.628 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:56.127 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:38.515 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:37.838 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:31.835 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:32.077 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:31.420 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:31.591 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:28.429 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:27.200 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:26.801 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:25.799 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:22.814 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:22.044 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.702 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.703 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
index 56f0f585d2..dc1bc04430 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -727,7 +727,7 @@ well as provides information about the model's performance
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2646.0374 2645.5478 2649.8098 2643.5758 1.9627
+ 2686.6466 2686.2724 2691.1577 2683.8304 2.0018
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 4017c5076b..70cbfa50b9 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
@@ -437,7 +437,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.3725 15.5663 15.7423 14.6626 0.3860
+ 16.1432 16.0172 16.8460 15.9411 0.2694
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 66aaa0f0d6..22bf05b4a2 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
@@ -130,7 +130,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.99M/170M [00:00<00:04, 39.8MB/s]
7%|7 | 11.9M/170M [00:00<00:04, 40.3MB/s]
9%|9 | 16.0M/170M [00:00<00:03, 40.9MB/s]
14%|#3 | 23.7M/170M [00:00<00:03, 41.8MB/s]
16%|#6 | 27.7M/170M [00:00<00:03, 41.1MB/s]
19%|#8 | 32.0M/170M [00:00<00:03, 36.8MB/s]
21%|## | 35.5M/170M [00:01<00:04, 32.3MB/s]
24%|##3 | 40.0M/170M [00:01<00:04, 31.5MB/s]
28%|##8 | 48.0M/170M [00:01<00:03, 42.4MB/s]
33%|###2 | 56.0M/170M [00:01<00:02, 49.3MB/s]
38%|###7 | 64.1M/170M [00:01<00:01, 57.7MB/s]
42%|####2 | 72.0M/170M [00:01<00:01, 60.2MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 63.8MB/s]
52%|#####2 | 89.0M/170M [00:01<00:01, 71.7MB/s]
57%|#####6 | 96.7M/170M [00:01<00:01, 74.4MB/s]
61%|######1 | 104M/170M [00:02<00:00, 69.2MB/s]
68%|######8 | 116M/170M [00:02<00:00, 83.1MB/s
]
73%|#######2 | 124M/170M [00:02<00:00, 80.3MB/s]
79%|#######9 | 134M/170M [00:02<00:00, 88.8MB/s]
84%|########4 | 143M/170M [00:02<00:00, 89.4MB/s]
89%|########9 | 152M/170M [00:02<00:00, 82.6MB/s]
94%|#########4| 160M/170M [00:02<00:00, 76.9MB/s]
99%|#########8| 167M/170M [00:02<00:00, 76.9MB/s]
100%|##########| 170M/170M [00:02<00:00, 60.8MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.99M/170M [00:00<00:02, 80.5MB/s]
9%|9 | 16.0M/170M [00:00<00:02, 59.4MB/s]
14%|#4 | 24.0M/170M [00:00<00:02, 57.0MB/s]
19%|#8 | 32.0M/170M [00:00<00:02, 57.4MB/s]
25%|##5 | 42.6M/170M [00:00<00:02, 60.8MB/s]
31%|### | 52.0M/170M [00:00<00:01, 70.2MB/s]
35%|###4 | 59.1M/170M [00:00<00:01, 68.7MB/s]
40%|#### | 68.4M/170M [00:01<00:01, 76.5MB/s]
45%|####4 | 76.0M/170M [00:01<00:01, 70.6MB/s]
49%|####9 | 83.9M/170M [00:01<00:01, 73.9MB/s]
54%|#####3 | 91.2M/170M [00:01<00:01, 70.4MB/s]
58%|#####7 | 98.1M/170M [00:01<00:01, 64.7MB/s]
61%|######1 | 104M/170M [00:01<00:01, 62.3MB/s]
70%|####### | 119M/170M [00:01<00:00, 87.0MB/s]
75%|#######5 | 128M/170M [00:01<00:00, 72.3MB/s]
80%|######## | 136M/170M [00:02<00:00, 73.9MB/s]
85%|########4 | 144M/170M [00:02<00:00, 68.7MB/s]
89%|########9 | 152M/170M [00:02<00:00, 68.9MB/s]
94%|#########4| 160M/170M [00:02<00:00, 72.1MB/s]
98%|#########8| 167M/170M [00:02<00:00, 71.2MB/s]
100%|##########| 170M/170M [00:02<00:00, 69.4MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -299,7 +299,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 27.290 seconds)
+ **Total running time of the script:** ( 3 minutes 42.915 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 ec6a3091b1..8ab5552a41 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -227,7 +227,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 46.2MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 70.5MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 61.1MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 86.1MB/s]
@@ -409,7 +409,7 @@ 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)
- 88.2023 88.0587 92.6748 87.9495 0.5394
+ 90.1994 90.1297 93.5782 90.0036 0.3756
@@ -458,7 +458,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 15.071 seconds)
+ **Total running time of the script:** ( 1 minutes 17.695 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 6247573bac..18a9c48874 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
@@ -423,7 +423,7 @@ 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)
- 117.6103 117.5951 118.2696 116.8346 0.2654
+ 120.2610 120.2151 123.7796 119.4926 0.4966
@@ -460,7 +460,7 @@ 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 34.549 seconds)
+ **Total running time of the script:** ( 2 minutes 36.418 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 233e16ff25..2b79a8a454 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -257,7 +257,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 34.455 seconds)
+ **Total running time of the script:** ( 1 minutes 34.272 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 c1bffa629a..09202e0b3a 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
@@ -170,7 +170,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
5%|5 | 7266/132723 [00:00<00:01, 72651.58KB/s]
12%|#2 | 16240/132723 [00:00<00:01, 82698.75KB/s]
19%|#8 | 25100/132723 [00:00<00:01, 85390.02KB/s]
25%|##5 | 33640/132723 [00:00<00:01, 53706.78KB/s]
32%|###1 | 41925/132723 [00:00<00:01, 61334.45KB/s]
37%|###7 | 49140/132723 [00:00<00:01, 55995.95KB/s]
42%|####1 | 55453/132723 [00:00<00:01, 56391.18KB/s]
48%|####8 | 64353/132723 [00:01<00:01, 64891.31KB/s]
55%|#####5 | 73235/132723 [00:01<00:00, 71382.93KB/s]
62%|######1 | 82156/132723 [00:01<00:00, 76362.36KB/s]
69%|######8 | 91134/132723 [00:01<00:00, 80187.74KB/s]
75%|#######5 | 100112/132723 [00:01<00:00, 82962.58KB/s]
82%|########2 | 109131/132723 [00:01<00:00, 85075.34KB/s]
89%|########8 | 118025/132723 [00:01<00:00, 86206.52KB/s]
96%|#########5| 127017/132723 [00:01<00:00, 87302.26KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 74612.79KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|3 | 5222/132723 [00:00<00:02, 52212.33KB/s]
9%|9 | 12133/132723 [00:00<00:01, 62148.35KB/s]
15%|#4 | 19699/132723 [00:00<00:01, 68315.85KB/s]
21%|##1 | 28271/132723 [00:00<00:01, 75183.22KB/s]
28%|##7 | 36713/132723 [00:00<00:01, 78509.17KB/s]
34%|###4 | 45195/132723 [00:00<00:01, 80643.66KB/s]
40%|#### | 53752/132723 [00:00<00:00, 82249.25KB/s]
47%|####6 | 62185/132723 [00:00<00:00, 82910.08KB/s]
53%|#####3 | 70706/132723 [00:00<00:00, 83626.59KB/s]
60%|#####9 | 79289/132723 [00:01<00:00, 84304.74KB/s]
66%|######6 | 87817/132723 [00:01<00:00, 84599.64KB/s]
73%|#######2 | 96277/132723 [00:01<00:00, 84420.51KB/s]
79%|#######8 | 104720/132723 [00:01<00:00, 84150.02KB/s]
85%|########5 | 113339/132723 [00:01<00:00, 84760.09KB/s]
92%|#########1| 121919/132723 [00:01<00:00, 85069.66KB/s]
98%|########
#8| 130572/132723 [00:01<00:00, 85506.30KB/s]
100%|##########| 132723/132723 [00:01<00:00, 81499.18KB/s]
@@ -246,7 +246,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 43.632 seconds)
+ **Total running time of the script:** ( 3 minutes 50.963 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 3927f0b10f..1b6063ce3b 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**15:08.228** total execution time for **how_to_deploy_models** files:
+**15:38.964** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:43.632 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:50.963 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:27.290 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:42.915 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:34.549 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:36.418 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:34.455 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:34.272 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:15.071 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:17.695 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:55.824 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:56.798 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:41.770 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:43.077 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:27.994 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:28.643 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:27.637 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:28.177 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 9442ca3512..73adc04615 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
@@ -463,7 +463,7 @@ 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.zip4cbfe758-7622-491b-bd51-a4e4afe01bb7 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip185f8114-67e0-49b9-a251-870552496085 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
diff --git a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
index 1cb00893fc..b2ab95476d 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:54.377** total execution time for **how_to_extend_tvm** files:
+**00:54.888** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:50.575 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:50.811 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.720 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.767 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.074 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.302 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 9878f08175..14998ab1e5 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
@@ -220,10 +220,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 22781us [22781us] (49.75%; 49.75%)
- FoldScaleAxis: 23006us [7us] (50.25%; 50.25%)
- FoldConstant: 22999us [1674us] (50.23%; 99.97%)
- InferType: 21325us [21325us] (46.57%; 92.72%)
+ InferType: 22179us [22179us] (48.78%; 48.78%)
+ FoldScaleAxis: 23284us [7us] (51.22%; 51.22%)
+ FoldConstant: 23277us [1666us] (51.20%; 99.97%)
+ InferType: 21611us [21611us] (47.54%; 92.84%)
@@ -262,10 +262,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 21244us [21244us] (47.84%; 47.84%)
- FoldScaleAxis: 23167us [5us] (52.16%; 52.16%)
- FoldConstant: 23162us [1659us] (52.15%; 99.98%)
- InferType: 21502us [21502us] (48.42%; 92.84%)
+ InferType: 21627us [21627us] (48.34%; 48.34%)
+ FoldScaleAxis: 23110us [5us] (51.66%; 51.66%)
+ FoldConstant: 23104us [1712us] (51.65%; 99.98%)
+ InferType: 21393us [21393us] (47.82%; 92.59%)
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 065cd58594..7506c7249f 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
@@ -331,7 +331,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 48.641311 ms
+ Convolution: 54.343681 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 266359228d..a5c6912fc2 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
@@ -608,7 +608,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 13.350146 ms
+ conv2d with tensor core: 12.903427 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 692e8d88d4..134e4713e2 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -134,8 +134,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.016757
- Baseline: 3.303109
+ Numpy running time: 0.018578
+ Baseline: 3.402711
@@ -227,7 +227,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.295757
+ Opt1: 0.317495
@@ -318,7 +318,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.328162
+ Opt2: 0.343500
@@ -406,7 +406,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.114045
+ Opt3: 0.118646
@@ -523,7 +523,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109349
+ Opt4: 0.109404
@@ -635,7 +635,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.101966
+ Opt5: 0.111543
@@ -748,7 +748,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.133909
+ Opt6: 0.146951
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 b10ea8ee00..71b2d63658 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:33.378** total execution time for **how_to_optimize_operators** files:
+**00:35.493** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:30.829 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.674 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.532 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.646 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.017 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.173 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
index 7a4cdafe00..fe1ae7f93b 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**09:46.825** total execution time for **how_to_tune_with_autoscheduler** files:
+**10:04.072** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 06:00.304 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 06:10.908 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:39.930 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:43.475 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:07.316 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:08.927 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:32.242 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:32.698 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:13.827 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.341 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.206 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.723 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
index 4ba74c6eec..9723122a12 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
@@ -209,6 +209,13 @@ file and apply it.
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+ .T
+
+
@@ -244,162 +251,36 @@ cooperative fetching, unrolling and operator fusion.
def main(data: T.Buffer((1, 512, 7, 7), "float32"), kernel: T.Buffer((512, 512, 3, 3), "float32"), bias: T.Buffer((1, 512, 1, 1), "float32"), compute: T.Buffer((1, 512, 7, 7), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
blockIdx_x = T.env_thread("blockIdx.x")
- T.launch_thread(blockIdx_x, 32)
- conv2d_nchw = T.allocate([14], "float32", "local")
- pad_temp_shared = T.allocate([1008], "float32", "shared")
- kernel_shared = T.allocate([768], "float32", "shared")
+ T.launch_thread(blockIdx_x, 16)
+ conv2d_nchw = T.allocate([7], "float32", "local")
+ pad_temp_shared = T.allocate([324], "float32", "shared")
+ kernel_shared = T.allocate([1152], "float32", "shared")
threadIdx_x = T.env_thread("threadIdx.x")
- T.launch_thread(threadIdx_x, 56)
- conv2d_nchw_1 = T.Buffer((14,), data=conv2d_nchw, scope="local", align=32)
- conv2d_nchw_1[0] = T.float32(0)
- conv2d_nchw_1[1] = T.float32(0)
- conv2d_nchw_1[2] = T.float32(0)
- conv2d_nchw_1[3] = T.float32(0)
- conv2d_nchw_1[4] = T.float32(0)
- conv2d_nchw_1[5] = T.float32(0)
- conv2d_nchw_1[6] = T.float32(0)
- conv2d_nchw_1[7] = T.float32(0)
- conv2d_nchw_1[8] = T.float32(0)
- conv2d_nchw_1[9] = T.float32(0)
- conv2d_nchw_1[10] = T.float32(0)
- conv2d_nchw_1[11] = T.float32(0)
- conv2d_nchw_1[12] = T.float32(0)
- conv2d_nchw_1[13] = T.float32(0)
- for rc_outer_outer, rx_outer_outer in T.grid(32, 3):
- cse_var_2: T.int32 = rc_outer_outer * 784
- cse_var_1: T.int32 = rc_outer_outer * 144
- threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.Buffer((1008,), data=pad_temp_shared, scope="shared")
- data_1 = T.Buffer((25088,), data=data.data)
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 56] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 56) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 112] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 112) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 168] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 168) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 224] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 224) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 280] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 280) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 336] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 336) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 392] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 2) % 9 and (threadIdx_x_1 // 7 + 2) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 392) // 63 * 49 + (threadIdx_x_1 // 7 + 2) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 448] = T.if_then_else(threadIdx_x_1 < 49 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 448) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 504] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer + 384], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 560] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 560) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 616] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 616) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 672] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 672) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 728] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 728) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 784] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 784) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 840] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 840) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 896] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 2) % 9 and (threadIdx_x_1 // 7 + 2) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 896) // 63 * 49 + (threadIdx_x_1 // 7 + 2) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 952] = T.if_then_else(threadIdx_x_1 < 49 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 952) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
- threadIdx_x_2 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((768,), data=kernel_shared, scope="shared")
- kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[(threadIdx_x_2 + 56) // 48 * 48 + (threadIdx_x_2 + 8) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 56) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[(threadIdx_x_2 + 112) // 48 * 48 + (threadIdx_x_2 + 16) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 112) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 16) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[(threadIdx_x_2 + 168) // 48 * 48 + (threadIdx_x_2 // 3 + 8) % 16 * 3 + threadIdx_x_2 % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 168) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 // 3 + 8) % 16 * 9 + threadIdx_x_2 % 3 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[(threadIdx_x_2 + 224) // 48 * 48 + (threadIdx_x_2 + 32) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 224) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 32) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[(threadIdx_x_2 + 280) // 48 * 48 + (threadIdx_x_2 + 40) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 280) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 40) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 336] = kernel_1[blockIdx_x * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + rx_outer_outer + 32256]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[(threadIdx_x_2 + 392) // 48 * 48 + (threadIdx_x_2 + 8) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 392) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[(threadIdx_x_2 + 448) // 48 * 48 + (threadIdx_x_2 + 16) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 448) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 16) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[(threadIdx_x_2 + 504) // 48 * 48 + (threadIdx_x_2 // 3 + 8) % 16 * 3 + threadIdx_x_2 % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 504) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 // 3 + 8) % 16 * 9 + threadIdx_x_2 % 3 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[(threadIdx_x_2 + 560) // 48 * 48 + (threadIdx_x_2 + 32) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 560) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 32) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[(threadIdx_x_2 + 616) // 48 * 48 + (threadIdx_x_2 + 40) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 616) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 40) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 672] = kernel_1[blockIdx_x * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + rx_outer_outer + 64512]
- with T.launch_thread(threadIdx_x_2, 56):
- if T.likely(threadIdx_x_2 < 40):
- kernel_shared_1[(threadIdx_x_2 + 728) // 48 * 48 + (threadIdx_x_2 + 8) // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 728) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + rx_outer_outer]
- for rc_outer_inner, ry_outer_inner in T.grid(4, 3):
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 3] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 4] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 5] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 6] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 3]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 3]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 3]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 66] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 3]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 67] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 3]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 68] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 3]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 69] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 3]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 6]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 127] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 6]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 128] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 6]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 129] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 6]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 130] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 6]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 131] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 6]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 132] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 6]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 189] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 9]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 190] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 9]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 191] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 9]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 192] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 9]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 193] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 9]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 194] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 9]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 195] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 9]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 48]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 48]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 48]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 3] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 48]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 4] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 48]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 5] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 48]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 6] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 48]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 51]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 51]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 51]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 66] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 51]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 67] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 51]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 68] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 51]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 69] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 51]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 54]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 127] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 54]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 128] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 54]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 129] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 54]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 130] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 54]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 131] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 54]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 132] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 54]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 189] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 57]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 190] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 57]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 191] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 57]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 192] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 57]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 193] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 57]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 194] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 57]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 195] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 57]
- for i1_inner, i3_inner in T.grid(2, 7):
+ T.launch_thread(threadIdx_x, 224)
+ conv2d_nchw_1 = T.Buffer((7,), data=conv2d_nchw, scope="local", align=16)
+ for xx_inner_init in range(7):
+ conv2d_nchw_1[xx_inner_init] = T.float32(0)
+ for rc_outer_outer in range(128):
+ pad_temp_shared_1 = T.Buffer((324,), data=pad_temp_shared, scope="shared")
+ for ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer in range(2):
+ threadIdx_x_1 = T.env_thread("threadIdx.x")
+ T.launch_thread(threadIdx_x_1, 224)
+ if T.likely(ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56 + threadIdx_x_1 // 4 < 81):
+ data_1 = T.Buffer((25088,), data=data.data)
+ pad_temp_shared_1[ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224 + threadIdx_x_1] = T.if_then_else(9 <= (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 62 + threadIdx_x_1) % 81 and (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 62 + threadIdx_x_1) % 81 < 72 and 1 <= (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8 + threadIdx_x_1) % 9 and (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8 + threadIdx_x_1) % 9 < 8, data_1[rc_outer_outer * 196 + (ax0_ax1_f [...]
+ kernel_shared_1 = T.Buffer((1152,), data=kernel_shared, scope="shared")
+ for ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer in range(6):
+ threadIdx_x_1 = T.env_thread("threadIdx.x")
+ T.launch_thread(threadIdx_x_1, 224)
+ if T.likely(ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7 + threadIdx_x_1 // 32 < 36):
+ kernel_1 = T.Buffer((2359296,), data=kernel.data)
+ kernel_shared_1[ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224 + threadIdx_x_1] = kernel_1[blockIdx_x * 147456 + (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56 + threadIdx_x_1 // 4) // 9 * 4608 + rc_outer_outer * 36 + (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8 + threadIdx_x_1) % 36 // 3 * 3 + (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2 + threadIdx_x_1) % 3]
+ for rc_inner, ry_inner, rx_inner, xx_inner in T.grid(4, 3, 3, 7):
+ conv2d_nchw_1[xx_inner] = conv2d_nchw_1[xx_inner] + pad_temp_shared_1[rc_inner * 81 + ry_inner * 9 + threadIdx_x % 7 * 9 + xx_inner + rx_inner] * kernel_shared_1[threadIdx_x // 7 * 36 + rc_inner * 9 + ry_inner * 3 + rx_inner]
+ for i3_inner in range(7):
compute_1 = T.Buffer((25088,), data=compute.data)
bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + i3_inner] = T.max(conv2d_nchw_1[i1_inner * 7 + i3_inner] + bias_1[blockIdx_x * 16 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 1568 + threadIdx_x * 7 + i3_inner] = T.max(conv2d_nchw_1[i3_inner] + bias_1[blockIdx_x * 32 + threadIdx_x // 7], T.float32(0))
@@ -449,7 +330,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.371 ms
+ Execution time of this operator: 0.342 ms
@@ -498,8 +379,8 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+ conv2d_nchw_ff_o_o_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_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
@@ -510,17 +391,17 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+ 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_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
@@ -546,14 +427,14 @@ 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=56)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 0)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -571,128 +452,38 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[1008];
- __shared__ float kernel_shared[768];
- conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 784) + ((int)threadIdx.x)) + rx_outer_outer) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 56) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 112) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 168)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 168) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 224) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 280) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 336) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = ((((((int)threadIdx.x) < 49) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 448) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 504)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 784) + ((int)threadIdx.x)) + rx_outer_outer) + 384)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 560) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 616) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 672) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 728)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 728) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 840)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 840) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 896) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 952)] = ((((((int)threadIdx.x) < 49) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 952) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + rx_outer_outer)];
- kernel_shared[(((((((int)threadIdx.x) + 56) / 48) * 48) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((((((int)threadIdx.x) + 112) / 48) * 48) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((((((int)threadIdx.x) + 168) / 48) * 48) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 3)) + (((int)threadIdx.x) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((((((int)threadIdx.x) + 224) / 48) * 48) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((((((int)threadIdx.x) + 280) / 48) * 48) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + rx_outer_outer) + 32256)];
- kernel_shared[(((((((int)threadIdx.x) + 392) / 48) * 48) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((((((int)threadIdx.x) + 448) / 48) * 48) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((((((int)threadIdx.x) + 504) / 48) * 48) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 3)) + (((int)threadIdx.x) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 504) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((((((int)threadIdx.x) + 560) / 48) * 48) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((((((int)threadIdx.x) + 616) / 48) * 48) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 616) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + rx_outer_outer) + 64512)];
- if (((int)threadIdx.x) < 40) {
- kernel_shared[(((((((int)threadIdx.x) + 728) / 48) * 48) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 728) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ extern "C" __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[7];
+ __shared__ float pad_temp_shared[324];
+ __shared__ float kernel_shared[1152];
+ for (int xx_inner_init = 0; xx_inner_init < 7; ++xx_inner_init) {
+ conv2d_nchw[xx_inner_init] = 0.000000e+00f;
+ }
+ for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
+ __syncthreads();
+ for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 2; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) < 81) {
+ pad_temp_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224) + ((int)threadIdx.x))] = (((((9 <= (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 62) + ((int)threadIdx.x)) % 81)) && ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 62) + ((int)threadIdx.x)) % 81) < 72)) && (1 <= (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + ((int)threadIdx.x)) % 9))) && ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + ((int)threadIdx.x)) % 9) < 8)) ? data[(((((r [...]
+ }
+ }
+ for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 < 6; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1) {
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 7) + (((int)threadIdx.x) >> 5)) < 36) {
+ kernel_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 224) + ((int)threadIdx.x))] = kernel[(((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 56) + (((int)threadIdx.x) >> 2)) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 8) + ((int)threadIdx.x)) % 36) / 3) * 3)) + (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 2) + ((int)threadIdx.x)) % 3))];
}
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 64)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 65)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 66)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 67)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 68)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 69)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 127)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 128)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 129)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 130)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 131)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 132)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 190)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 191)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 192)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 193)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 194)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 195)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 48)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 48)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 48)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 48)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 48)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 48)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 48)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 51)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 64)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 51)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 65)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 51)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 66)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 51)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 67)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 51)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 68)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 51)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 69)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 51)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 54)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 127)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 54)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 128)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 54)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 129)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 54)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 130)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 54)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 131)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 54)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 132)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 54)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 57)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 190)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 57)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 191)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 57)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 192)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 57)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 193)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 57)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 194)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 57)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 195)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 57)]));
+ }
+ __syncthreads();
+ for (int rc_inner = 0; rc_inner < 4; ++rc_inner) {
+ for (int ry_inner = 0; ry_inner < 3; ++ry_inner) {
+ for (int rx_inner = 0; rx_inner < 3; ++rx_inner) {
+ for (int xx_inner = 0; xx_inner < 7; ++xx_inner) {
+ conv2d_nchw[xx_inner] = (conv2d_nchw[xx_inner] + (pad_temp_shared[(((((rc_inner * 81) + (ry_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_inner) + rx_inner)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_inner * 9)) + (ry_inner * 3)) + rx_inner)]));
+ }
}
}
}
}
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- }
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
}
}
@@ -752,7 +543,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 6 minutes 0.304 seconds)
+ **Total running time of the script:** ( 6 minutes 10.908 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 bd605a39bd..9bb8ec1f0a 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.9344 7.9381 7.9475 7.9175 0.0125
+ 7.8981 7.8975 7.9038 7.8931 0.0044
@@ -675,7 +675,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.316 seconds)
+ **Total running time of the script:** ( 1 minutes 8.927 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
index dfa81d8a06..9feb39a472 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -666,7 +666,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 723.1857 720.7894 728.1370 720.6308 3.5016
+ 755.8260 752.9500 763.6801 750.8478 5.6197
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 39.930 seconds)
+ **Total running time of the script:** ( 1 minutes 43.475 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 73c3d46645..3ebd2a49ae 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
@@ -392,23 +392,82 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
for i0_outer_i1_outer_fused in T.parallel(256):
compute_1 = T.allocate([256], "float32", "global")
compute_2 = T.Buffer((256,), data=compute_1)
- for nb_j_inner in range(2):
- for i_inner_init, j_init in T.grid(8, 16):
- compute_2[i_inner_init * 32 + nb_j_inner * 16 + j_init] = T.float32(0)
- for elem_idx, i_inner, j in T.grid(T.let(cse_var_1, i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner, placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]), 8, 16):
- cse_var_1 = T.int32()
+ for i_outer_inner in range(16):
+ cse_var_2: T.int32 = i_outer_inner * 16
+ cse_var_1: T.int32 = i0_outer_i1_outer_fused % 64 // 2
+ compute_2[cse_var_2] = T.float32(0)
+ compute_2[cse_var_2 + 1] = T.float32(0)
+ compute_2[cse_var_2 + 2] = T.float32(0)
+ compute_2[cse_var_2 + 3] = T.float32(0)
+ compute_2[cse_var_2 + 4] = T.float32(0)
+ compute_2[cse_var_2 + 5] = T.float32(0)
+ compute_2[cse_var_2 + 6] = T.float32(0)
+ compute_2[cse_var_2 + 7] = T.float32(0)
+ compute_2[cse_var_2 + 8] = T.float32(0)
+ compute_2[cse_var_2 + 9] = T.float32(0)
+ compute_2[cse_var_2 + 10] = T.float32(0)
+ compute_2[cse_var_2 + 11] = T.float32(0)
+ compute_2[cse_var_2 + 12] = T.float32(0)
+ compute_2[cse_var_2 + 13] = T.float32(0)
+ compute_2[cse_var_2 + 14] = T.float32(0)
+ compute_2[cse_var_2 + 15] = T.float32(0)
+ for elem_idx in range(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
- cse_var_3: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
- cse_var_2: T.int32 = i_inner * 32 + nb_j_inner * 16 + j
placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
placeholder_7 = T.Buffer((32768,), data=placeholder.data)
placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
- compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer_i1_outer_fused // 16 * 2048 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
- for i0_inner, i1_inner in T.grid(8, 32):
- cse_var_4: T.int32 = i0_outer_i1_outer_fused // 16 * 4096 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32 + i1_inner
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_3: T.int32 = cse_var_2 + 1
+ compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_4: T.int32 = cse_var_2 + 2
+ compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_5: T.int32 = cse_var_2 + 3
+ compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_6: T.int32 = cse_var_2 + 4
+ compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_7: T.int32 = cse_var_2 + 5
+ compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 5] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_8: T.int32 = cse_var_2 + 6
+ compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 6] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_9: T.int32 = cse_var_2 + 7
+ compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 7] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_10: T.int32 = cse_var_2 + 8
+ compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_11: T.int32 = cse_var_2 + 9
+ compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_12: T.int32 = cse_var_2 + 10
+ compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_13: T.int32 = cse_var_2 + 11
+ compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_14: T.int32 = cse_var_2 + 12
+ compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_15: T.int32 = cse_var_2 + 13
+ compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 5] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_16: T.int32 = cse_var_2 + 14
+ compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 6] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_17: T.int32 = cse_var_2 + 15
+ compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 7] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
+ for i0_inner in range(32):
+ cse_var_18: T.int32 = i0_outer_i1_outer_fused // 64 * 16384 + i0_inner * 512 + i0_outer_i1_outer_fused % 64 * 8
compute_3 = T.Buffer((65536,), data=compute.data)
placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
- compute_3[cse_var_4] = T.max(compute_2[i0_inner * 32 + i1_inner] + placeholder_5[cse_var_4], T.float32(0))
+ compute_3[cse_var_18:cse_var_18 + 8] = T.max(compute_2[i0_inner * 8:i0_inner * 8 + 8] + placeholder_5[cse_var_18:cse_var_18 + 8], T.Broadcast(T.float32(0), 8))
@@ -458,7 +517,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.584 ms
+ Execution time of this operator: 2.288 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 2d1cb8a0fc..0a32246a0c 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:53.891** total execution time for **how_to_tune_with_autotvm** files:
+**00:42.384** total execution time for **how_to_tune_with_autotvm** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:53.856 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:42.349 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.007 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.004 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 12b418bd79..cec83c0065 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
@@ -268,7 +268,8 @@ for this template
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ No: 1 GFLOPS: 127.62/127.62 result: MeasureResult(costs=(0.001813984985074627,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.11116623878479, timestamp=1677845860.7700906) [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1215527
+ No: 2 GFLOPS: 0.00/127.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -390,8 +391,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10228095
- No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8515723
+ No: 3 GFLOPS: 18.15/127.62 result: MeasureResult(costs=(0.01275651888888889,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.876296281814575, timestamp=1677845863.33124) [('tile_f', [-1, 16, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8033368
+ No: 4 GFLOPS: 0.00/127.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -513,8 +515,10 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10091340
- No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3518318
+ No: 5 GFLOPS: 6.24/127.62 result: MeasureResult(costs=(0.03711889625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.749978065490723, timestamp=1677845869.7278771) [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8330306
+ No: 6 GFLOPS: 3.87/127.62 result: MeasureResult(costs=(0.059764766500000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.930164098739624, timestamp=1677845870.9373977) [('tile_f', [-1, 4, 1, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1780867
+ No: 7 GFLOPS: 0.00/127.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -636,9 +640,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2161210
- No: 4 GFLOPS: 6.90/6.90 result: MeasureResult(costs=(0.03354587925,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.678717613220215, timestamp=1677805465.9553194) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7951583
- No: 5 GFLOPS: 0.00/6.90 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 64, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4181808
+ No: 8 GFLOPS: 0.00/127.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -760,10 +763,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4482313
- No: 6 GFLOPS: 8.62/8.62 result: MeasureResult(costs=(0.026846216,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.123527765274048, timestamp=1677805476.8576145) [('tile_f', [-1, 4, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1862842
- No: 7 GFLOPS: 4.16/8.62 result: MeasureResult(costs=(0.055586814750000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=9.57439661026001, timestamp=1677805478.0032456) [('tile_f', [-1, 16, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3650519
- No: 8 GFLOPS: 0.00/8.62 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7690881
+ No: 9 GFLOPS: 0.00/127.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -885,8 +886,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,449315
- No: 9 GFLOPS: 0.00/8.62 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7306692
+ No: 10 GFLOPS: 0.00/127.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1008,9 +1009,10 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6863773
- No: 10 GFLOPS: 34.59/34.59 result: MeasureResult(costs=(0.006693454941176471,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1895654201507568, timestamp=1677805479.3749352) [('tile_f', [-1, 2, 64, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5368095
- No: 11 GFLOPS: 0.00/34.59 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9536542
+ No: 11 GFLOPS: 41.77/127.62 result: MeasureResult(costs=(0.0055423053181818185,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0154471397399902, timestamp=1677845874.6394875) [('tile_f', [-1, 1, 8, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1212101
+ No: 12 GFLOPS: 179.25/179.25 result: MeasureResult(costs=(0.0012915266693548386,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.900968074798584, timestamp=1677845875.6529262) [('tile_f', [-1, 1, 32, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8728850
+ No: 13 GFLOPS: 0.00/179.25 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1132,8 +1134,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9810008
- No: 12 GFLOPS: 0.00/34.59 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,61297
+ No: 14 GFLOPS: 18.54/179.25 result: MeasureResult(costs=(0.012488249,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4176852703094482, timestamp=1677845877.2635472) [('tile_f', [-1, 1, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6778174
+ No: 15 GFLOPS: 0.00/179.25 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1255,8 +1258,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4052515
- No: 13 GFLOPS: 0.00/34.59 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,822895
+ No: 16 GFLOPS: 0.00/179.25 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1378,9 +1381,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1925144
- No: 14 GFLOPS: 8.18/34.59 result: MeasureResult(costs=(0.028291608750000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7224013805389404, timestamp=1677805481.3147876) [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6877563
- No: 15 GFLOPS: 0.00/34.59 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8072379
+ No: 17 GFLOPS: 0.00/179.25 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1502,8 +1504,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3737494
- No: 16 GFLOPS: 0.00/34.59 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,53422
+ No: 18 GFLOPS: 0.00/179.25 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1625,8 +1627,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10150224
- No: 17 GFLOPS: 0.00/34.59 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2240825
+ No: 19 GFLOPS: 0.00/179.25 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1748,149 +1750,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6075407
- No: 18 GFLOPS: 149.79/149.79 result: MeasureResult(costs=(0.0015454607605633803,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.803270101547241, timestamp=1677805492.3559427) [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7983936
- No: 19 GFLOPS: 0.00/149.79 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
- res = future.result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
- return self.__get_result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
- raise self._exception
- File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
- result = self.fn(*self.args, **self.kwargs)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
- worker = lambda *args: self._worker_run(*args)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
- return proc.recv()
- File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
- raise TimeoutError()
- TimeoutError
-
- [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8917762
- No: 20 GFLOPS: 0.00/149.79 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target=target, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1734
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:451
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1753
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1697
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1621
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
- Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1734
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:451
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1753
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1697
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1621
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1993755
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 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,10013435
+ No: 20 GFLOPS: 35.83/179.25 result: MeasureResult(costs=(0.006461237818181819,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.405557155609131, timestamp=1677845879.9267914) [('tile_f', [-1, 1, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8213580
@@ -1945,9 +1806,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7983936
+ [('tile_f', [-1, 1, 32, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8728850
Finish loading 20 records
- Time cost of this operator: 0.001374
+ Time cost of this operator: 0.001636
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 a7f741378d..3149c903f7 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
@@ -360,10 +360,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.8 98.74 (1, 2, 10, 10, 3) 2 1 [315.8]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.057 0.956 (1, 6, 10, 10) 1 1 [3.057]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.972 0.304 (1, 1, 10, 10, 3) 1 1 [0.972]
- Total_time - 319.828 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 317.0 98.733 (1, 2, 10, 10, 3) 2 1 [317.0]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.113 0.97 (1, 6, 10, 10) 1 1 [3.113]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.954 0.297 (1, 1, 10, 10, 3) 1 1 [0.954]
+ Total_time - 321.067 - - - - -
@@ -428,10 +428,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.3 97.306 (1, 6, 10, 10, 1) 2 1 [100.3]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.8 1.746 (1, 6, 10, 10) 1 1 [1.8]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.977 0.948 (1, 1, 10, 10, 3) 1 1 [0.977]
- Total_time - 103.077 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.7 97.357 (1, 6, 10, 10, 1) 2 1 [100.7]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.76 1.701 (1, 6, 10, 10) 1 1 [1.76]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.974 0.942 (1, 1, 10, 10, 3) 1 1 [0.974]
+ Total_time - 103.433 - - - - -
@@ -439,7 +439,7 @@ Timing the tuned program
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.412 seconds)
+ **Total running time of the script:** ( 1 minutes 21.746 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_autotune.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index acd1c0432c..ce5b68e52e 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -118,7 +118,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
61%|###### | 2.09M/3.42M [00:00<00:00, 18.5MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 28.0MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 52.2MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -324,7 +324,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 18.622 seconds)
+ **Total running time of the script:** ( 1 minutes 19.297 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index d6132aa5fb..cccd5cd33c 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -218,7 +218,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmpk2282udu/images/random'
+ '/tmp/tmpqr1cnsj8/images/random'
@@ -309,7 +309,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0]
+ :alt: [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -318,8 +318,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpk2282udu/images/target contains 8144 images
- /tmp/tmpk2282udu/images/random contains 5000 images
+ /tmp/tmpqr1cnsj8/images/target contains 8144 images
+ /tmp/tmpqr1cnsj8/images/random contains 5000 images
@@ -494,13 +494,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2177 - accuracy: 0.9228 - val_loss: 0.1116 - val_accuracy: 0.9619 - 47s/epoch - 144ms/step
+ 328/328 - 47s - loss: 0.2775 - accuracy: 0.9126 - val_loss: 0.1314 - val_accuracy: 0.9513 - 47s/epoch - 145ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.1026 - accuracy: 0.9638 - val_loss: 0.1258 - val_accuracy: 0.9554 - 43s/epoch - 131ms/step
+ 328/328 - 43s - loss: 0.1074 - accuracy: 0.9584 - val_loss: 0.1195 - val_accuracy: 0.9622 - 43s/epoch - 132ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0759 - accuracy: 0.9719 - val_loss: 0.0953 - val_accuracy: 0.9683 - 43s/epoch - 131ms/step
+ 328/328 - 43s - loss: 0.0642 - accuracy: 0.9768 - val_loss: 0.1480 - val_accuracy: 0.9520 - 43s/epoch - 132ms/step
- <keras.callbacks.History object at 0x7fb43c50cdd0>
+ <keras.callbacks.History object at 0x7f01b5763990>
@@ -861,7 +861,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 19.081 seconds)
+ **Total running time of the script:** ( 4 minutes 32.137 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_train.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
index be0f352a70..5041c97a66 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**08:17.037** total execution time for **how_to_work_with_microtvm** files:
+**07:30.675** total execution time for **how_to_work_with_microtvm** files:
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:19.081 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:32.137 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:21.412 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:21.746 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:18.622 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:19.297 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:10.176 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:10.141 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:07.747 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:07.354 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.000 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 5cb5f5236a..bc030ce45e 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:46.432** total execution time for **how_to_work_with_relay** files:
+**00:46.610** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:33.458 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:34.055 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:11.251 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.863 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.717 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.686 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.006 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index 2559c7cc58..675a393c5d 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -264,7 +264,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7fb2ed0f99e0>
+ <function my_cuda_math_rule at 0x7f0052826440>
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 b58bead3db..d62edbf859 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:08.481** total execution time for **how_to_work_with_schedules** files:
+**00:07.815** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.710 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.254 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.423 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.179 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.570 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.582 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.553 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.569 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.115 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.118 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.051 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.054 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.033 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.032 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.027 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
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 83dcaa4cb0..bfad30a6cb 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:30.775** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:31.361** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:30.768 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:31.355 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 7c8dbb24a3..735289a1ca 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -293,7 +293,7 @@ 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 32.80s!
+ resnet18_v1 inference graph built in 33.49s!
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 a3fb7a9319..eef2fbcda8 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -337,7 +337,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 22.77s!
+ yolov3-tiny inference graph built in 22.65s!
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 8ca3772430..f708e237e9 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**01:39.308** total execution time for **topic_vta_tutorials_frontend** files:
+**01:39.770** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:49.681 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:50.304 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.627 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.465 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
index 9c9f301a25..a017b25cac 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:03.138** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.219** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.690 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.768 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.448 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.451 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
index cd1d9738f3..b5f21442ac 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:00.764** total execution time for **topic_vta_tutorials** files:
+**00:00.768** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.399 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.396 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.365 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.372 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 3df39fa2e8..df30f97d3f 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -318,7 +318,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 94.108 ms
+ Execution time of this operator: 95.451 ms
@@ -416,7 +416,7 @@ resume the status and do more 5 trials.
.. code-block:: none
Resume search:
- *E
+
@@ -434,7 +434,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 29.499 seconds)
+ **Total running time of the script:** ( 1 minutes 31.372 seconds)
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index e1b9bf60d5..575c81f6c6 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -454,16 +454,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 2.47/2.47 result: MeasureResult(costs=(0.1086027312,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.992234468460083, timestamp=1677803887.743921) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
- No: 2 GFLOPS: 1.53/2.47 result: MeasureResult(costs=(0.17523738360000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0335025787353516, timestamp=1677803892.041611) [('tile_y', [-1, 1]), ('tile_x', [-1, 1])],None,0
- No: 3 GFLOPS: 1.52/2.47 result: MeasureResult(costs=(0.176713112,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0642268657684326, timestamp=1677803896.3533745) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
- No: 4 GFLOPS: 12.50/12.50 result: MeasureResult(costs=(0.0214717934,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5894973278045654, timestamp=1677803896.9566832) [('tile_y', [-1, 16]), ('tile_x', [-1, 512])],None,94
- No: 5 GFLOPS: 11.45/12.50 result: MeasureResult(costs=(0.0234519066,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6166484355926514, timestamp=1677803897.7046928) [('tile_y', [-1, 4]), ('tile_x', [-1, 512])],None,92
- No: 6 GFLOPS: 3.69/12.50 result: MeasureResult(costs=(0.07283559040000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4186043739318848, timestamp=1677803899.1284313) [('tile_y', [-1, 128]), ('tile_x', [-1, 16])],None,47
- No: 7 GFLOPS: 2.08/12.50 result: MeasureResult(costs=(0.1290436072,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3066203594207764, timestamp=1677803902.6964877) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 8 GFLOPS: 2.11/12.50 result: MeasureResult(costs=(0.1271837906,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.261035919189453, timestamp=1677803904.9860985) [('tile_y', [-1, 4]), ('tile_x', [-1, 1])],None,2
- No: 9 GFLOPS: 3.10/12.50 result: MeasureResult(costs=(0.0865279456,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6244361400604248, timestamp=1677803906.7268276) [('tile_y', [-1, 128]), ('tile_x', [-1, 8])],None,37
- No: 10 GFLOPS: 10.55/12.50 result: MeasureResult(costs=(0.025440617999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6536457538604736, timestamp=1677803907.3967638) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
+ No: 1 GFLOPS: 12.91/12.91 result: MeasureResult(costs=(0.020797073800000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.685373067855835, timestamp=1677844252.9702888) [('tile_y', [-1, 128]), ('tile_x', [-1, 128])],None,77
+ No: 2 GFLOPS: 2.62/12.91 result: MeasureResult(costs=(0.1023227136,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8994560241699219, timestamp=1677844254.8658452) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 9.30/12.91 result: MeasureResult(costs=(0.0288499542,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6877975463867188, timestamp=1677844256.8420646) [('tile_y', [-1, 512]), ('tile_x', [-1, 32])],None,59
+ No: 4 GFLOPS: 3.04/12.91 result: MeasureResult(costs=(0.0884132614,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6720380783081055, timestamp=1677844259.7753706) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 5 GFLOPS: 10.17/12.91 result: MeasureResult(costs=(0.0264003802,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6902482509613037, timestamp=1677844261.8579967) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 6 GFLOPS: 1.33/12.91 result: MeasureResult(costs=(0.20220253600000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.4799842834472656, timestamp=1677844265.361071) [('tile_y', [-1, 1]), ('tile_x', [-1, 2])],None,10
+ No: 7 GFLOPS: 1.56/12.91 result: MeasureResult(costs=(0.17238554420000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0023674964904785, timestamp=1677844268.3743265) [('tile_y', [-1, 32]), ('tile_x', [-1, 4])],None,25
+ No: 8 GFLOPS: 3.07/12.91 result: MeasureResult(costs=(0.08748784779999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6443095207214355, timestamp=1677844270.0298047) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
+ No: 9 GFLOPS: 0.90/12.91 result: MeasureResult(costs=(0.2998453614,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.0338051319122314, timestamp=1677844275.1809046) [('tile_y', [-1, 256]), ('tile_x', [-1, 2])],None,18
+ No: 10 GFLOPS: 1.56/12.91 result: MeasureResult(costs=(0.1723189246,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0037426948547363, timestamp=1677844278.200178) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 0122ce7680..2bf9af8d48 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -311,7 +311,7 @@ standard deviation.
.. code-block:: none
- {'mean': 516.1143709299984, 'median': 516.40067015, 'std': 1.8692819764048865}
+ {'mean': 517.2449440699995, 'median': 517.6538770500031, 'std': 2.257015344069442}
@@ -545,32 +545,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 22.05/ 22.05 GFLOPS | Progress: (4/20) | 12.24 s
[Task 1/25] Current/Best: 11.54/ 22.05 GFLOPS | Progress: (8/20) | 15.92 s
[Task 1/25] Current/Best: 11.23/ 22.05 GFLOPS | Progress: (12/20) | 19.37 s
[Task 1/25] Current/Best: 14.40/ 22.05 GFLOPS | Progress: (16/20) | 21.66 s
[Task 1/25] Current/Best: 18.15/ 22.05 GFLOPS | Progress: (20/20) | 25.63 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 5.72/ 19.04 GFLOPS | Progress: (4/20) | 4.74 s
[Task 2/25] Current/Best: 16.07/ 19.04 GFLOPS | Progress: (8/20) | 6.23 s
[Task 2/25] Current/Best: 5.74/ 19.04 GFLOPS | Progress: (12/20) | 7.97 s
[Task 2/25] Current/Best: 19.58/ 19.58 GFLOPS | Progress: (16/20) | 10.22 s
[Task 2/25] Current/Best: 17.27/ 19.58 GFLOPS | Progress: (20/20) | 11.55 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 10.34/ 15.87 GFLOPS | Progress: (4/20) | 5.10 s
[Task 3/25] Current/Best: 9.72/ 19.51 GFLOPS | Progress: (8/20) | 7.93 s
[Task 3/25] Current/Best: 9.33/ 20.43 GFLOPS | Progress: (12/20) | 10.03 s
[Task 3/25] Current/Best: 13.77/ 20.43 GFLOPS | Progress: (16/20) | 12.88 s
[Task 3/25] Current/Best: 18.18/ 20.43 GFLOPS | Progress: (20/20) | 15.49 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.69/ 17.05 GFLOPS | Progress: (4/20) | 4.82 s
[Task 4/25] Current/Best: 11.45/ 17.05 GFLOPS | Progress: (8/20) | 9.54 s
[Task 4/25] Current/Best: 12.07/ 17.05 GFLOPS | Progress: (12/20) | 12.38 s
[Task 4/25] Current/Best: 7.57/ 17.05 GFLOPS | Progress: (16/20) | 15.26 s
[Task 4/25] Current/Best: 6.33/ 18.30 GFLOPS | Progress: (20/20) | 17.22 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.59/ 21.03 GFLOPS | Progress: (4/20) | 5.20 s
[Task 5/25] Current/Best: 9.96/ 21.03 GFLOPS | Progress: (8/20) | 7.62 s
[Task 5/25] Current/Best: 14.10/ 21.03 GFLOPS | Progress: (12/20) | 10.44 s
[Task 5/25] Current/Best: 8.98/ 21.03 GFLOPS | Progress: (16/20) | 12.93 s
[Task 5/25] Current/Best: 11.52/ 21.03 GFLOPS | Progress: (20/20) | 15.39 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 4.91/ 20.25 GFLOPS | Progress: (4/20) | 6.44 s
[Task 6/25] Current/Best: 18.36/ 20.25 GFLOPS | Progress: (8/20) | 8.92 s
[Task 6/25] Current/Best: 10.98/ 20.25 GFLOPS | Progress: (12/20) | 12.25 s
[Task 6/25] Current/Best: 9.69/ 20.25 GFLOPS | Progress: (16/20) | 14.96 s
[Task 6/25] Current/Best: 5.08/ 22.30 GFLOPS | Progress: (20/20) | 17.64 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 13.93/ 13.93 GFLOPS | Progress: (4/20) | 5.15 s
[Task 7/25] Current/Best: 6.70/ 21.58 GFLOPS | Progress: (8/20) | 7.60 s
[Task 7/25] Current/Best: 6.07/ 21.58 GFLOPS | Progress: (12/20) | 10.20 s
[Task 7/25] Current/Best: 9.21/ 21.58 GFLOPS | Progress: (16/20) | 13.05 s
[Task 7/25] Current/Best: 17.81/ 21.58 GFLOPS | Progress: (20/20) | 15.48 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 17.48/ 17.48 GFLOPS | Progress: (4/20) | 5.71 s
[Task 8/25] Current/Best: 16.78/ 17.48 GFLOPS | Progress: (8/20) | 17.15 s
[Task 8/25] Current/Best: 9.61/ 17.48 GFLOPS | Progress: (12/20) | 22.51 s
[Task 8/25] Current/Best: 8.12/ 17.48 GFLOPS | Progress: (16/20) | 31.06 s
[Task 8/25] Current/Best: 12.72/ 18.54 GFLOPS | Progress: (20/20) | 34.15 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 19.25/ 19.25 GFLOPS | Progress: (4/20) | 4.58 s
[Task 9/25] Current/Best: 16.57/ 19.25 GFLOPS | Progress: (8/20) | 8.33 s
[Task 9/25] Current/Best: 6.26/ 20.00 GFLOPS | Progress: (12/20) | 10.16 s Done.
-
[Task 9/25] Current/Best: 4.82/ 20.00 GFLOPS | Progress: (16/20) | 12.38 s
[Task 9/25] Current/Best: 13.32/ 20.00 GFLOPS | Progress: (20/20) | 18.74 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 14.10/ 14.10 GFLOPS | Progress: (4/20) | 6.40 s
[Task 10/25] Current/Best: 3.51/ 14.53 GFLOPS | Progress: (8/20) | 9.13 s
[Task 10/25] Current/Best: 20.99/ 20.99 GFLOPS | Progress: (12/20) | 12.47 s
[Task 10/25] Current/Best: 11.65/ 20.99 GFLOPS | Progress: (16/20) | 15.25 s
[Task 10/25] Current/Best: 8.58/ 20.99 GFLOPS | Progress: (20/20) | 18.07 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 7.08/ 20.79 GFLOPS | Progress: (4/20) | 5.50 s
[Task 11/25] Current/Best: 3.01/ 20.79 GFLOPS | Progress: (8/20) | 8.85 s
[Task 11/25] Current/Best: 12.35/ 20.79 GFLOPS | Progress: (12/20) | 12.78 s
[Task 11/25] Current/Best: 19.04/ 20.79 GFLOPS | Progress: (16/20) | 16.04 s
[Task 11/25] Current/Best: 9.93/ 20.79 GFLOPS | Progress: (20/20) | 18.91 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 14.68/ 14.68 GFLOPS | Progress: (4/20) | 5.25 s
[Task 12/25] Current/Best: 5.95/ 14.68 GFLOPS | Progress: (8/20) | 7.84 s
[Task 12/25] Current/Best: 10.11/ 15.50 GFLOPS | Progress: (12/20) | 10.92 s
[Task 12/25] Current/Best: 15.19/ 15.50 GFLOPS | Progress: (16/20) | 15.90 s
[Task 12/25] Current/Best: 13.78/ 15.50 GFLOPS | Progress: (20/20) | 19.98 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.46/ 20.54 GFLOPS | Progress: (4/20) | 5.44 s
[Task 13/25] Current/Best: 16.82/ 20.54 GFLOPS | Progress: (8/20) | 7.49 s
[Task 13/25] Current/Best: 14.11/ 20.54 GFLOPS | Progress: (12/20) | 10.88 s
[Task 13/25] Current/Best: 9.33/ 20.54 GFLOPS | Progress: (16/20) | 14.70 s
[Task 13/25] Current/Best: 1.56/ 20.54 GFLOPS | Progress: (20/20) | 18.78 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 14.21/ 14.21 GFLOPS | Progress: (4/20) | 12.24 s
[Task 14/25] Current/Best: 6.26/ 15.66 GFLOPS | Progress: (8/20) | 14.93 s
[Task 14/25] Current/Best: 11.92/ 18.27 GFLOPS | Progress: (12/20) | 17.86 s
[Task 14/25] Current/Best: 11.24/ 18.27 GFLOPS | Progress: (16/20) | 26.33 s
[Task 14/25] Current/Best: 17.31/ 18.27 GFLOPS | Progress: (20/20) | 29.52 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 6.46/ 17.14 GFLOPS | Progress: (4/20) | 9.70 s
[Task 15/25] Current/Best: 22.99/ 22.99 GFLOPS | Progress: (8/20) | 13.13 s
[Task 15/25] Current/Best: 12.42/ 22.99 GFLOPS | Progress: (12/20) | 16.15 s
[Task 15/25] Current/Best: 10.79/ 22.99 GFLOPS | Progress: (16/20) | 21.46 s
[Task 15/25] Current/Best: 11.87/ 22.99 GFLOPS | Progress: (20
/20) | 23.47 s Done.
-
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 18.64/ 18.64 GFLOPS | Progress: (4/20) | 4.61 s
[Task 16/25] Current/Best: 15.32/ 18.64 GFLOPS | Progress: (8/20) | 6.25 s
[Task 16/25] Current/Best: 15.78/ 18.64 GFLOPS | Progress: (12/20) | 7.91 s
[Task 16/25] Current/Best: 17.99/ 18.64 GFLOPS | Progress: (16/20) | 9.59 s
[Task 16/25] Current/Best: 15.04/ 18.64 GFLOPS | Progress: (20/20) | 11.29 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 23.50/ 23.50 GFLOPS | Progress: (4/20) | 5.39 s
[Task 17/25] Current/Best: 3.09/ 23.50 GFLOPS | Progress: (8/20) | 8.45 s
[Task 17/25] Current/Best: 23.63/ 23.63 GFLOPS | Progress: (12/20) | 10.50 s
[Task 17/25] Current/Best: 10.70/ 23.63 GFLOPS | Progress: (16/20) | 13.53 s
[Task 17/25] Current/Best: 17.71/ 23.63 GFLOPS | Progress: (20/20) | 15.76 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 6.67/ 19.95 GFLOPS | Progress: (4/20) | 5.07 s
[Task 18/25] Current/Best: 9.58/ 19.95 GFLOPS | Progress: (8/20) | 7.12 s
[Task 18/25] Current/Best: 18.79/ 19.95 GFLOPS | Progress: (12/20) | 9.82 s
[Task 18/25] Current/Best: 14.10/ 19.95 GFLOPS | Progress: (16/20) | 14.54 s
[Task 18/25] Current/Best: 8.65/ 20.77 GFLOPS | Progress: (20/20) | 22.27 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 23.19/ 23.19 GFLOPS | Progress: (4/20) | 6.70 s
[Task 19/25] Current/Best: 10.32/ 23.19 GFLOPS | Progress: (8/20) | 11.19 s
[Task 19/25] Current/Best: 18.10/ 23.19 GFLOPS | Progress: (12/20) | 13.73 s
[Task 19/25] Current/Best: 10.59/ 23.19 GFLOPS | Progress: (16/20) | 18.75 s
[Task 19/25] Current/Best: 18.28/ 23.19 GFLOPS | Progress: (20/20) | 21.24 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 2.08/ 9.22 GFLOPS | Progress: (4/20) | 7.91 s
[Task 20/25] Current/Best: 7.97/ 13.18 GFLOPS | Progress: (8/20) | 12.47 s Done.
-
[Task 20/25] Current/Best: 13.46/ 13.46 GFLOPS | Progress: (12/20) | 17.28 s
[Task 20/25] Current/Best: 6.24/ 18.72 GFLOPS | Progress: (16/20) | 20.20 s
[Task 20/25] Current/Best: 7.62/ 18.72 GFLOPS | Progress: (20/20) | 23.75 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 8.77/ 11.09 GFLOPS | Progress: (4/20) | 5.62 s
[Task 21/25] Current/Best: 10.70/ 20.71 GFLOPS | Progress: (8/20) | 8.66 s
[Task 21/25] Current/Best: 16.28/ 20.71 GFLOPS | Progress: (12/20) | 10.86 s
[Task 21/25] Current/Best: 9.15/ 20.71 GFLOPS | Progress: (16/20) | 13.37 s
[Task 21/25] Current/Best: 9.31/ 20.71 GFLOPS | Progress: (20/20) | 16.63 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 5.37/ 20.41 GFLOPS | Progress: (4/20) | 4.57 s
[Task 22/25] Current/Best: 6.19/ 20.41 GFLOPS | Progress: (8/2
0) | 6.60 s
[Task 22/25] Current/Best: 19.70/ 20.41 GFLOPS | Progress: (12/20) | 8.40 s
[Task 22/25] Current/Best: 6.55/ 20.41 GFLOPS | Progress: (16/20) | 11.77 s
[Task 22/25] Current/Best: 1.55/ 21.96 GFLOPS | Progress: (20/20) | 14.07 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.54/ 18.06 GFLOPS | Progress: (4/20) | 6.03 s
[Task 23/25] Current/Best: 12.07/ 18.06 GFLOPS | Progress: (8/20) | 11.76 s
[Task 23/25] Current/Best: 12.14/ 18.24 GFLOPS | Progress: (12/20) | 14.11 s
[Task 23/25] Current/Best: 12.06/ 18.24 GFLOPS | Progress: (16/20) | 17.36 s
[Task 23/25] Current/Best: 11.14/ 18.24 GFLOPS | Progress: (20/20) | 21.50 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 6.19/ 9.83 GFLOPS | Progress: (4/20) | 13.65 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 11.18/ 12.58 GFLOPS | Progress: (4/20) | 11.30 s
[Task 1/25] Current/Best: 23.08/ 23.08 GFLOPS | Progress: (8/20) | 15.73 s
[Task 1/25] Current/Best: 12.64/ 23.08 GFLOPS | Progress: (12/20) | 17.86 s
[Task 1/25] Current/Best: 9.19/ 23.08 GFLOPS | Progress: (16/20) | 23.81 s
[Task 1/25] Current/Best: 3.44/ 23.08 GFLOPS | Progress: (20/20) | 26.93 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 14.04/ 19.64 GFLOPS | Progress: (4/20) | 4.95 s
[Task 2/25] Current/Best: 16.78/ 19.64 GFLOPS | Progress: (8/20) | 6.59 s
[Task 2/25] Current/Best: 12.80/ 20.60 GFLOPS | Progress: (12/20) | 8.23 s
[Task 2/25] Current/Best: 7.98/ 20.60 GFLOPS | Progress: (16/20) | 10.66 s
[Task 2/25] Current/Best: 10.58/ 20.60 GFLOPS | Progress: (20/20) | 14.08 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 12.41/ 19.05 GFLOPS | Progress: (4/20) | 4.95 s
[Task 3/25] Current/Best: 3.03/ 20.13 GFLOPS | Progress: (8/20) | 8.54 s
[Task 3/25] Current/Best: 21.75/ 21.75 GFLOPS | Progress: (12/20) | 10.49 s
[Task 3/25] Current/Best: 7.42/ 21.75 GFLOPS | Progress: (16/20) | 13.10 s
[Task 3/25] Current/Best: 14.37/ 21.75 GFLOPS | Progress: (20/20) | 16.14 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 14.25/ 20.32 GFLOPS | Progress: (4/20) | 4.92 s
[Task 4/25] Current/Best: 14.51/ 20.32 GFLOPS | Progress: (8/20) | 6.79 s
[Task 4/25] Current/Best: 12.24/ 20.32 GFLOPS | Progress: (12/20) | 9.47 s
[Task 4/25] Current/Best: 17.84/ 20.32 GFLOPS | Progress: (16/20) | 11.38 s
[Task 4/25] Current/Best: 15.84/ 20.32 GFLOPS | Progress: (20/20) | 13.30 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 6.02/ 10.33 GFLOPS | Progress: (4/20) | 6.39 s
[Task 5/25] Current/Best: 20.03/ 20.03 GFLOPS | Progress: (8/20) | 8.37 s
[Task 5/25] Current/Best: 8.82/ 20.03 GFLOPS | Progress: (12/20) | 10.49 s
[Task 5/25] Current/Best: 5.28/ 20.03 GFLOPS | Progress: (16/20) | 12.68 s
[Task 5/25] Current/Best: 12.28/ 20.03 GFLOPS | Progress: (20/20) | 14.99 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.37/ 17.58 GFLOPS | Progress: (4/20) | 5.19 s
[Task 6/25] Current/Best: 13.99/ 17.58 GFLOPS | Progress: (8/20) | 8.12 s
[Task 6/25] Current/Best: 5.27/ 17.58 GFLOPS | Progress: (12/20) | 11.34 s
[Task 6/25] Current/Best: 13.07/ 22.34 GFLOPS | Progress: (16/20) | 13.73 s
[Task 6/25] Current/Best: 17.51/ 22.34 GFLOPS | Progress: (20/20) | 16.71 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.07/ 17.22 GFLOPS | Progress: (4/20) | 6.19 s
[Task 7/25] Current/Best: 14.07/ 19.36 GFLOPS | Progress: (8/20) | 9.18 s
[Task 7/25] Current/Best: 9.14/ 19.36 GFLOPS | Progress: (12/20) | 11.73 s
[Task 7/25] Current/Best: 3.15/ 19.36 GFLOPS | Progress: (16/20) | 14.75 s
[Task 7/25] Current/Best: 14.09/ 21.59 GFLOPS | Progress: (20/20) | 18.37 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 2.43/ 16.24 GFLOPS | Progress: (4/20) | 6.44 s
[Task 8/25] Current/Best: 11.13/ 16.24 GFLOPS | Progress: (8/20) | 17.97 s
[Task 8/25] Current/Best: 11.85/ 18.34 GFLOPS | Progress: (12/20) | 24.36 s
[Task 8/25] Current/Best: 12.37/ 18.34 GFLOPS | Progress: (16/20) | 35.80 s
[Task 8/25] Current/Best: 19.26/ 19.26 GFLOPS | Progress: (20/20) | 39.83 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 3.18/ 21.86 GFLOPS | Progress: (4/20) | 4.81 s
[Task 9/25] Current/Best: 18.92/ 21.86 GFLOPS | Progress: (8/20) | 10.56 s
[Task 9/25] Current/Best: 20.01/ 22.92 GFLOPS | Progress: (12/20) | 13.15 s
[Task 9/25] Current/Best: 16.02/ 22.92 GFLOPS | Progress: (16/20) | 22.62 s
[Task 9/25] Current/Best: 9.20/ 22.92 GFLOPS | Progress: (20/20) | 28.44 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 9.29/ 13.47 GFLOPS | Progress: (4/20) | 5.21 s
[Task 10/25] Current/Best: 11.30/ 16.26 GFLOPS | Progress: (8/20) | 7.57 s
[Task 10/25] Current/Best: 14.25/ 21.28 GFLOPS | Progress: (12/20) | 9.91 s
[Task 10/25] Current/Best: 10.55/ 21.28 GFLOPS | Progress: (16/20) | 13.02 s
[Task 10/25] Current/Best: 13.71/ 21.28 GFLOPS | Progress: (20/20) | 15.20 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 1.58/ 17.67 GFLOPS | Progress: (4/20) | 6.50 s
[Task 11/25] Current/Best: 11.54/ 19.09 GFLOPS | Progress: (8/20) | 9.77 s
[Task 11/25] Current/Best: 16.26/ 19.09 GFLOPS | Progress: (12/20) | 12.22 s
[Task 11/25] Current/Best: 19.04/ 21.85 GFLOPS | Progress: (16/20) | 14.51 s
[Task 11/25] Current/Best: 14.09/ 21.85 GFLOPS | Progress: (20/20) | 16.91 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 14.31/ 14.31 GFLOPS | Progress: (4/20) | 5.95 s
[Task 12/25] Current/Best: 15.41/ 18.52 GFLOPS | Progress: (8/20) | 10.56 s
[Task 12/25] Current/Best: 11.30/ 18.52 GFLOPS | Progress: (12/20) | 14.64 s
[Task 12/25] Current/Best: 15.40/ 18.52 GFLOPS | Progress: (16/20) | 17.09 s
[Task 12/25] Current/Best: 16.57/ 18.52 GFLOPS | Progress: (20/20) | 20.32 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 18.27/ 18.27 GFLOPS | Progress: (4/20) | 5.52 s
[Task 13/25] Current/Best: 13.55/ 20.18 GFLOPS | Progress: (8/20) | 8.62 s
[Task 13/25] Current/Best: 8.13/ 20.18 GFLOPS | Progress: (12/20) | 11.79 s
[Task 13/25] Current/Best: 14.21/ 20.18 GFLOPS | Progress: (16/20) | 13.99 s
[Task 13/25] Current/Best: 18.47/ 22.00 GFLOPS | Progress: (20/20) | 17.04 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 2.81/ 18.28 GFLOPS | Progress: (4/20) | 5.53 s
[Task 14/25] Current/Best: 6.24/ 18.28 GFLOPS | Progress: (8/20) | 8.71 s
[Task 14/25] Current/Best: 12.71/ 19.42 GFLOPS | Progress: (12/20) | 11.77 s
[Task 14/25] Current/Best: 12.54/ 20.68 GFLOPS | Progress: (16/20) | 14.75 s
[Task 14/25] Current/Best: 15.86/ 20.68 GFLOPS | Progress: (20/20) | 18.03 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 22.04/ 22.04 GFLOPS | Progress: (4/20) | 5.45 s
[Task 15/25] Current/Best: 10.56/ 22.04 GFLOPS | Progress: (8/20) | 9.81 s
[Task 15/25] Current/Best: 17.81/ 22.04 GFLOPS | Progress: (12/20) | 11.65 s
[Task 15/25] Current/Best: 14.05/ 22.04 GFLOPS | Progress: (16/20) | 21.39 s
[Task 15/25] Current/Best: 12.78/ 22.04 GFLOPS | Progress: (20/20
) | 23.61 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 18.06/ 18.06 GFLOPS | Progress: (4/20) | 5.78 s
[Task 16/25] Current/Best: 15.00/ 18.06 GFLOPS | Progress: (8/20) | 7.58 s
[Task 16/25] Current/Best: 15.34/ 20.18 GFLOPS | Progress: (12/20) | 9.19 s
[Task 16/25] Current/Best: 15.75/ 20.18 GFLOPS | Progress: (16/20) | 12.21 s
[Task 16/25] Current/Best: 12.59/ 20.18 GFLOPS | Progress: (20/20) | 14.64 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 9.74/ 9.95 GFLOPS | Progress: (4/20) | 6.12 s
[Task 17/25] Current/Best: 12.20/ 22.85 GFLOPS | Progress: (8/20) | 9.01 s
[Task 17/25] Current/Best: 6.19/ 22.85 GFLOPS | Progress: (12/20) | 13.17 s
[Task 17/25] Current/Best: 18.79/ 22.85 GFLOPS | Progress: (16/20) | 17.61 s
[Task 17/25] Current/Best: 18.12/ 22.85 GFLOPS | Progress: (20/20) | 20.79 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 12.35/ 15.62 GFLOPS | Progress: (4/20) | 5.13 s
[Task 18/25] Current/Best: 14.89/ 15.89 GFLOPS | Progress: (8/20) | 13.03 s
[Task 18/25] Current/Best: 17.66/ 17.66 GFLOPS | Progress: (12/20) | 15.73 s
[Task 18/25] Current/Best: 16.23/ 17.66 GFLOPS | Progress: (16/20) | 17.80 s Done.
Done.
-
[Task 24/25] Current/Best: 10.32/ 10.32 GFLOPS | Progress: (8/20) | 24.60 s
[Task 24/25] Current/Best: 4.25/ 10.32 GFLOPS | Progress: (12/20) | 35.29 s
[Task 24/25] Current/Best: 6.15/ 10.32 GFLOPS | Progress: (16/20) | 47.89 s
[Task 24/25] Current/Best: 7.61/ 10.32 GFLOPS | Progress: (20/20) | 60.54 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.54/ 9.16 GFLOPS | Progress: (4/20) | 15.07 s Done.
-
[Task 25/25] Current/Best: 9.23/ 9.23 GFLOPS | Progress: (8/20) | 17.72 s
[Task 25/25] Current/Best: 3.49/ 9.23 GFLOPS | Progress: (12/20) | 19.14 s
[Task 25/25] Current/Best: 4.44/ 9.23 GFLOPS | Progress: (16/20) | 20.51 s
[Task 25/25] Current/Best: 3.60/ 9.60 GFLOPS | Progress: (20/20) | 23.10 s Done.
-
+
[Task 18/25] Current/Best: 16.57/ 17.77 GFLOPS | Progress: (20/20) | 23.93 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 8.96/ 12.70 GFLOPS | Progress: (4/20) | 6.09 s
[Task 19/25] Current/Best: 17.72/ 17.72 GFLOPS | Progress: (8/20) | 9.20 s
[Task 19/25] Current/Best: 9.60/ 18.51 GFLOPS | Progress: (12/20) | 12.78 s
[Task 19/25] Current/Best: 18.13/ 18.51 GFLOPS | Progress: (16/20) | 16.53 s
[Task 19/25] Current/Best: 11.18/ 18.51 GFLOPS | Progress: (20/20) | 22.03 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 13.53/ 13.94 GFLOPS | Progress: (4/20) | 4.83 s
[Task 20/25] Current/Best: 15.93/ 15.93 GFLOPS | Progress: (8/20) | 7.70 s
[Task 20/25] Current/Best: 20.36/ 20.36 GFLOPS | Progress: (12/20) | 11.78 s
[Task 20/25] Current/Best: 9.48/ 20.36 GFLOPS | Progress: (16/20) | 14.02 s
[Task 20/25] Current/Best: 12.66/ 20.36 GFLOPS | Progress: (20/20) | 17.22 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 10.21/ 10.21 GFLOPS | Progress: (4/20) | 6.05 s
[Task 21/25] Current/Best: 7.26/ 17.07 GFLOPS | Progress: (8/20) | 9.07 s Done.
+
[Task 21/25] Current/Best: 20.07/ 20.07 GFLOPS | Progress: (12/20) | 10.85 s
[Task 21/25] Current/Best: 18.50/ 20.07 GFLOPS | Progress: (16/20) | 15.29 s
[Task 21/25] Current/Best: 16.23/ 20.18 GFLOPS | Progress: (20/20) | 17.03 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 4.94/ 19.91 GFLOPS | Progress: (4/20) | 5.81 s
[Task 22/25] Current/Best: 14.60/ 19.91 GFLOPS | Progress: (8/20) | 7.79 s
[Task 22/25] Current/Best: 17.38/ 19.91 GFLOPS | Progress: (12/20) | 10.50 s
[Task 22/25] Current/Best: 16.92/ 19.91 GFLOPS | Progress: (16/20) | 12.74 s
[Task 22/25] Current/Best: 7.73/ 20.28 GFLOPS | Progress: (20/20) | 14.42 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 6.78/ 18.00 GFLOPS | Progress: (4/20) | 7.51 s
[Task 23/25] Current/Best: 13.77/ 18.61 GFLOPS | Progress: (8/20) | 10.93 s
[Task 23/25] Current/Best: 10.59/ 18.61 GFLOPS | Progress: (12/20) | 14.11 s
[Task 23/25] Current/Best: 7.93/ 19.76 GFLOPS | Progress: (16/20) | 17.10 s
[Task 23/25] Current/Best: 21.21/ 21.40 GFLOPS | Progress: (20/20) | 19.14 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 3.22/ 8.72 GFLOPS | Progress: (4/20) | 9.17 s
[Task 24/25] Current/Best: 3.05/ 8.72 GFLOPS | Progress: (8/20) | 19.54 s
[Task 24/25] Current/Best: 2.28/ 8.72 GFLOPS | Progress: (12/20) | 26.28 s
[Task 24/25] Current/Best: 5.49/ 8.72 GFLOPS | Progress: (16/20) | 36.92 s
[Task 24/25] Current/Best: 3.34/ 8.72 GFLOPS | Progress: (20/20) | 40.43 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+ Done.
+
[Task 25/25] Current/Best: 5.04/ 8.58 GFLOPS | Progress: (4/20) | 13.80 s
[Task 25/25] Current/Best: 9.01/ 9.01 GFLOPS | Progress: (8/20) | 19.54 s
[Task 25/25] Current/Best: 3.01/ 9.01 GFLOPS | Progress: (12/20) | 30.48 s
[Task 25/25] Current/Best: 6.95/ 9.39 GFLOPS | Progress: (16/20) | 41.43 s
[Task 25/25] Current/Best: 3.50/ 9.39 GFLOPS | Progress: (20/20) | 52.39 s
@@ -666,7 +665,7 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621102
+ class='n02123045 tabby, tabby cat' with probability=0.621104
class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
@@ -724,8 +723,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 414.68397561000074, 'median': 413.87612144999366, 'std': 1.8714302502193594}
- unoptimized: {'mean': 516.1143709299984, 'median': 516.40067015, 'std': 1.8692819764048865}
+ optimized: {'mean': 416.23713565000116, 'median': 416.4539518500078, 'std': 1.4458089148268325}
+ unoptimized: {'mean': 517.2449440699995, 'median': 517.6538770500031, 'std': 2.257015344069442}
@@ -748,7 +747,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 12 minutes 41.108 seconds)
+ **Total running time of the script:** ( 13 minutes 5.324 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 a9addc8ec2..49fd112529 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -274,7 +274,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.243e-07 secs/op
+ 1.237e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 89d06838c4..3bb8a6919f 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -277,7 +277,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x8fadcb0)), stage(b, placeholder(b, 0x22ba3150)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[a[ax0, ax1, ax2] * b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T. [...]
+ [stage(a, placeholder(a, 0x1addf380)), stage(b, placeholder(b, 0xa7123e0)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[a[ax0, ax1, ax2] * b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T. [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 828063009b..5cafdef242 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**16:17.370** total execution time for **tutorial** files:
+**16:49.364** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:41.108 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 13:05.324 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:29.499 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:31.372 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.219 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.985 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.408 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.758 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:28.123 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:32.506 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.994 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.381 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.852 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.855 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.168 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.182 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 0fae0f09e7..25c55263cc 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -392,7 +392,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000010
+ parallel: 0.000007
@@ -447,7 +447,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000034
+ vector: 0.000025
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -504,10 +504,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.119080000597023e-06 1.0
- naive 6.6787999999999995e-06 0.822605516820734
- parallel 9.836799999999999e-06 1.2115658423462592
- vector 3.38825e-05 4.173194499562574
+ numpy 7.8743500012024e-06 1.0
+ naive 6.693300000000001e-06 0.8500130168176351
+ parallel 6.9917e-06 0.8879082081609757
+ vector 2.46253e-05 3.1272803464717414
@@ -928,7 +928,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018536
+ Numpy running time: 0.019057
@@ -986,7 +986,7 @@ optimizations.
.. code-block:: none
- none: 3.299490
+ none: 3.399315
@@ -1086,7 +1086,7 @@ schedule.
.. code-block:: none
- blocking: 0.278418
+ blocking: 0.299730
@@ -1170,7 +1170,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.321086
+ vectorization: 0.341815
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1236,7 +1236,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.118858
+ loop permutation: 0.116570
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1327,7 +1327,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.109991
+ array packing: 0.107985
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1410,7 +1410,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110963
+ block caching: 0.109840
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1484,7 +1484,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.146265
+ parallelization: 0.145948
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1554,13 +1554,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.2994895548 1.0
- blocking 0.2784177397 0.08438206427869005
- vectorization 0.3210864014 0.09731396207419205
- loop permutation 0.118857718 0.03602306236341597
- array packing 0.1099905202 0.03333561703203122
- block caching 0.1109628112 0.03363029624948337
- parallelization 0.1462651268 0.044329622619116285
+ none 3.3993146897999997 1.0
+ blocking 0.2997299752 0.08817364750000088
+ vectorization 0.3418154392 0.10055422059794966
+ loop permutation 0.11656959999999998 0.03429208844646813
+ array packing 0.10798507770000002 0.0317667199285846
+ block caching 0.1098397069 0.03231230907499843
+ parallelization 0.14594775910000002 0.0429344654491482
@@ -1600,6 +1600,11 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 0.985 seconds)
+
+
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/arch/benchmark.html b/docs/arch/benchmark.html
index 9abfb3774b..fea6081283 100644
--- a/docs/arch/benchmark.html
+++ b/docs/arch/benchmark.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/arch/convert_layout.html b/docs/arch/convert_layout.html
index f5e4c47a13..0890978166 100644
--- a/docs/arch/convert_layout.html
+++ b/docs/arch/convert_layout.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/arch/debugger.html b/docs/arch/debugger.html
index ed399a91d3..c5bda234c3 100644
--- a/docs/arch/debugger.html
+++ b/docs/arch/debugger.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/arch/device_target_interactions.html b/docs/arch/device_target_interactions.html
index 0e23231482..3b3e9f5b87 100644
--- a/docs/arch/device_target_interactions.html
+++ b/docs/arch/device_target_interactions.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/arch/frontend/tensorflow.html b/docs/arch/frontend/tensorflow.html
index 9951275ffb..4f56de8cca 100644
--- a/docs/arch/frontend/tensorflow.html
+++ b/docs/arch/frontend/tensorflow.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/arch/hybrid_script.html b/docs/arch/hybrid_script.html
index fc1b7452ce..6f5fd8c377 100644
--- a/docs/arch/hybrid_script.html
+++ b/docs/arch/hybrid_script.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/arch/index.html b/docs/arch/index.html
index 48bc7277d7..1b27fd3421 100644
--- a/docs/arch/index.html
+++ b/docs/arch/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/arch/inferbound.html b/docs/arch/inferbound.html
index 1fcc04dfb2..40f164e171 100644
--- a/docs/arch/inferbound.html
+++ b/docs/arch/inferbound.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/arch/introduction_to_module_serialization.html b/docs/arch/introduction_to_module_serialization.html
index 02b1531c1c..ad2fbdcfc6 100644
--- a/docs/arch/introduction_to_module_serialization.html
+++ b/docs/arch/introduction_to_module_serialization.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/arch/microtvm_design.html b/docs/arch/microtvm_design.html
index fc1d3d20fa..a8c10ff691 100644
--- a/docs/arch/microtvm_design.html
+++ b/docs/arch/microtvm_design.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/arch/microtvm_project_api.html b/docs/arch/microtvm_project_api.html
index 2c7a9aa9f1..b03aec5f96 100644
--- a/docs/arch/microtvm_project_api.html
+++ b/docs/arch/microtvm_project_api.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/arch/model_library_format.html b/docs/arch/model_library_format.html
index a843e7d390..1663daf81e 100644
--- a/docs/arch/model_library_format.html
+++ b/docs/arch/model_library_format.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/arch/pass_infra.html b/docs/arch/pass_infra.html
index 83c099cac3..a38194c28c 100644
--- a/docs/arch/pass_infra.html
+++ b/docs/arch/pass_infra.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/arch/relay_intro.html b/docs/arch/relay_intro.html
index d41da7b158..2de9514157 100644
--- a/docs/arch/relay_intro.html
+++ b/docs/arch/relay_intro.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/arch/relay_op_strategy.html b/docs/arch/relay_op_strategy.html
index 22fd19c608..031f216bf5 100644
--- a/docs/arch/relay_op_strategy.html
+++ b/docs/arch/relay_op_strategy.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/arch/runtime.html b/docs/arch/runtime.html
index a995ba1fe1..4996868852 100644
--- a/docs/arch/runtime.html
+++ b/docs/arch/runtime.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/arch/runtimes/vulkan.html b/docs/arch/runtimes/vulkan.html
index 68a500dd25..340a2270e7 100644
--- a/docs/arch/runtimes/vulkan.html
+++ b/docs/arch/runtimes/vulkan.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/arch/security.html b/docs/arch/security.html
index 65f64f6b41..10217327ac 100644
--- a/docs/arch/security.html
+++ b/docs/arch/security.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/arch/virtual_machine.html b/docs/arch/virtual_machine.html
index 947f7a9809..4c7ddffbbe 100644
--- a/docs/arch/virtual_machine.html
+++ b/docs/arch/virtual_machine.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/commit_hash b/docs/commit_hash
index a63d89a5e9..3ee1a18422 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-a42e98b1956f867dc0a2527b734612012f3cce27
+bc92a3ff665de14803d7c7d6dcac20e7fc8dbd1b
diff --git a/docs/contribute/ci.html b/docs/contribute/ci.html
index 668f81ee63..12b5864d85 100644
--- a/docs/contribute/ci.html
+++ b/docs/contribute/ci.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/contribute/code_guide.html b/docs/contribute/code_guide.html
index ecace19803..901d38f38f 100644
--- a/docs/contribute/code_guide.html
+++ b/docs/contribute/code_guide.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/contribute/code_review.html b/docs/contribute/code_review.html
index e6bef85efc..e9973dfbdf 100644
--- a/docs/contribute/code_review.html
+++ b/docs/contribute/code_review.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/contribute/committer_guide.html b/docs/contribute/committer_guide.html
index b4cb648421..06ff63dc07 100644
--- a/docs/contribute/committer_guide.html
+++ b/docs/contribute/committer_guide.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/contribute/community.html b/docs/contribute/community.html
index cb82e5b5e7..5435fbab8e 100644
--- a/docs/contribute/community.html
+++ b/docs/contribute/community.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/contribute/document.html b/docs/contribute/document.html
index f9d4344398..b2daa2bc0e 100644
--- a/docs/contribute/document.html
+++ b/docs/contribute/document.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/contribute/error_handling.html b/docs/contribute/error_handling.html
index 09b5bfca22..fe7eddd2a9 100644
--- a/docs/contribute/error_handling.html
+++ b/docs/contribute/error_handling.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/contribute/git_howto.html b/docs/contribute/git_howto.html
index 2c8ac2f17c..7372afbc64 100644
--- a/docs/contribute/git_howto.html
+++ b/docs/contribute/git_howto.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/contribute/index.html b/docs/contribute/index.html
index 76b793b970..5c446e0953 100644
--- a/docs/contribute/index.html
+++ b/docs/contribute/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/contribute/pull_request.html b/docs/contribute/pull_request.html
index c7a38a9cfd..fa4586e374 100644
--- a/docs/contribute/pull_request.html
+++ b/docs/contribute/pull_request.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/contribute/release_process.html b/docs/contribute/release_process.html
index e583fd9aca..d7c213f28e 100644
--- a/docs/contribute/release_process.html
+++ b/docs/contribute/release_process.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/dev/how_to/debugging_tvm.html b/docs/dev/how_to/debugging_tvm.html
index 9dc6f78bf7..206f1d3bf5 100644
--- a/docs/dev/how_to/debugging_tvm.html
+++ b/docs/dev/how_to/debugging_tvm.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/dev/how_to/how_to.html b/docs/dev/how_to/how_to.html
index 68915866e1..6a585fd391 100644
--- a/docs/dev/how_to/how_to.html
+++ b/docs/dev/how_to/how_to.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/dev/how_to/pytest_target_parametrization.html b/docs/dev/how_to/pytest_target_parametrization.html
index 39a02fe08d..9515f1d6ef 100644
--- a/docs/dev/how_to/pytest_target_parametrization.html
+++ b/docs/dev/how_to/pytest_target_parametrization.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/dev/how_to/relay_add_op.html b/docs/dev/how_to/relay_add_op.html
index fdc250a0f4..60b80734b2 100644
--- a/docs/dev/how_to/relay_add_op.html
+++ b/docs/dev/how_to/relay_add_op.html
@@ -202,6 +202,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/dev/how_to/relay_add_pass.html b/docs/dev/how_to/relay_add_pass.html
index 9270e963e0..7a796df292 100644
--- a/docs/dev/how_to/relay_add_pass.html
+++ b/docs/dev/how_to/relay_add_pass.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/dev/how_to/relay_bring_your_own_codegen.html b/docs/dev/how_to/relay_bring_your_own_codegen.html
index 5c7a1a625a..87eb70c10d 100644
--- a/docs/dev/how_to/relay_bring_your_own_codegen.html
+++ b/docs/dev/how_to/relay_bring_your_own_codegen.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/dev/tutorial/codebase_walkthrough.html b/docs/dev/tutorial/codebase_walkthrough.html
index 314fe58c0f..1a5967042c 100644
--- a/docs/dev/tutorial/codebase_walkthrough.html
+++ b/docs/dev/tutorial/codebase_walkthrough.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/dev/tutorial/index.html b/docs/dev/tutorial/index.html
index 39c4895d1e..2227db512f 100644
--- a/docs/dev/tutorial/index.html
+++ b/docs/dev/tutorial/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/errors.html b/docs/errors.html
index ee2cf9cf2e..0922d7d546 100644
--- a/docs/errors.html
+++ b/docs/errors.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/faq.html b/docs/faq.html
index 90c012903f..971c563959 100644
--- a/docs/faq.html
+++ b/docs/faq.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/genindex.html b/docs/genindex.html
index ed31a674d1..373830539f 100644
--- a/docs/genindex.html
+++ b/docs/genindex.html
@@ -199,6 +199,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/compile_models/from_coreml.html b/docs/how_to/compile_models/from_coreml.html
index 486fb834f9..bbd0b11c7e 100644
--- a/docs/how_to/compile_models/from_coreml.html
+++ b/docs/how_to/compile_models/from_coreml.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 1905208549..797875eb0f 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -585,7 +590,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.423 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 18.904 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_keras.html b/docs/how_to/compile_models/from_keras.html
index 5a8d7dda86..f146f316ba 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -506,7 +511,7 @@ Tensorflow is also required since itβs used as the default backend of keras.</
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 975ms/step
+1/1 [==============================] - 1s 976ms/step
Keras top-1 id: 285, class name: Egyptian cat
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 6ece48e2ee..79db4f6e1c 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -439,7 +444,7 @@
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip4ac2ee4b-cbe1-4033-bfb7-e35b9acb4f8a from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip2a72abed-73a2-4253-8595-3432c282a687 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_oneflow.html b/docs/how_to/compile_models/from_oneflow.html
index e90ef5818b..cc907a6482 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -449,12 +454,12 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 50.9MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 55.7MB/s]
- 54%|#####4 | 22.5M/41.5M [00:00<00:00, 60.2MB/s]
- 68%|######8 | 28.4M/41.5M [00:00<00:00, 50.4MB/s]
- 81%|######## | 33.4M/41.5M [00:00<00:00, 43.6MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 54.9MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 45.7MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 43.6MB/s]
+ 55%|#####4 | 22.8M/41.5M [00:00<00:00, 51.8MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 54.9MB/s]
+ 96%|#########6| 40.0M/41.5M [00:00<00:00, 55.6MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 54.4MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_onnx.html b/docs/how_to/compile_models/from_onnx.html
index 34607b6940..30b573f764 100644
--- a/docs/how_to/compile_models/from_onnx.html
+++ b/docs/how_to/compile_models/from_onnx.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/compile_models/from_paddle.html b/docs/how_to/compile_models/from_paddle.html
index 72878fd4ac..4f8103b076 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index c4f3f80610..8f84534690 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -432,12 +437,11 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 18%|#7 | 7.99M/44.7M [00:00<00:00, 55.2MB/s]
- 36%|###5 | 16.0M/44.7M [00:00<00:00, 68.1MB/s]
- 58%|#####8 | 26.1M/44.7M [00:00<00:00, 63.3MB/s]
- 72%|#######2 | 32.3M/44.7M [00:00<00:00, 53.2MB/s]
- 90%|########9 | 40.0M/44.7M [00:00<00:00, 59.9MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 58.3MB/s]
+ 18%|#8 | 8.12M/44.7M [00:00<00:00, 79.3MB/s]
+ 38%|###8 | 17.2M/44.7M [00:00<00:00, 88.2MB/s]
+ 58%|#####8 | 26.1M/44.7M [00:00<00:00, 88.1MB/s]
+ 86%|########5 | 38.3M/44.7M [00:00<00:00, 86.4MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 81.7MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_tensorflow.html b/docs/how_to/compile_models/from_tensorflow.html
index 62d076ad3f..29da94594e 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -649,7 +654,7 @@ 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 24.554 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 24.191 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7f1d3d1b878694c201c614c807cdebc8/from_tensorflow.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_tensorflow.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_tflite.html b/docs/how_to/compile_models/from_tflite.html
index 8305b323a0..d58b1ed4ff 100644
--- a/docs/how_to/compile_models/from_tflite.html
+++ b/docs/how_to/compile_models/from_tflite.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/compile_models/index.html b/docs/how_to/compile_models/index.html
index bd60592ec3..4d2b71cabe 100644
--- a/docs/how_to/compile_models/index.html
+++ b/docs/how_to/compile_models/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index 6eb3d7a746..2e263d6889 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -199,6 +199,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -340,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">ΒΆ</a></h1>
-<p><strong>06:46.121</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>06:38.473</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,43 +354,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:24.554</p></td>
+<td><p>01:24.191</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:23.423</p></td>
+<td><p>01:18.904</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:55.628</p></td>
+<td><p>00:56.127</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:38.515</p></td>
+<td><p>00:37.838</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:31.835</p></td>
+<td><p>00:32.077</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:31.420</p></td>
+<td><p>00:31.591</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:28.429</p></td>
+<td><p>00:27.200</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:26.801</p></td>
+<td><p>00:25.799</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:22.814</p></td>
+<td><p>00:22.044</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></td>
-<td><p>00:02.702</p></td>
+<td><p>00:02.703</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy/adreno.html b/docs/how_to/deploy/adreno.html
index 3fb65eb940..be70ae2d62 100644
--- a/docs/how_to/deploy/adreno.html
+++ b/docs/how_to/deploy/adreno.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/deploy/android.html b/docs/how_to/deploy/android.html
index 24b259d37a..7b4f11de39 100644
--- a/docs/how_to/deploy/android.html
+++ b/docs/how_to/deploy/android.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/deploy/arm_compute_lib.html b/docs/how_to/deploy/arm_compute_lib.html
index b0d710ee40..59c6f981ae 100644
--- a/docs/how_to/deploy/arm_compute_lib.html
+++ b/docs/how_to/deploy/arm_compute_lib.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/deploy/bnns.html b/docs/how_to/deploy/bnns.html
index c8b3c444ae..f905e5cfba 100644
--- a/docs/how_to/deploy/bnns.html
+++ b/docs/how_to/deploy/bnns.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/deploy/cpp_deploy.html b/docs/how_to/deploy/cpp_deploy.html
index af98e6a5c7..758975a9a0 100644
--- a/docs/how_to/deploy/cpp_deploy.html
+++ b/docs/how_to/deploy/cpp_deploy.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/deploy/hls.html b/docs/how_to/deploy/hls.html
index 9a951d5618..4ddc2bf87e 100644
--- a/docs/how_to/deploy/hls.html
+++ b/docs/how_to/deploy/hls.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/deploy/index.html b/docs/how_to/deploy/index.html
index 7e3971c75d..c647f156f7 100644
--- a/docs/how_to/deploy/index.html
+++ b/docs/how_to/deploy/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/deploy/integrate.html b/docs/how_to/deploy/integrate.html
index 5e9c5c85bd..a53f92aa25 100644
--- a/docs/how_to/deploy/integrate.html
+++ b/docs/how_to/deploy/integrate.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/deploy/tensorrt.html b/docs/how_to/deploy/tensorrt.html
index 8491694e84..9521448acc 100644
--- a/docs/how_to/deploy/tensorrt.html
+++ b/docs/how_to/deploy/tensorrt.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/deploy/vitis_ai.html b/docs/how_to/deploy/vitis_ai.html
index 775af3d478..5004776be3 100644
--- a/docs/how_to/deploy/vitis_ai.html
+++ b/docs/how_to/deploy/vitis_ai.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno.html b/docs/how_to/deploy_models/deploy_model_on_adreno.html
index 30f888092c..8db5a83616 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -920,7 +925,7 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2646.0374 2645.5478 2649.8098 2643.5758 1.9627
+ 2686.6466 2686.2724 2691.1577 2683.8304 2.0018
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
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 477ee6f0b6..463562e3cd 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -662,7 +667,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.3725 15.5663 15.7423 14.6626 0.3860
+ 16.1432 16.0172 16.8460 15.9411 0.2694
</pre></div>
</div>
</div>
diff --git a/docs/how_to/deploy_models/deploy_model_on_nano.html b/docs/how_to/deploy_models/deploy_model_on_nano.html
index a854d180a6..a7b5d6a630 100644
--- a/docs/how_to/deploy_models/deploy_model_on_nano.html
+++ b/docs/how_to/deploy_models/deploy_model_on_nano.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</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 56f82e7d0e..9a083691e0 100644
--- a/docs/how_to/deploy_models/deploy_model_on_rasp.html
+++ b/docs/how_to/deploy_models/deploy_model_on_rasp.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</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 bfa7d9eece..fa9cdc6a6a 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -454,30 +459,27 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 5%|4 | 7.99M/170M [00:00<00:04, 39.8MB/s]
- 7%|7 | 11.9M/170M [00:00<00:04, 40.3MB/s]
- 9%|9 | 16.0M/170M [00:00<00:03, 40.9MB/s]
- 14%|#3 | 23.7M/170M [00:00<00:03, 41.8MB/s]
- 16%|#6 | 27.7M/170M [00:00<00:03, 41.1MB/s]
- 19%|#8 | 32.0M/170M [00:00<00:03, 36.8MB/s]
- 21%|## | 35.5M/170M [00:01<00:04, 32.3MB/s]
- 24%|##3 | 40.0M/170M [00:01<00:04, 31.5MB/s]
- 28%|##8 | 48.0M/170M [00:01<00:03, 42.4MB/s]
- 33%|###2 | 56.0M/170M [00:01<00:02, 49.3MB/s]
- 38%|###7 | 64.1M/170M [00:01<00:01, 57.7MB/s]
- 42%|####2 | 72.0M/170M [00:01<00:01, 60.2MB/s]
- 47%|####7 | 80.0M/170M [00:01<00:01, 63.8MB/s]
- 52%|#####2 | 89.0M/170M [00:01<00:01, 71.7MB/s]
- 57%|#####6 | 96.7M/170M [00:01<00:01, 74.4MB/s]
- 61%|######1 | 104M/170M [00:02<00:00, 69.2MB/s]
- 68%|######8 | 116M/170M [00:02<00:00, 83.1MB/s]
- 73%|#######2 | 124M/170M [00:02<00:00, 80.3MB/s]
- 79%|#######9 | 134M/170M [00:02<00:00, 88.8MB/s]
- 84%|########4 | 143M/170M [00:02<00:00, 89.4MB/s]
- 89%|########9 | 152M/170M [00:02<00:00, 82.6MB/s]
- 94%|#########4| 160M/170M [00:02<00:00, 76.9MB/s]
- 99%|#########8| 167M/170M [00:02<00:00, 76.9MB/s]
-100%|##########| 170M/170M [00:02<00:00, 60.8MB/s]
+ 5%|4 | 7.99M/170M [00:00<00:02, 80.5MB/s]
+ 9%|9 | 16.0M/170M [00:00<00:02, 59.4MB/s]
+ 14%|#4 | 24.0M/170M [00:00<00:02, 57.0MB/s]
+ 19%|#8 | 32.0M/170M [00:00<00:02, 57.4MB/s]
+ 25%|##5 | 42.6M/170M [00:00<00:02, 60.8MB/s]
+ 31%|### | 52.0M/170M [00:00<00:01, 70.2MB/s]
+ 35%|###4 | 59.1M/170M [00:00<00:01, 68.7MB/s]
+ 40%|#### | 68.4M/170M [00:01<00:01, 76.5MB/s]
+ 45%|####4 | 76.0M/170M [00:01<00:01, 70.6MB/s]
+ 49%|####9 | 83.9M/170M [00:01<00:01, 73.9MB/s]
+ 54%|#####3 | 91.2M/170M [00:01<00:01, 70.4MB/s]
+ 58%|#####7 | 98.1M/170M [00:01<00:01, 64.7MB/s]
+ 61%|######1 | 104M/170M [00:01<00:01, 62.3MB/s]
+ 70%|####### | 119M/170M [00:01<00:00, 87.0MB/s]
+ 75%|#######5 | 128M/170M [00:01<00:00, 72.3MB/s]
+ 80%|######## | 136M/170M [00:02<00:00, 73.9MB/s]
+ 85%|########4 | 144M/170M [00:02<00:00, 68.7MB/s]
+ 89%|########9 | 152M/170M [00:02<00:00, 68.9MB/s]
+ 94%|#########4| 160M/170M [00:02<00:00, 72.1MB/s]
+ 98%|#########8| 167M/170M [00:02<00:00, 71.2MB/s]
+100%|##########| 170M/170M [00:02<00:00, 69.4MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode=& [...]
@@ -575,7 +577,7 @@ 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 27.290 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 42.915 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7795da4b258c8feff986668b95ef57ad/deploy_object_detection_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_object_detection_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized.html b/docs/how_to/deploy_models/deploy_prequantized.html
index af838eb47c..63e77cc833 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -495,8 +500,8 @@ training. Other models require a full post training calibration.</p>
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 59%|#####8 | 7.99M/13.6M [00:00<00:00, 46.2MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 70.5MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 61.1MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 86.1MB/s]
</pre></div>
</div>
</div>
@@ -587,7 +592,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 88.2023 88.0587 92.6748 87.9495 0.5394
+ 90.1994 90.1297 93.5782 90.0036 0.3756
</pre></div>
</div>
<div class="admonition note">
@@ -626,7 +631,7 @@ 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">ΒΆ</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 15.071 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 17.695 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/fb8217c13f4351224c6cf3aacf1a87fc/deploy_prequantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized_tflite.html b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
index 49b003fe01..dae6c88054 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -580,7 +585,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 117.6103 117.5951 118.2696 116.8346 0.2654
+ 120.2610 120.2151 123.7796 119.4926 0.4966
</pre></div>
</div>
<div class="admonition note">
@@ -608,7 +613,7 @@ 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 34.549 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 36.418 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/56691c7a27d45da61d112276334640d3/deploy_prequantized_tflite.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized_tflite.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_quantized.html b/docs/how_to/deploy_models/deploy_quantized.html
index 7df4da4bdf..ec8b469ffa 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -521,7 +526,7 @@ 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 34.455 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 34.272 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7810ecf51bfc05f7d5e8a400ac3e815d/deploy_quantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_quantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_sparse.html b/docs/how_to/deploy_models/deploy_sparse.html
index 91b0e42d15..213fb76ad8 100644
--- a/docs/how_to/deploy_models/deploy_sparse.html
+++ b/docs/how_to/deploy_models/deploy_sparse.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
index 6863bcf8af..482801e7cc 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -463,22 +468,23 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|5 | 7266/132723 [00:00<00:01, 72651.58KB/s]
- 12%|#2 | 16240/132723 [00:00<00:01, 82698.75KB/s]
- 19%|#8 | 25100/132723 [00:00<00:01, 85390.02KB/s]
- 25%|##5 | 33640/132723 [00:00<00:01, 53706.78KB/s]
- 32%|###1 | 41925/132723 [00:00<00:01, 61334.45KB/s]
- 37%|###7 | 49140/132723 [00:00<00:01, 55995.95KB/s]
- 42%|####1 | 55453/132723 [00:00<00:01, 56391.18KB/s]
- 48%|####8 | 64353/132723 [00:01<00:01, 64891.31KB/s]
- 55%|#####5 | 73235/132723 [00:01<00:00, 71382.93KB/s]
- 62%|######1 | 82156/132723 [00:01<00:00, 76362.36KB/s]
- 69%|######8 | 91134/132723 [00:01<00:00, 80187.74KB/s]
- 75%|#######5 | 100112/132723 [00:01<00:00, 82962.58KB/s]
- 82%|########2 | 109131/132723 [00:01<00:00, 85075.34KB/s]
- 89%|########8 | 118025/132723 [00:01<00:00, 86206.52KB/s]
- 96%|#########5| 127017/132723 [00:01<00:00, 87302.26KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 74612.79KB/s]
+ 4%|3 | 5222/132723 [00:00<00:02, 52212.33KB/s]
+ 9%|9 | 12133/132723 [00:00<00:01, 62148.35KB/s]
+ 15%|#4 | 19699/132723 [00:00<00:01, 68315.85KB/s]
+ 21%|##1 | 28271/132723 [00:00<00:01, 75183.22KB/s]
+ 28%|##7 | 36713/132723 [00:00<00:01, 78509.17KB/s]
+ 34%|###4 | 45195/132723 [00:00<00:01, 80643.66KB/s]
+ 40%|#### | 53752/132723 [00:00<00:00, 82249.25KB/s]
+ 47%|####6 | 62185/132723 [00:00<00:00, 82910.08KB/s]
+ 53%|#####3 | 70706/132723 [00:00<00:00, 83626.59KB/s]
+ 60%|#####9 | 79289/132723 [00:01<00:00, 84304.74KB/s]
+ 66%|######6 | 87817/132723 [00:01<00:00, 84599.64KB/s]
+ 73%|#######2 | 96277/132723 [00:01<00:00, 84420.51KB/s]
+ 79%|#######8 | 104720/132723 [00:01<00:00, 84150.02KB/s]
+ 85%|########5 | 113339/132723 [00:01<00:00, 84760.09KB/s]
+ 92%|#########1| 121919/132723 [00:01<00:00, 85069.66KB/s]
+ 98%|#########8| 130572/132723 [00:01<00:00, 85506.30KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 81499.18KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -517,7 +523,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 43.632 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 50.963 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/cccb17d28e5e8b2e94ea8cd5ec59f6ed/deploy_ssd_gluoncv.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_ssd_gluoncv.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/index.html b/docs/how_to/deploy_models/index.html
index b9afbbdaf1..ed6ff31322 100644
--- a/docs/how_to/deploy_models/index.html
+++ b/docs/how_to/deploy_models/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/deploy_models/sg_execution_times.html b/docs/how_to/deploy_models/sg_execution_times.html
index 9b77e51322..f47f653444 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -199,6 +199,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -340,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">ΒΆ</a></h1>
-<p><strong>15:08.228</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>15:38.964</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,39 +354,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>03:43.632</p></td>
+<td><p>03:50.963</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:27.290</p></td>
+<td><p>03:42.915</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>02:34.549</p></td>
+<td><p>02:36.418</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></td>
-<td><p>01:34.455</p></td>
+<td><p>01:34.272</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:15.071</p></td>
+<td><p>01:17.695</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_adreno.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno.py</span></code>)</p></td>
-<td><p>00:55.824</p></td>
+<td><p>00:56.798</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:41.770</p></td>
+<td><p>00:43.077</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:27.994</p></td>
+<td><p>00:28.643</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:27.637</p></td>
+<td><p>00:28.177</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 3983dc7235..35af6c7559 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -619,7 +624,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip4cbfe758-7622-491b-bd51-a4e4afe01bb7 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.zip185f8114-67e0-49b9-a251-870552496085 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
</pre></div>
</div>
<p>Itβs easy to execute MobileNet with native TVM:</p>
diff --git a/docs/how_to/extend_tvm/index.html b/docs/how_to/extend_tvm/index.html
index 0b0d4d625d..a1b188e150 100644
--- a/docs/how_to/extend_tvm/index.html
+++ b/docs/how_to/extend_tvm/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
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 fe208eaa10..0e778803a2 100644
--- a/docs/how_to/extend_tvm/low_level_custom_pass.html
+++ b/docs/how_to/extend_tvm/low_level_custom_pass.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 96ce49e690..b8295beb13 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -199,6 +199,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -340,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">ΒΆ</a></h1>
-<p><strong>00:54.377</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:54.888</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +354,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:50.575</p></td>
+<td><p>00:50.811</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></td>
-<td><p>00:02.720</p></td>
+<td><p>00:02.767</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:01.074</p></td>
+<td><p>00:01.302</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_infra.html b/docs/how_to/extend_tvm/use_pass_infra.html
index 7d301f1aa0..60a0c4ee4c 100644
--- a/docs/how_to/extend_tvm/use_pass_infra.html
+++ b/docs/how_to/extend_tvm/use_pass_infra.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 05435e5607..11b174b289 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -526,10 +531,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 22781us [22781us] (49.75%; 49.75%)
-FoldScaleAxis: 23006us [7us] (50.25%; 50.25%)
- FoldConstant: 22999us [1674us] (50.23%; 99.97%)
- InferType: 21325us [21325us] (46.57%; 92.72%)
+InferType: 22179us [22179us] (48.78%; 48.78%)
+FoldScaleAxis: 23284us [7us] (51.22%; 51.22%)
+ FoldConstant: 23277us [1666us] (51.20%; 99.97%)
+ InferType: 21611us [21611us] (47.54%; 92.84%)
</pre></div>
</div>
</div>
@@ -551,10 +556,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 21244us [21244us] (47.84%; 47.84%)
-FoldScaleAxis: 23167us [5us] (52.16%; 52.16%)
- FoldConstant: 23162us [1659us] (52.15%; 99.98%)
- InferType: 21502us [21502us] (48.42%; 92.84%)
+InferType: 21627us [21627us] (48.34%; 48.34%)
+FoldScaleAxis: 23110us [5us] (51.66%; 51.66%)
+ FoldConstant: 23104us [1712us] (51.65%; 99.98%)
+ InferType: 21393us [21393us] (47.82%; 92.59%)
</pre></div>
</div>
<p>Register empty list to clear existing instruments.</p>
diff --git a/docs/how_to/index.html b/docs/how_to/index.html
index 11c0a71fcb..4b70c25c29 100644
--- a/docs/how_to/index.html
+++ b/docs/how_to/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/optimize_operators/index.html b/docs/how_to/optimize_operators/index.html
index a12467100e..8c20383a70 100644
--- a/docs/how_to/optimize_operators/index.html
+++ b/docs/how_to/optimize_operators/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/optimize_operators/opt_conv_cuda.html b/docs/how_to/optimize_operators/opt_conv_cuda.html
index a361bc5d95..9d9721e1af 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -575,7 +580,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 48.641311 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.343681 ms
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-optimize-operators-opt-conv-cuda-py">
diff --git a/docs/how_to/optimize_operators/opt_conv_tensorcore.html b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
index a772fb7f75..9c3adfcbac 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -867,7 +872,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.350146 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.903427 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 c4cbeda8e6..bae068701f 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -472,8 +477,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.016757
-Baseline: 3.303109
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018578
+Baseline: 3.402711
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -532,7 +537,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.295757
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.317495
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -589,7 +594,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.328162
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.343500
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -644,7 +649,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.114045
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.118646
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -721,7 +726,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109349
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109404
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -799,7 +804,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.101966
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111543
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -879,7 +884,7 @@ class Module:
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.133909
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146951
</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 323b34eb6f..9a76947b7c 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -199,6 +199,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -340,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">ΒΆ</a></h1>
-<p><strong>00:33.378</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.493</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +354,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:30.829</p></td>
+<td><p>00:32.674</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></td>
-<td><p>00:01.532</p></td>
+<td><p>00:01.646</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></td>
-<td><p>00:01.017</p></td>
+<td><p>00:01.173</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/profile/index.html b/docs/how_to/profile/index.html
index 649b8befa3..b42586f8e9 100644
--- a/docs/how_to/profile/index.html
+++ b/docs/how_to/profile/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/profile/papi.html b/docs/how_to/profile/papi.html
index 3bfd479553..d42d3dcbb2 100644
--- a/docs/how_to/profile/papi.html
+++ b/docs/how_to/profile/papi.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/index.html b/docs/how_to/tune_with_autoscheduler/index.html
index fe5d1bde18..52d72566e1 100644
--- a/docs/how_to/tune_with_autoscheduler/index.html
+++ b/docs/how_to/tune_with_autoscheduler/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</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 a0a2d2a097..c7dcca8a21 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -199,6 +199,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -340,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">ΒΆ</a></h1>
-<p><strong>09:46.825</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>10:04.072</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -349,27 +354,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>06:00.304</p></td>
+<td><p>06:10.908</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:39.930</p></td>
+<td><p>01:43.475</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>01:07.316</p></td>
+<td><p>01:08.927</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:32.242</p></td>
+<td><p>00:32.698</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:13.827</p></td>
+<td><p>00:14.341</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:13.206</p></td>
+<td><p>00:13.723</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
index 58c6399a68..3c926e4e06 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
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -489,6 +494,9 @@ file and apply it.</p>
<span class="k">del</span> <span class="n">measure_ctx</span>
</pre></div>
</div>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>.T
+</pre></div>
+</div>
<p>We can lower the schedule to see the IR after auto-scheduling.
The auto-scheduler correctly performs optimizations including multi-level tiling,
cooperative fetching, unrolling and operator fusion.</p>
@@ -506,162 +514,36 @@ class Module:
def main(data: T.Buffer((1, 512, 7, 7), "float32"), kernel: T.Buffer((512, 512, 3, 3), "float32"), bias: T.Buffer((1, 512, 1, 1), "float32"), compute: T.Buffer((1, 512, 7, 7), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
blockIdx_x = T.env_thread("blockIdx.x")
- T.launch_thread(blockIdx_x, 32)
- conv2d_nchw = T.allocate([14], "float32", "local")
- pad_temp_shared = T.allocate([1008], "float32", "shared")
- kernel_shared = T.allocate([768], "float32", "shared")
+ T.launch_thread(blockIdx_x, 16)
+ conv2d_nchw = T.allocate([7], "float32", "local")
+ pad_temp_shared = T.allocate([324], "float32", "shared")
+ kernel_shared = T.allocate([1152], "float32", "shared")
threadIdx_x = T.env_thread("threadIdx.x")
- T.launch_thread(threadIdx_x, 56)
- conv2d_nchw_1 = T.Buffer((14,), data=conv2d_nchw, scope="local", align=32)
- conv2d_nchw_1[0] = T.float32(0)
- conv2d_nchw_1[1] = T.float32(0)
- conv2d_nchw_1[2] = T.float32(0)
- conv2d_nchw_1[3] = T.float32(0)
- conv2d_nchw_1[4] = T.float32(0)
- conv2d_nchw_1[5] = T.float32(0)
- conv2d_nchw_1[6] = T.float32(0)
- conv2d_nchw_1[7] = T.float32(0)
- conv2d_nchw_1[8] = T.float32(0)
- conv2d_nchw_1[9] = T.float32(0)
- conv2d_nchw_1[10] = T.float32(0)
- conv2d_nchw_1[11] = T.float32(0)
- conv2d_nchw_1[12] = T.float32(0)
- conv2d_nchw_1[13] = T.float32(0)
- for rc_outer_outer, rx_outer_outer in T.grid(32, 3):
- cse_var_2: T.int32 = rc_outer_outer * 784
- cse_var_1: T.int32 = rc_outer_outer * 144
- threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.Buffer((1008,), data=pad_temp_shared, scope="shared")
- data_1 = T.Buffer((25088,), data=data.data)
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 56] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 56) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 112] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 112) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 168] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 168) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 224] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 224) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 280] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 280) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 336] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 336) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 392] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 2) % 9 and (threadIdx_x_1 // 7 + 2) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 392) // 63 * 49 + (threadIdx_x_1 // 7 + 2) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 448] = T.if_then_else(threadIdx_x_1 < 49 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 448) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 504] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer + 384], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 560] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 560) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 616] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 616) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 672] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 672) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 728] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 728) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 784] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 784) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 840] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 840) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 896] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 2) % 9 and (threadIdx_x_1 // 7 + 2) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 896) // 63 * 49 + (threadIdx_x_1 // 7 + 2) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 + 952] = T.if_then_else(threadIdx_x_1 < 49 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 952) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
- threadIdx_x_2 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((768,), data=kernel_shared, scope="shared")
- kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[(threadIdx_x_2 + 56) // 48 * 48 + (threadIdx_x_2 + 8) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 56) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[(threadIdx_x_2 + 112) // 48 * 48 + (threadIdx_x_2 + 16) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 112) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 16) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[(threadIdx_x_2 + 168) // 48 * 48 + (threadIdx_x_2 // 3 + 8) % 16 * 3 + threadIdx_x_2 % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 168) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 // 3 + 8) % 16 * 9 + threadIdx_x_2 % 3 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[(threadIdx_x_2 + 224) // 48 * 48 + (threadIdx_x_2 + 32) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 224) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 32) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[(threadIdx_x_2 + 280) // 48 * 48 + (threadIdx_x_2 + 40) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 280) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 40) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 336] = kernel_1[blockIdx_x * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + rx_outer_outer + 32256]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[(threadIdx_x_2 + 392) // 48 * 48 + (threadIdx_x_2 + 8) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 392) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[(threadIdx_x_2 + 448) // 48 * 48 + (threadIdx_x_2 + 16) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 448) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 16) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[(threadIdx_x_2 + 504) // 48 * 48 + (threadIdx_x_2 // 3 + 8) % 16 * 3 + threadIdx_x_2 % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 504) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 // 3 + 8) % 16 * 9 + threadIdx_x_2 % 3 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[(threadIdx_x_2 + 560) // 48 * 48 + (threadIdx_x_2 + 32) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 560) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 32) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[(threadIdx_x_2 + 616) // 48 * 48 + (threadIdx_x_2 + 40) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 616) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 40) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 672] = kernel_1[blockIdx_x * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + rx_outer_outer + 64512]
- with T.launch_thread(threadIdx_x_2, 56):
- if T.likely(threadIdx_x_2 < 40):
- kernel_shared_1[(threadIdx_x_2 + 728) // 48 * 48 + (threadIdx_x_2 + 8) // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 728) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + rx_outer_outer]
- for rc_outer_inner, ry_outer_inner in T.grid(4, 3):
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 3] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 4] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 5] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 6] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 3]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 3]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 3]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 66] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 3]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 67] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 3]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 68] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 3]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 69] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 3]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 6]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 127] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 6]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 128] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 6]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 129] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 6]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 130] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 6]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 131] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 6]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 132] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 6]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 189] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 9]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 190] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 9]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 191] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 9]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 192] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 9]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 193] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 9]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 194] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 9]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 195] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 9]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 48]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 48]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 48]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 3] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 48]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 4] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 48]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 5] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 48]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 6] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 48]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 51]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 51]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 51]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 66] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 51]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 67] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 51]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 68] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 51]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 69] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 51]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 54]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 127] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 54]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 128] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 54]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 129] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 54]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 130] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 54]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 131] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 54]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 132] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 54]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 189] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 57]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 190] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 57]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 191] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 57]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 192] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 57]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 193] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 57]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 194] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 57]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + ry_outer_inner * 7 + threadIdx_x % 7 * 7 + 195] * kernel_shared_1[threadIdx_x // 7 * 96 + rc_outer_inner * 12 + ry_outer_inner + 57]
- for i1_inner, i3_inner in T.grid(2, 7):
+ T.launch_thread(threadIdx_x, 224)
+ conv2d_nchw_1 = T.Buffer((7,), data=conv2d_nchw, scope="local", align=16)
+ for xx_inner_init in range(7):
+ conv2d_nchw_1[xx_inner_init] = T.float32(0)
+ for rc_outer_outer in range(128):
+ pad_temp_shared_1 = T.Buffer((324,), data=pad_temp_shared, scope="shared")
+ for ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer in range(2):
+ threadIdx_x_1 = T.env_thread("threadIdx.x")
+ T.launch_thread(threadIdx_x_1, 224)
+ if T.likely(ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56 + threadIdx_x_1 // 4 < 81):
+ data_1 = T.Buffer((25088,), data=data.data)
+ pad_temp_shared_1[ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224 + threadIdx_x_1] = T.if_then_else(9 <= (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 62 + threadIdx_x_1) % 81 and (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 62 + threadIdx_x_1) % 81 < 72 and 1 <= (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8 + threadIdx_x_1) % 9 and (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8 + threadIdx_x_1) % 9 < 8, data_1[rc_outer_outer * 196 + (a [...]
+ kernel_shared_1 = T.Buffer((1152,), data=kernel_shared, scope="shared")
+ for ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer in range(6):
+ threadIdx_x_1 = T.env_thread("threadIdx.x")
+ T.launch_thread(threadIdx_x_1, 224)
+ if T.likely(ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7 + threadIdx_x_1 // 32 < 36):
+ kernel_1 = T.Buffer((2359296,), data=kernel.data)
+ kernel_shared_1[ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224 + threadIdx_x_1] = kernel_1[blockIdx_x * 147456 + (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56 + threadIdx_x_1 // 4) // 9 * 4608 + rc_outer_outer * 36 + (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8 + threadIdx_x_1) % 36 // 3 * 3 + (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2 + threadIdx_x_1) % 3]
+ for rc_inner, ry_inner, rx_inner, xx_inner in T.grid(4, 3, 3, 7):
+ conv2d_nchw_1[xx_inner] = conv2d_nchw_1[xx_inner] + pad_temp_shared_1[rc_inner * 81 + ry_inner * 9 + threadIdx_x % 7 * 9 + xx_inner + rx_inner] * kernel_shared_1[threadIdx_x // 7 * 36 + rc_inner * 9 + ry_inner * 3 + rx_inner]
+ for i3_inner in range(7):
compute_1 = T.Buffer((25088,), data=compute.data)
bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + i3_inner] = T.max(conv2d_nchw_1[i1_inner * 7 + i3_inner] + bias_1[blockIdx_x * 16 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 1568 + threadIdx_x * 7 + i3_inner] = T.max(conv2d_nchw_1[i3_inner] + bias_1[blockIdx_x * 32 + threadIdx_x // 7], T.float32(0))
</pre></div>
</div>
</div>
@@ -695,7 +577,7 @@ class Module:
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.371 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.342 ms
</pre></div>
</div>
</div>
@@ -725,8 +607,8 @@ conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+conv2d_nchw_ff_o_o_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_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
@@ -737,17 +619,17 @@ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+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_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
@@ -773,14 +655,14 @@ 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=56)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 0)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -798,128 +680,38 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[1008];
- __shared__ float kernel_shared[768];
- conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 784) + ((int)threadIdx.x)) + rx_outer_outer) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 56) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 112) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 168)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 168) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 224) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 280) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 336) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = ((((((int)threadIdx.x) < 49) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 448) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 504)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 784) + ((int)threadIdx.x)) + rx_outer_outer) + 384)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 560) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 616) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 672) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 728)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 728) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 840)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 840) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 896) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 952)] = ((((((int)threadIdx.x) < 49) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 952) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + rx_outer_outer)];
- kernel_shared[(((((((int)threadIdx.x) + 56) / 48) * 48) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((((((int)threadIdx.x) + 112) / 48) * 48) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((((((int)threadIdx.x) + 168) / 48) * 48) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 3)) + (((int)threadIdx.x) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((((((int)threadIdx.x) + 224) / 48) * 48) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((((((int)threadIdx.x) + 280) / 48) * 48) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + rx_outer_outer) + 32256)];
- kernel_shared[(((((((int)threadIdx.x) + 392) / 48) * 48) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((((((int)threadIdx.x) + 448) / 48) * 48) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((((((int)threadIdx.x) + 504) / 48) * 48) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 3)) + (((int)threadIdx.x) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 504) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((((((int)threadIdx.x) + 560) / 48) * 48) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((((((int)threadIdx.x) + 616) / 48) * 48) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 616) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + rx_outer_outer) + 64512)];
- if (((int)threadIdx.x) < 40) {
- kernel_shared[(((((((int)threadIdx.x) + 728) / 48) * 48) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 728) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+extern "C" __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[7];
+ __shared__ float pad_temp_shared[324];
+ __shared__ float kernel_shared[1152];
+ for (int xx_inner_init = 0; xx_inner_init < 7; ++xx_inner_init) {
+ conv2d_nchw[xx_inner_init] = 0.000000e+00f;
+ }
+ for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
+ __syncthreads();
+ for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 2; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) < 81) {
+ pad_temp_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224) + ((int)threadIdx.x))] = (((((9 <= (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 62) + ((int)threadIdx.x)) % 81)) && ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 62) + ((int)threadIdx.x)) % 81) < 72)) && (1 <= (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + ((int)threadIdx.x)) % 9))) && ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + ((int)threadIdx [...]
+ }
+ }
+ for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 < 6; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1) {
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 7) + (((int)threadIdx.x) >> 5)) < 36) {
+ kernel_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 224) + ((int)threadIdx.x))] = kernel[(((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 56) + (((int)threadIdx.x) >> 2)) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 8) + ((int)threadIdx.x)) % 36) / 3) * 3)) + (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 2) + ((int)threadIdx.x)) % 3))];
}
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 64)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 65)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 66)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 67)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 68)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 69)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 127)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 128)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 129)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 130)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 131)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 132)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 190)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 191)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 192)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 193)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 194)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 195)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 48)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 48)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 48)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 48)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 48)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 48)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 48)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 51)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 64)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 51)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 65)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 51)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 66)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 51)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 67)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 51)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 68)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 51)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 69)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 51)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 54)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 127)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 54)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 128)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 54)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 129)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 54)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 130)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 54)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 131)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 54)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 132)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 54)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 57)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 190)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 57)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 191)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 57)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 192)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 57)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 193)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 57)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 194)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 57)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 252) + (ry_outer_inner * 7)) + ((((int)threadIdx.x) % 7) * 7)) + 195)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 12)) + ry_outer_inner) + 57)]));
+ }
+ __syncthreads();
+ for (int rc_inner = 0; rc_inner < 4; ++rc_inner) {
+ for (int ry_inner = 0; ry_inner < 3; ++ry_inner) {
+ for (int rx_inner = 0; rx_inner < 3; ++rx_inner) {
+ for (int xx_inner = 0; xx_inner < 7; ++xx_inner) {
+ conv2d_nchw[xx_inner] = (conv2d_nchw[xx_inner] + (pad_temp_shared[(((((rc_inner * 81) + (ry_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_inner) + rx_inner)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_inner * 9)) + (ry_inner * 3)) + rx_inner)]));
+ }
}
}
}
}
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- }
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
}
}
</pre></div>
@@ -954,7 +746,7 @@ 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> ( 6 minutes 0.304 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 10.908 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e3e540f3b477c0c52d8eb73e674e8ffd/tune_conv2d_layer_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_conv2d_layer_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_arm.html b/docs/how_to/tune_with_autoscheduler/tune_network_arm.html
index 9f48e531ac..092022e97a 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_arm.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_arm.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
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 bf53e9fb67..4c7a73100f 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -916,7 +921,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.9344 7.9381 7.9475 7.9175 0.0125
+ 7.8981 7.8975 7.9038 7.8931 0.0044
</pre></div>
</div>
</div>
@@ -938,7 +943,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.316 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.927 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/eafe360d52540634c9eea0fa89e804bd/tune_network_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_mali.html b/docs/how_to/tune_with_autoscheduler/tune_network_mali.html
index 4322f4a8d4..35d082b646 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_mali.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_mali.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index dd5b8eb64e..eff08298f0 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -935,7 +940,7 @@ 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)
- 723.1857 720.7894 728.1370 720.6308 3.5016
+ 755.8260 752.9500 763.6801 750.8478 5.6197
</pre></div>
</div>
</div>
@@ -957,7 +962,7 @@ 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 39.930 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 43.475 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e416b94ca1090b0897c0f6e0df95b911/tune_network_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_x86.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
index 443106f788..4d0bd96423 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -635,23 +640,82 @@ class Module:
for i0_outer_i1_outer_fused in T.parallel(256):
compute_1 = T.allocate([256], "float32", "global")
compute_2 = T.Buffer((256,), data=compute_1)
- for nb_j_inner in range(2):
- for i_inner_init, j_init in T.grid(8, 16):
- compute_2[i_inner_init * 32 + nb_j_inner * 16 + j_init] = T.float32(0)
- for elem_idx, i_inner, j in T.grid(T.let(cse_var_1, i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner, placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]), 8, 16):
- cse_var_1 = T.int32()
+ for i_outer_inner in range(16):
+ cse_var_2: T.int32 = i_outer_inner * 16
+ cse_var_1: T.int32 = i0_outer_i1_outer_fused % 64 // 2
+ compute_2[cse_var_2] = T.float32(0)
+ compute_2[cse_var_2 + 1] = T.float32(0)
+ compute_2[cse_var_2 + 2] = T.float32(0)
+ compute_2[cse_var_2 + 3] = T.float32(0)
+ compute_2[cse_var_2 + 4] = T.float32(0)
+ compute_2[cse_var_2 + 5] = T.float32(0)
+ compute_2[cse_var_2 + 6] = T.float32(0)
+ compute_2[cse_var_2 + 7] = T.float32(0)
+ compute_2[cse_var_2 + 8] = T.float32(0)
+ compute_2[cse_var_2 + 9] = T.float32(0)
+ compute_2[cse_var_2 + 10] = T.float32(0)
+ compute_2[cse_var_2 + 11] = T.float32(0)
+ compute_2[cse_var_2 + 12] = T.float32(0)
+ compute_2[cse_var_2 + 13] = T.float32(0)
+ compute_2[cse_var_2 + 14] = T.float32(0)
+ compute_2[cse_var_2 + 15] = T.float32(0)
+ for elem_idx in range(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
- cse_var_3: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
- cse_var_2: T.int32 = i_inner * 32 + nb_j_inner * 16 + j
placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
placeholder_7 = T.Buffer((32768,), data=placeholder.data)
placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
- compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer_i1_outer_fused // 16 * 2048 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
- for i0_inner, i1_inner in T.grid(8, 32):
- cse_var_4: T.int32 = i0_outer_i1_outer_fused // 16 * 4096 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32 + i1_inner
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_3: T.int32 = cse_var_2 + 1
+ compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_4: T.int32 = cse_var_2 + 2
+ compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_5: T.int32 = cse_var_2 + 3
+ compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_6: T.int32 = cse_var_2 + 4
+ compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_7: T.int32 = cse_var_2 + 5
+ compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 5] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_8: T.int32 = cse_var_2 + 6
+ compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 6] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_9: T.int32 = cse_var_2 + 7
+ compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 7] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_10: T.int32 = cse_var_2 + 8
+ compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_11: T.int32 = cse_var_2 + 9
+ compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_12: T.int32 = cse_var_2 + 10
+ compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_13: T.int32 = cse_var_2 + 11
+ compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_14: T.int32 = cse_var_2 + 12
+ compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_15: T.int32 = cse_var_2 + 13
+ compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 5] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_16: T.int32 = cse_var_2 + 14
+ compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 6] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
+ if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ cse_var_17: T.int32 = cse_var_2 + 15
+ compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 7] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 8192 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
+ for i0_inner in range(32):
+ cse_var_18: T.int32 = i0_outer_i1_outer_fused // 64 * 16384 + i0_inner * 512 + i0_outer_i1_outer_fused % 64 * 8
compute_3 = T.Buffer((65536,), data=compute.data)
placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
- compute_3[cse_var_4] = T.max(compute_2[i0_inner * 32 + i1_inner] + placeholder_5[cse_var_4], T.float32(0))
+ compute_3[cse_var_18:cse_var_18 + 8] = T.max(compute_2[i0_inner * 8:i0_inner * 8 + 8] + placeholder_5[cse_var_18:cse_var_18 + 8], T.Broadcast(T.float32(0), 8))
</pre></div>
</div>
</div>
@@ -685,7 +749,7 @@ class Module:
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.584 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.288 ms
</pre></div>
</div>
<div class="admonition note">
diff --git a/docs/how_to/tune_with_autotvm/index.html b/docs/how_to/tune_with_autotvm/index.html
index 8fd251b413..b976cc3f4d 100644
--- a/docs/how_to/tune_with_autotvm/index.html
+++ b/docs/how_to/tune_with_autotvm/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
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 1186e49ba3..95e6a17da8 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -199,6 +199,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -340,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">ΒΆ</a></h1>
-<p><strong>00:53.891</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:42.384</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +354,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:53.856</p></td>
+<td><p>00:42.349</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.021</p></td>
+<td><p>00:00.020</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
-<td><p>00:00.005</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
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 8a01999252..a8d1e8a068 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -568,130 +573,8 @@ for this template</p>
waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target=target, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1734
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:451
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1753
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1697
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1621
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
-Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1734
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:451
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1753
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1697
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1621
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10228095
-No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+No: 1 GFLOPS: 127.62/127.62 result: MeasureResult(costs=(0.001813984985074627,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.11116623878479, timestamp=1677845860.7700906) [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1215527
+No: 2 GFLOPS: 0.00/127.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -813,8 +696,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10091340
-No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8515723
+No: 3 GFLOPS: 18.15/127.62 result: MeasureResult(costs=(0.01275651888888889,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.876296281814575, timestamp=1677845863.33124) [('tile_f', [-1, 16, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8033368
+No: 4 GFLOPS: 0.00/127.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -936,9 +820,10 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2161210
-No: 4 GFLOPS: 6.90/6.90 result: MeasureResult(costs=(0.03354587925,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.678717613220215, timestamp=1677805465.9553194) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7951583
-No: 5 GFLOPS: 0.00/6.90 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3518318
+No: 5 GFLOPS: 6.24/127.62 result: MeasureResult(costs=(0.03711889625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.749978065490723, timestamp=1677845869.7278771) [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8330306
+No: 6 GFLOPS: 3.87/127.62 result: MeasureResult(costs=(0.059764766500000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.930164098739624, timestamp=1677845870.9373977) [('tile_f', [-1, 4, 1, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1780867
+No: 7 GFLOPS: 0.00/127.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1060,10 +945,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4482313
-No: 6 GFLOPS: 8.62/8.62 result: MeasureResult(costs=(0.026846216,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.123527765274048, timestamp=1677805476.8576145) [('tile_f', [-1, 4, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1862842
-No: 7 GFLOPS: 4.16/8.62 result: MeasureResult(costs=(0.055586814750000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=9.57439661026001, timestamp=1677805478.0032456) [('tile_f', [-1, 16, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3650519
-No: 8 GFLOPS: 0.00/8.62 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 64, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4181808
+No: 8 GFLOPS: 0.00/127.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1185,8 +1068,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,449315
-No: 9 GFLOPS: 0.00/8.62 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7690881
+No: 9 GFLOPS: 0.00/127.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1308,9 +1191,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6863773
-No: 10 GFLOPS: 34.59/34.59 result: MeasureResult(costs=(0.006693454941176471,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1895654201507568, timestamp=1677805479.3749352) [('tile_f', [-1, 2, 64, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5368095
-No: 11 GFLOPS: 0.00/34.59 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7306692
+No: 10 GFLOPS: 0.00/127.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1432,8 +1314,10 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9810008
-No: 12 GFLOPS: 0.00/34.59 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9536542
+No: 11 GFLOPS: 41.77/127.62 result: MeasureResult(costs=(0.0055423053181818185,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0154471397399902, timestamp=1677845874.6394875) [('tile_f', [-1, 1, 8, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1212101
+No: 12 GFLOPS: 179.25/179.25 result: MeasureResult(costs=(0.0012915266693548386,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.900968074798584, timestamp=1677845875.6529262) [('tile_f', [-1, 1, 32, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8728850
+No: 13 GFLOPS: 0.00/179.25 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1555,8 +1439,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4052515
-No: 13 GFLOPS: 0.00/34.59 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,61297
+No: 14 GFLOPS: 18.54/179.25 result: MeasureResult(costs=(0.012488249,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4176852703094482, timestamp=1677845877.2635472) [('tile_f', [-1, 1, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6778174
+No: 15 GFLOPS: 0.00/179.25 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1678,9 +1563,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1925144
-No: 14 GFLOPS: 8.18/34.59 result: MeasureResult(costs=(0.028291608750000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7224013805389404, timestamp=1677805481.3147876) [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6877563
-No: 15 GFLOPS: 0.00/34.59 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,822895
+No: 16 GFLOPS: 0.00/179.25 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1802,8 +1686,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3737494
-No: 16 GFLOPS: 0.00/34.59 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8072379
+No: 17 GFLOPS: 0.00/179.25 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1925,8 +1809,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10150224
-No: 17 GFLOPS: 0.00/34.59 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,53422
+No: 18 GFLOPS: 0.00/179.25 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2048,27 +1932,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6075407
-No: 18 GFLOPS: 149.79/149.79 result: MeasureResult(costs=(0.0015454607605633803,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.803270101547241, timestamp=1677805492.3559427) [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7983936
-No: 19 GFLOPS: 0.00/149.79 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
- res = future.result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
- return self.__get_result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
- raise self._exception
- File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
- result = self.fn(*self.args, **self.kwargs)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
- worker = lambda *args: self._worker_run(*args)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
- return proc.recv()
- File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
- raise TimeoutError()
-TimeoutError
-
- [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8917762
-No: 20 GFLOPS: 0.00/149.79 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2240825
+No: 19 GFLOPS: 0.00/179.25 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2190,7 +2055,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1993755
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 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,10013435
+No: 20 GFLOPS: 35.83/179.25 result: MeasureResult(costs=(0.006461237818181819,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.405557155609131, timestamp=1677845879.9267914) [('tile_f', [-1, 1, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8213580
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2229,9 +2095,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7983936
+[('tile_f', [-1, 1, 32, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8728850
Finish loading 20 records
-Time cost of this operator: 0.001374
+Time cost of this operator: 0.001636
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/how_to/tune_with_autotvm/tune_relay_arm.html b/docs/how_to/tune_with_autotvm/tune_relay_arm.html
index cf1a39a9ac..e48e33a16b 100644
--- a/docs/how_to/tune_with_autotvm/tune_relay_arm.html
+++ b/docs/how_to/tune_with_autotvm/tune_relay_arm.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
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 629f111259..18f5d33e54 100644
--- a/docs/how_to/tune_with_autotvm/tune_relay_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_relay_cuda.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
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 75d28dd230..57aa002d07 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
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
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 3cbb394144..0547b832b9 100644
--- a/docs/how_to/tune_with_autotvm/tune_relay_x86.html
+++ b/docs/how_to/tune_with_autotvm/tune_relay_x86.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/work_with_microtvm/index.html b/docs/how_to/work_with_microtvm/index.html
index f63b2d9041..aea6484cb8 100644
--- a/docs/how_to/work_with_microtvm/index.html
+++ b/docs/how_to/work_with_microtvm/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/work_with_microtvm/micro_aot.html b/docs/how_to/work_with_microtvm/micro_aot.html
index 015722cec6..dbc93886f6 100644
--- a/docs/how_to/work_with_microtvm/micro_aot.html
+++ b/docs/how_to/work_with_microtvm/micro_aot.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index 79c9aff7da..99a383b836 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -643,10 +648,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.8 98.74 (1, 2, 10, 10, 3) 2 1 [315.8]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.057 0.956 (1, 6, 10, 10) 1 1 [3.057]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.972 0.304 (1, 1, 10, 10, 3) 1 1 [0.972]
-Total_time - 319.828 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 317.0 98.733 (1, 2, 10, 10, 3) 2 1 [317.0]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.113 0.97 (1, 6, 10, 10) 1 1 [3.113]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.954 0.297 (1, 1, 10, 10, 3) 1 1 [0.954]
+Total_time - 321.067 - - - - -
</pre></div>
</div>
</div>
@@ -698,13 +703,13 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.3 97.306 (1, 6, 10, 10, 1) 2 1 [100.3]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.8 1.746 (1, 6, 10, 10) 1 1 [1.8]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.977 0.948 (1, 1, 10, 10, 3) 1 1 [0.977]
-Total_time - 103.077 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.7 97.357 (1, 6, 10, 10, 1) 2 1 [100.7]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.76 1.701 (1, 6, 10, 10) 1 1 [1.76]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.974 0.942 (1, 1, 10, 10, 3) 1 1 [0.974]
+Total_time - 103.433 - - - - -
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.412 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.746 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/9ccca8fd489a1486ac71b55a55c320c5/micro_autotune.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_autotune.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_ethosu.html b/docs/how_to/work_with_microtvm/micro_ethosu.html
index 41899d7495..8675058b76 100644
--- a/docs/how_to/work_with_microtvm/micro_ethosu.html
+++ b/docs/how_to/work_with_microtvm/micro_ethosu.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/work_with_microtvm/micro_mlperftiny.html b/docs/how_to/work_with_microtvm/micro_mlperftiny.html
index 54a84c8932..6328e83da7 100644
--- a/docs/how_to/work_with_microtvm/micro_mlperftiny.html
+++ b/docs/how_to/work_with_microtvm/micro_mlperftiny.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index c03414af35..fc9b7bce70 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -454,8 +459,7 @@ download a cat image and preprocess it to use as the model input.</p>
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
0%| | 0.00/3.42M [00:00<?, ?B/s]
- 61%|###### | 2.09M/3.42M [00:00<00:00, 18.5MB/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 28.0MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 52.2MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -581,7 +585,7 @@ via the host <cite>main.cc`</cite> or if a Zephyr emulated board is selected as
Torch top-1 id: 282, class name: tiger cat
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 18.622 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.297 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/12b9ecc04c41abaa12022061771821d1/micro_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_tflite.html b/docs/how_to/work_with_microtvm/micro_tflite.html
index ca5500e17d..6d0f1809c7 100644
--- a/docs/how_to/work_with_microtvm/micro_tflite.html
+++ b/docs/how_to/work_with_microtvm/micro_tflite.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 25f46c5213..ed60a32923 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -523,7 +528,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpk2282udu/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpqr1cnsj8/images/random'
</pre></div>
</div>
</div>
@@ -583,8 +588,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpk2282udu/images/target contains 8144 images
-/tmp/tmpk2282udu/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpqr1cnsj8/images/target contains 8144 images
+/tmp/tmpqr1cnsj8/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -696,13 +701,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 47s - loss: 0.2177 - accuracy: 0.9228 - val_loss: 0.1116 - val_accuracy: 0.9619 - 47s/epoch - 144ms/step
+328/328 - 47s - loss: 0.2775 - accuracy: 0.9126 - val_loss: 0.1314 - val_accuracy: 0.9513 - 47s/epoch - 145ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.1026 - accuracy: 0.9638 - val_loss: 0.1258 - val_accuracy: 0.9554 - 43s/epoch - 131ms/step
+328/328 - 43s - loss: 0.1074 - accuracy: 0.9584 - val_loss: 0.1195 - val_accuracy: 0.9622 - 43s/epoch - 132ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0759 - accuracy: 0.9719 - val_loss: 0.0953 - val_accuracy: 0.9683 - 43s/epoch - 131ms/step
+328/328 - 43s - loss: 0.0642 - accuracy: 0.9768 - val_loss: 0.1480 - val_accuracy: 0.9520 - 43s/epoch - 132ms/step
-<keras.callbacks.History object at 0x7fb43c50cdd0>
+<keras.callbacks.History object at 0x7f01b5763990>
</pre></div>
</div>
</div>
@@ -966,7 +971,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVMβs autotuning capabilities</a> to dramatically improve the modelβs performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 19.081 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 32.137 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-train-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/b52cec46baf4f78d6bcd94cbe269c8a6/micro_train.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_train.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_tvmc.html b/docs/how_to/work_with_microtvm/micro_tvmc.html
index 33c273e1dc..08aff07b92 100644
--- a/docs/how_to/work_with_microtvm/micro_tvmc.html
+++ b/docs/how_to/work_with_microtvm/micro_tvmc.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
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 dd4167d91f..958aa36f50 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -199,6 +199,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -340,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">ΒΆ</a></h1>
-<p><strong>08:17.037</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>07:30.675</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,23 +354,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">5. Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>05:19.081</p></td>
+<td><p>04:32.137</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">6. Model Tuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>01:21.412</p></td>
+<td><p>01:21.746</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">4. microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:18.622</p></td>
+<td><p>01:19.297</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">3. microTVM Ahead-of-Time (AOT) Compilation</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:10.176</p></td>
+<td><p>00:10.141</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">2. microTVM TFLite Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:07.747</p></td>
+<td><p>00:07.354</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">7. Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/build_gcn.html b/docs/how_to/work_with_relay/build_gcn.html
index 997dac5b0a..de2b6112c8 100644
--- a/docs/how_to/work_with_relay/build_gcn.html
+++ b/docs/how_to/work_with_relay/build_gcn.html
@@ -202,6 +202,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/work_with_relay/index.html b/docs/how_to/work_with_relay/index.html
index e3cd0fc345..e6b3c9a89c 100644
--- a/docs/how_to/work_with_relay/index.html
+++ b/docs/how_to/work_with_relay/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
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 227c1c6809..d6abfb7b57 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -199,6 +199,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -340,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">ΒΆ</a></h1>
-<p><strong>00:46.432</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:46.610</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +354,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:33.458</p></td>
+<td><p>00:34.055</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:11.251</p></td>
+<td><p>00:10.863</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></td>
-<td><p>00:01.717</p></td>
+<td><p>00:01.686</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/using_external_lib.html b/docs/how_to/work_with_relay/using_external_lib.html
index 1ea75bed72..fcb9d50c88 100644
--- a/docs/how_to/work_with_relay/using_external_lib.html
+++ b/docs/how_to/work_with_relay/using_external_lib.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/work_with_relay/using_pipeline_executor.html b/docs/how_to/work_with_relay/using_pipeline_executor.html
index 7b012c52b7..e46a80157f 100644
--- a/docs/how_to/work_with_relay/using_pipeline_executor.html
+++ b/docs/how_to/work_with_relay/using_pipeline_executor.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/work_with_relay/using_relay_viz.html b/docs/how_to/work_with_relay/using_relay_viz.html
index 76fe88085e..5f3bc92a51 100644
--- a/docs/how_to/work_with_relay/using_relay_viz.html
+++ b/docs/how_to/work_with_relay/using_relay_viz.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/work_with_schedules/extern_op.html b/docs/how_to/work_with_schedules/extern_op.html
index d66043907a..f80edd37ab 100644
--- a/docs/how_to/work_with_schedules/extern_op.html
+++ b/docs/how_to/work_with_schedules/extern_op.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/work_with_schedules/index.html b/docs/how_to/work_with_schedules/index.html
index b36a60c923..4ce0f2f2ef 100644
--- a/docs/how_to/work_with_schedules/index.html
+++ b/docs/how_to/work_with_schedules/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 65a946c447..21085c786d 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -535,7 +540,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fb2ed0f99e0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f0052826440>
</pre></div>
</div>
<p>Register the rule to TVM with override option to override existing rule.
diff --git a/docs/how_to/work_with_schedules/reduction.html b/docs/how_to/work_with_schedules/reduction.html
index d6ed85be26..2b395c83c3 100644
--- a/docs/how_to/work_with_schedules/reduction.html
+++ b/docs/how_to/work_with_schedules/reduction.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/work_with_schedules/scan.html b/docs/how_to/work_with_schedules/scan.html
index 1dd82443e8..75c41ddf16 100644
--- a/docs/how_to/work_with_schedules/scan.html
+++ b/docs/how_to/work_with_schedules/scan.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/work_with_schedules/schedule_primitives.html b/docs/how_to/work_with_schedules/schedule_primitives.html
index 5740feb0db..d1d4736ee8 100644
--- a/docs/how_to/work_with_schedules/schedule_primitives.html
+++ b/docs/how_to/work_with_schedules/schedule_primitives.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
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 9ccb057d6e..e8c5cd6450 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -199,6 +199,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -340,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">ΒΆ</a></h1>
-<p><strong>00:08.481</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:07.815</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,31 +354,31 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:05.710</p></td>
+<td><p>00:05.254</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:01.423</p></td>
+<td><p>00:01.179</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.570</p></td>
+<td><p>00:00.582</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></td>
-<td><p>00:00.553</p></td>
+<td><p>00:00.569</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.115</p></td>
+<td><p>00:00.118</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.051</p></td>
+<td><p>00:00.054</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.033</p></td>
+<td><p>00:00.032</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tedd.html b/docs/how_to/work_with_schedules/tedd.html
index 3b47394aa4..fc159069ce 100644
--- a/docs/how_to/work_with_schedules/tedd.html
+++ b/docs/how_to/work_with_schedules/tedd.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index c67188d328..4ef1fb4073 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/how_to/work_with_schedules/tuple_inputs.html b/docs/how_to/work_with_schedules/tuple_inputs.html
index c95467fae2..25ac201e2c 100644
--- a/docs/how_to/work_with_schedules/tuple_inputs.html
+++ b/docs/how_to/work_with_schedules/tuple_inputs.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/index.html b/docs/index.html
index 4ca7087689..37d17c4905 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -200,6 +200,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/install/docker.html b/docs/install/docker.html
index ba259aa3dd..f9eda7ccab 100644
--- a/docs/install/docker.html
+++ b/docs/install/docker.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/install/from_source.html b/docs/install/from_source.html
index 4104c3eb35..dea07a0792 100644
--- a/docs/install/from_source.html
+++ b/docs/install/from_source.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/install/index.html b/docs/install/index.html
index ebbeed606b..fd3e7ef0ca 100644
--- a/docs/install/index.html
+++ b/docs/install/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 23d2181e9d..de9a595da6 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/py-modindex.html b/docs/py-modindex.html
index 6032f42634..458b66f3a0 100644
--- a/docs/py-modindex.html
+++ b/docs/py-modindex.html
@@ -202,6 +202,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/links.html b/docs/reference/api/links.html
index ee130dcc4a..2a6e971a0e 100644
--- a/docs/reference/api/links.html
+++ b/docs/reference/api/links.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index f077af0790..37c841087b 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -1616,7 +1621,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1900,7 +1905,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/python/autotvm.html b/docs/reference/api/python/autotvm.html
index a2e712bad3..f7c594df6b 100644
--- a/docs/reference/api/python/autotvm.html
+++ b/docs/reference/api/python/autotvm.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/contrib.html b/docs/reference/api/python/contrib.html
index 6722e4de48..4ad2337f71 100644
--- a/docs/reference/api/python/contrib.html
+++ b/docs/reference/api/python/contrib.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/driver.html b/docs/reference/api/python/driver.html
index 3bf9d78717..098bf933c0 100644
--- a/docs/reference/api/python/driver.html
+++ b/docs/reference/api/python/driver.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/error.html b/docs/reference/api/python/error.html
index bf15376836..7744dbd49f 100644
--- a/docs/reference/api/python/error.html
+++ b/docs/reference/api/python/error.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/graph_executor.html b/docs/reference/api/python/graph_executor.html
index a389b9f5d2..c610f720a9 100644
--- a/docs/reference/api/python/graph_executor.html
+++ b/docs/reference/api/python/graph_executor.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/index.html b/docs/reference/api/python/index.html
index 3d313c3479..d2cf535f2b 100644
--- a/docs/reference/api/python/index.html
+++ b/docs/reference/api/python/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/ir.html b/docs/reference/api/python/ir.html
index 296e862a91..d4907323ed 100644
--- a/docs/reference/api/python/ir.html
+++ b/docs/reference/api/python/ir.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/micro.html b/docs/reference/api/python/micro.html
index 10542dce5c..9cf3ae881d 100644
--- a/docs/reference/api/python/micro.html
+++ b/docs/reference/api/python/micro.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/ndarray.html b/docs/reference/api/python/ndarray.html
index 270fe20564..a6805d5745 100644
--- a/docs/reference/api/python/ndarray.html
+++ b/docs/reference/api/python/ndarray.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/relay/analysis.html b/docs/reference/api/python/relay/analysis.html
index 7ba6dcb3ad..e542535965 100644
--- a/docs/reference/api/python/relay/analysis.html
+++ b/docs/reference/api/python/relay/analysis.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/relay/backend.html b/docs/reference/api/python/relay/backend.html
index 6a7a99e8ec..489c37c3cc 100644
--- a/docs/reference/api/python/relay/backend.html
+++ b/docs/reference/api/python/relay/backend.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/relay/dataflow_pattern.html b/docs/reference/api/python/relay/dataflow_pattern.html
index e202a88cbc..f8836a0fd7 100644
--- a/docs/reference/api/python/relay/dataflow_pattern.html
+++ b/docs/reference/api/python/relay/dataflow_pattern.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/relay/frontend.html b/docs/reference/api/python/relay/frontend.html
index aa24b4ec46..3117dd7a36 100644
--- a/docs/reference/api/python/relay/frontend.html
+++ b/docs/reference/api/python/relay/frontend.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/relay/image.html b/docs/reference/api/python/relay/image.html
index 34658a19bf..844867c993 100644
--- a/docs/reference/api/python/relay/image.html
+++ b/docs/reference/api/python/relay/image.html
@@ -202,6 +202,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/relay/index.html b/docs/reference/api/python/relay/index.html
index 8529b97aba..912cb9fcb2 100644
--- a/docs/reference/api/python/relay/index.html
+++ b/docs/reference/api/python/relay/index.html
@@ -202,6 +202,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/relay/nn.html b/docs/reference/api/python/relay/nn.html
index abcec7f17a..5cc46db5c7 100644
--- a/docs/reference/api/python/relay/nn.html
+++ b/docs/reference/api/python/relay/nn.html
@@ -202,6 +202,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/relay/testing.html b/docs/reference/api/python/relay/testing.html
index 5ca7f8b6e6..6d5ee55ed5 100644
--- a/docs/reference/api/python/relay/testing.html
+++ b/docs/reference/api/python/relay/testing.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/relay/transform.html b/docs/reference/api/python/relay/transform.html
index bb30946528..db694d35b0 100644
--- a/docs/reference/api/python/relay/transform.html
+++ b/docs/reference/api/python/relay/transform.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/relay/vision.html b/docs/reference/api/python/relay/vision.html
index 82108e6d75..e2a82f9c1d 100644
--- a/docs/reference/api/python/relay/vision.html
+++ b/docs/reference/api/python/relay/vision.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/rpc.html b/docs/reference/api/python/rpc.html
index b296a217bd..9aa1e2326f 100644
--- a/docs/reference/api/python/rpc.html
+++ b/docs/reference/api/python/rpc.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/runtime.html b/docs/reference/api/python/runtime.html
index 8cf73275d6..9c2c7b5412 100644
--- a/docs/reference/api/python/runtime.html
+++ b/docs/reference/api/python/runtime.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/target.html b/docs/reference/api/python/target.html
index cdde5daee7..ba5a13adac 100644
--- a/docs/reference/api/python/target.html
+++ b/docs/reference/api/python/target.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/te.html b/docs/reference/api/python/te.html
index 4e1be31060..fa8a532df4 100644
--- a/docs/reference/api/python/te.html
+++ b/docs/reference/api/python/te.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/tir.html b/docs/reference/api/python/tir.html
index c85e92862f..1d920a7bcb 100644
--- a/docs/reference/api/python/tir.html
+++ b/docs/reference/api/python/tir.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/topi.html b/docs/reference/api/python/topi.html
index 8656d53b1e..34b164cb28 100644
--- a/docs/reference/api/python/topi.html
+++ b/docs/reference/api/python/topi.html
@@ -202,6 +202,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/python/vta/index.html b/docs/reference/api/python/vta/index.html
index 646fde13e5..a30938387f 100644
--- a/docs/reference/api/python/vta/index.html
+++ b/docs/reference/api/python/vta/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 6188599386..b1730f672c 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/a42e98b19/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/rpc_server.ts#L45">rpc_server.ts:45</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/a42e98b19/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/rpc_server.ts#L45">rpc_server.ts:45</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/a42e98b19/web/src/rpc_server.ts#L44">rpc_server.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/rpc_server.ts#L44">rpc_server.ts:44</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/a42e98b19/web/src/rpc_server.ts#L65">rpc_server.ts:65</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/rpc_server.ts#L65">rpc_server.ts:65</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/a42e98b19/web/src/rpc_server.ts#L51">rpc_server.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/rpc_server.ts#L51">rpc_server.ts:51</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/a42e98b19/web/src/rpc_server.ts#L59">rpc_server.ts:59</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/rpc_server.ts#L59">rpc_server.ts:59</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 55ce5ebe87..0cf74c0d86 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/a42e98b19/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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 b34a6d8f37..2fa01e6435 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/a42e98b19/web/src/runtime.ts#L359">runtime.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L359">runtime.ts:359</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/a42e98b19/web/src/runtime.ts#L357">runtime.ts:357</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L357">runtime.ts:357</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/a42e98b19/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L355">runtime.ts:355</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/a42e98b19/web/src/runtime.ts#L359">runtime.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L359">runtime.ts:359</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/a42e98b19/web/src/runtime.ts#L376">runtime.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L376">runtime.ts:376</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/a42e98b19/web/src/runtime.ts#L367">runtime.ts:367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L367">runtime.ts:367</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 ca9fb58876..ffeed240e3 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/a42e98b19/web/src/runtime.ts#L299">runtime.ts:299</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L299">runtime.ts:299</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/a42e98b19/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L297">runtime.ts:297</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/a42e98b19/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L295">runtime.ts:295</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/a42e98b19/web/src/runtime.ts#L320">runtime.ts:320</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L320">runtime.ts:320</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/a42e98b19/web/src/runtime.ts#L327">runtime.ts:327</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L327">runtime.ts:327</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 45fad023aa..2af68b6673 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/a42e98b19/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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 fe5eb7f179..ea185d16a9 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/a42e98b19/web/src/runtime.ts#L50">runtime.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L50">runtime.ts:50</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/a42e98b19/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L47">runtime.ts:47</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/a42e98b19/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L46">runtime.ts:46</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/a42e98b19/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L45">runtime.ts:45</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/a42e98b19/web/src/runtime.ts#L48">runtime.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L48">runtime.ts:48</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/a42e98b19/web/src/runtime.ts#L77">runtime.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L77">runtime.ts:77</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/a42e98b19/web/src/runtime.ts#L67">runtime.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L67">runtime.ts:67</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/a42e98b19/web/src/runtime.ts#L85">runtime.ts:85</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L85">runtime.ts:85</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/a42e98b19/web/src/runtime.ts#L96">runtime.ts:96</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L96">runtime.ts:96</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/a42e98b19/web/src/runtime.ts#L73">runtime.ts:73</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L73">runtime.ts:73</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/instance.html b/docs/reference/api/typedoc/classes/instance.html
index 4c653bbde6..a217fc3848 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -161,7 +161,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L844">runtime.ts:844</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L844">runtime.ts:844</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<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/a42e98b19/web/src/runtime.ts#L834">runtime.ts:834</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L834">runtime.ts:834</a></li>
</ul>
</aside>
</section>
@@ -234,7 +234,7 @@
<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/a42e98b19/web/src/runtime.ts#L833">runtime.ts:833</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L833">runtime.ts:833</a></li>
</ul>
</aside>
</section>
@@ -251,7 +251,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L973">runtime.ts:973</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L973">runtime.ts:973</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -296,7 +296,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -318,7 +318,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L901">runtime.ts:901</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L901">runtime.ts:901</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -381,7 +381,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L1215">runtime.ts:1215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L1215">runtime.ts:1215</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -412,7 +412,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L1000">runtime.ts:1000</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L1000">runtime.ts:1000</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -453,7 +453,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L1207">runtime.ts:1207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L1207">runtime.ts:1207</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -491,7 +491,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L922">runtime.ts:922</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L922">runtime.ts:922</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -508,7 +508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L1235">runtime.ts:1235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L1235">runtime.ts:1235</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -552,7 +552,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L943">runtime.ts:943</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L943">runtime.ts:943</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -577,7 +577,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L1088">runtime.ts:1088</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L1088">runtime.ts:1088</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -609,7 +609,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L1363">runtime.ts:1363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L1363">runtime.ts:1363</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -640,7 +640,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L1123">runtime.ts:1123</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L1123">runtime.ts:1123</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -672,7 +672,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L1016">runtime.ts:1016</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L1016">runtime.ts:1016</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -695,7 +695,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L1281">runtime.ts:1281</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L1281">runtime.ts:1281</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -729,7 +729,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L986">runtime.ts:986</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L986">runtime.ts:986</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -769,7 +769,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L1341">runtime.ts:1341</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L1341">runtime.ts:1341</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -817,7 +817,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L1055">runtime.ts:1055</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L1055">runtime.ts:1055</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -857,7 +857,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L1320">runtime.ts:1320</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L1320">runtime.ts:1320</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -900,7 +900,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L1197">runtime.ts:1197</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L1197">runtime.ts:1197</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -938,7 +938,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L1491">runtime.ts:1491</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L1491">runtime.ts:1491</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L1009">runtime.ts:1009</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L1009">runtime.ts:1009</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1014,7 +1014,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L1151">runtime.ts:1151</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L1151">runtime.ts:1151</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1046,7 +1046,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1078,7 +1078,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L1292">runtime.ts:1292</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L1292">runtime.ts:1292</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1110,7 +1110,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L1223">runtime.ts:1223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L1223">runtime.ts:1223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1141,7 +1141,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L957">runtime.ts:957</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L957">runtime.ts:957</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 de941ae714..9dba1b18c0 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/a42e98b19/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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 0b9c3f2a7b..1a171838b9 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.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/a42e98b19/web/src/runtime.ts#L614">runtime.ts:614</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L614">runtime.ts:614</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -169,7 +169,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L626">runtime.ts:626</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L626">runtime.ts:626</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -186,7 +186,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L653">runtime.ts:653</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L653">runtime.ts:653</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L641">runtime.ts:641</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L641">runtime.ts:641</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/a42e98b19/web/src/runtime.ts#L687">runtime.ts:687</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L687">runtime.ts:687</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 22da90f168..7dcf303e54 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/a42e98b19/web/src/runtime.ts#L401">runtime.ts:401</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L401">runtime.ts:401</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/a42e98b19/web/src/runtime.ts#L394">runtime.ts:394</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L394">runtime.ts:394</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/a42e98b19/web/src/runtime.ts#L390">runtime.ts:390</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L390">runtime.ts:390</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<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/a42e98b19/web/src/runtime.ts#L388">runtime.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L388">runtime.ts:388</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<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/a42e98b19/web/src/runtime.ts#L392">runtime.ts:392</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L392">runtime.ts:392</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -225,7 +225,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L480">runtime.ts:480</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L480">runtime.ts:480</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -258,7 +258,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L524">runtime.ts:524</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L524">runtime.ts:524</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -290,7 +290,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L465">runtime.ts:465</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L465">runtime.ts:465</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -307,7 +307,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L458">runtime.ts:458</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L458">runtime.ts:458</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -339,7 +339,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L584">runtime.ts:584</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L584">runtime.ts:584</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -363,7 +363,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L553">runtime.ts:553</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L553">runtime.ts:553</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 b67ccc37bf..4e647d02ae 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -117,7 +117,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L255">runtime.ts:255</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L255">runtime.ts:255</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -163,7 +163,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L264">runtime.ts:264</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L264">runtime.ts:264</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index 6cab17ab60..e4d771af6b 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/a42e98b19/web/src/rpc_server.ts#L95">rpc_server.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/rpc_server.ts#L95">rpc_server.ts:95</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/a42e98b19/web/src/rpc_server.ts#L84">rpc_server.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/rpc_server.ts#L84">rpc_server.ts:84</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/a42e98b19/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/rpc_server.ts#L80">rpc_server.ts:80</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/a42e98b19/web/src/rpc_server.ts#L83">rpc_server.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/rpc_server.ts#L83">rpc_server.ts:83</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/a42e98b19/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/rpc_server.ts#L81">rpc_server.ts:81</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/a42e98b19/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/rpc_server.ts#L82">rpc_server.ts:82</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/a42e98b19/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/runtimecontext.html b/docs/reference/api/typedoc/classes/runtimecontext.html
index a823825f68..3385883479 100644
--- a/docs/reference/api/typedoc/classes/runtimecontext.html
+++ b/docs/reference/api/typedoc/classes/runtimecontext.html
@@ -132,7 +132,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L148">runtime.ts:148</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L148">runtime.ts:148</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -172,7 +172,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Get<wbr>Item<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
</section>
@@ -182,7 +182,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Get<wbr>Size<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L144">runtime.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L144">runtime.ts:144</a></li>
</ul>
</aside>
</section>
@@ -192,7 +192,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Make<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
</section>
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Sys<wbr>Lib<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L146">runtime.ts:146</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L146">runtime.ts:146</a></li>
</ul>
</aside>
</section>
@@ -219,7 +219,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -263,7 +263,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L163">runtime.ts:163</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L163">runtime.ts:163</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -280,7 +280,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L208">runtime.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L208">runtime.ts:208</a></li>
</ul>
</aside>
<h4 class="tsd-type-parameters-title">Type parameters</h4>
@@ -309,7 +309,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -326,7 +326,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L167">runtime.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L167">runtime.ts:167</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -343,7 +343,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<h4 class="tsd-type-parameters-title">Type parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index 643d7b7d8f..3cb1f37650 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/a42e98b19/web/src/runtime.ts#L235">runtime.ts:235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L235">runtime.ts:235</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/a42e98b19/web/src/runtime.ts#L235">runtime.ts:235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L235">runtime.ts:235</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/a42e98b19/web/src/runtime.ts#L233">runtime.ts:233</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L233">runtime.ts:233</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/tvmarray.html b/docs/reference/api/typedoc/classes/tvmarray.html
index c32e35b4d4..a86641fd29 100644
--- a/docs/reference/api/typedoc/classes/tvmarray.html
+++ b/docs/reference/api/typedoc/classes/tvmarray.html
@@ -133,7 +133,7 @@
<aside class="tsd-sources">
<p>Overrides <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#constructor">constructor</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L784">runtime.ts:784</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L784">runtime.ts:784</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -162,7 +162,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#ctx">ctx</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#dispose">dispose</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L715">runtime.ts:715</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L715">runtime.ts:715</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -197,7 +197,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L804">runtime.ts:804</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L804">runtime.ts:804</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -230,7 +230,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#gethandle">getHandle</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L730">runtime.ts:730</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L730">runtime.ts:730</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/a42e98b19/web/src/runtime.ts#L796">runtime.ts:796</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L796">runtime.ts:796</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -283,7 +283,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#typeindex">typeIndex</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L738">runtime.ts:738</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L738">runtime.ts:738</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -306,7 +306,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#typekey">typeKey</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L758">runtime.ts:758</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L758">runtime.ts:758</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/tvmobject.html b/docs/reference/api/typedoc/classes/tvmobject.html
index 2b6a409fac..eb0acb077d 100644
--- a/docs/reference/api/typedoc/classes/tvmobject.html
+++ b/docs/reference/api/typedoc/classes/tvmobject.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/a42e98b19/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">ctx<span class="tsd-signature-symbol">:</span> <a href="runtimecontext.html" class="tsd-signature-type">RuntimeContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
</section>
@@ -175,7 +175,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L715">runtime.ts:715</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L715">runtime.ts:715</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -192,7 +192,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L730">runtime.ts:730</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L730">runtime.ts:730</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/a42e98b19/web/src/runtime.ts#L738">runtime.ts:738</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L738">runtime.ts:738</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -246,7 +246,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L758">runtime.ts:758</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L758">runtime.ts:758</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 077f380f05..cfdaa2a8ac 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/a42e98b19/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/webgpu.ts#L172">webgpu.ts:172</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/a42e98b19/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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 61ab993739..e23141dc46 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/a42e98b19/web/src/ctypes.ts#L242">ctypes.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L242">ctypes.ts:242</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/a42e98b19/web/src/ctypes.ts#L238">ctypes.ts:238</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L238">ctypes.ts:238</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/a42e98b19/web/src/ctypes.ts#L236">ctypes.ts:236</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L236">ctypes.ts:236</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/a42e98b19/web/src/ctypes.ts#L240">ctypes.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L240">ctypes.ts:240</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/a42e98b19/web/src/ctypes.ts#L248">ctypes.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L248">ctypes.ts:248</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/a42e98b19/web/src/ctypes.ts#L243">ctypes.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L243">ctypes.ts:243</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/a42e98b19/web/src/ctypes.ts#L241">ctypes.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L241">ctypes.ts:241</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/a42e98b19/web/src/ctypes.ts#L245">ctypes.ts:245</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L245">ctypes.ts:245</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/a42e98b19/web/src/ctypes.ts#L249">ctypes.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L249">ctypes.ts:249</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/a42e98b19/web/src/ctypes.ts#L244">ctypes.ts:244</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L244">ctypes.ts:244</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/a42e98b19/web/src/ctypes.ts#L250">ctypes.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L250">ctypes.ts:250</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/a42e98b19/web/src/ctypes.ts#L239">ctypes.ts:239</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L239">ctypes.ts:239</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/a42e98b19/web/src/ctypes.ts#L246">ctypes.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L246">ctypes.ts:246</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/a42e98b19/web/src/ctypes.ts#L247">ctypes.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L247">ctypes.ts:247</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/a42e98b19/web/src/ctypes.ts#L237">ctypes.ts:237</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L237">ctypes.ts:237</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index 5577a40de1..e59dc61d5d 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/a42e98b19/web/src/runtime.ts#L812">runtime.ts:812</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L812">runtime.ts:812</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/a42e98b19/web/src/runtime.ts#L811">runtime.ts:811</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L811">runtime.ts:811</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 03afa3e8fb..78dfe00d10 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/a42e98b19/web/src/runtime.ts#L339">runtime.ts:339</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L339">runtime.ts:339</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/a42e98b19/web/src/runtime.ts#L337">runtime.ts:337</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L337">runtime.ts:337</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/a42e98b19/web/src/runtime.ts#L340">runtime.ts:340</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L340">runtime.ts:340</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/a42e98b19/web/src/runtime.ts#L338">runtime.ts:338</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L338">runtime.ts:338</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 0b06ac080f..29ac6993b3 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/a42e98b19/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/rpc_server.ts#L29">rpc_server.ts:29</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/a42e98b19/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/rpc_server.ts#L30">rpc_server.ts:30</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/a42e98b19/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/rpc_server.ts#L31">rpc_server.ts:31</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/a42e98b19/web/src/rpc_server.ts#L34">rpc_server.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/rpc_server.ts#L34">rpc_server.ts:34</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/a42e98b19/web/src/rpc_server.ts#L33">rpc_server.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/rpc_server.ts#L33">rpc_server.ts:33</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/a42e98b19/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index 765e4fa27d..9d164e23c4 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/a42e98b19/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L228">ctypes.ts:228</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/a42e98b19/web/src/ctypes.ts#L229">ctypes.ts:229</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L229">ctypes.ts:229</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/a42e98b19/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L225">ctypes.ts:225</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/a42e98b19/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L226">ctypes.ts:226</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/a42e98b19/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L223">ctypes.ts:223</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/a42e98b19/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L224">ctypes.ts:224</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/a42e98b19/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L227">ctypes.ts:227</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/a42e98b19/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L222">ctypes.ts:222</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/a42e98b19/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index d0266fe3b2..4ee44d55cd 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -182,7 +182,7 @@
<div class="tsd-signature tsd-kind-icon">FObject<wbr>Constructor<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>, lib<span class="tsd-signature-symbol">: </span><a href="classes/ffilibrary.html" class="tsd-signature-type">FFILibrary</a>, ctx<span class="tsd-signature-symbol">: </span><a href="classes/runtimecontext.html" class="t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L778">runtime.ts:778</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L778">runtime.ts:778</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<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/a42e98b19/web/src/ctypes.ts#L113">ctypes.ts:113</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L113">ctypes.ts:113</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -288,7 +288,7 @@
<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/a42e98b19/web/src/ctypes.ts#L129">ctypes.ts:129</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L129">ctypes.ts:129</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<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/a42e98b19/web/src/ctypes.ts#L145">ctypes.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L145">ctypes.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -376,7 +376,7 @@
<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/a42e98b19/web/src/ctypes.ts#L137">ctypes.ts:137</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L137">ctypes.ts:137</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -420,7 +420,7 @@
<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/a42e98b19/web/src/ctypes.ts#L122">ctypes.ts:122</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L122">ctypes.ts:122</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -456,7 +456,7 @@
<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/a42e98b19/web/src/ctypes.ts#L161">ctypes.ts:161</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L161">ctypes.ts:161</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -508,7 +508,7 @@
<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/a42e98b19/web/src/ctypes.ts#L78">ctypes.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L78">ctypes.ts:78</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -556,7 +556,7 @@
<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/a42e98b19/web/src/ctypes.ts#L84">ctypes.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L84">ctypes.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -595,7 +595,7 @@
<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/a42e98b19/web/src/ctypes.ts#L68">ctypes.ts:68</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L68">ctypes.ts:68</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -651,7 +651,7 @@
<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/a42e98b19/web/src/ctypes.ts#L58">ctypes.ts:58</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L58">ctypes.ts:58</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -687,7 +687,7 @@
<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/a42e98b19/web/src/ctypes.ts#L101">ctypes.ts:101</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L101">ctypes.ts:101</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -726,7 +726,7 @@
<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/a42e98b19/web/src/ctypes.ts#L89">ctypes.ts:89</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L89">ctypes.ts:89</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -765,7 +765,7 @@
<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/a42e98b19/web/src/ctypes.ts#L95">ctypes.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L95">ctypes.ts:95</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -808,7 +808,7 @@
<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/a42e98b19/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -838,7 +838,7 @@
<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/a42e98b19/web/src/ctypes.ts#L53">ctypes.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L53">ctypes.ts:53</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -874,7 +874,7 @@
<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/a42e98b19/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -922,7 +922,7 @@
<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/a42e98b19/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -962,7 +962,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>obj<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/a42e98b19/web/src/ctypes.ts#L169">ctypes.ts:169</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L169">ctypes.ts:169</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -998,7 +998,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Get<wbr>Type<wbr>Index<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>obj<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out_tindex<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"> => [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/ctypes.ts#L174">ctypes.ts:174</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L174">ctypes.ts:174</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1037,7 +1037,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Type<wbr>Index2<wbr>Key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>type_index<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, out_type_key<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><spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1076,7 +1076,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Type<wbr>Key2<wbr>Index<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>type_key<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out_tindex<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"> [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/ctypes.ts#L184">ctypes.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L184">ctypes.ts:184</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1115,7 +1115,7 @@
<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/a42e98b19/web/src/ctypes.ts#L151">ctypes.ts:151</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L151">ctypes.ts:151</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1157,7 +1157,7 @@
<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/a42e98b19/web/src/ctypes.ts#L189">ctypes.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L189">ctypes.ts:189</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1193,7 +1193,7 @@
<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/a42e98b19/web/src/ctypes.ts#L192">ctypes.ts:192</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L192">ctypes.ts:192</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1229,7 +1229,7 @@
<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/a42e98b19/web/src/ctypes.ts#L209">ctypes.ts:209</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L209">ctypes.ts:209</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1269,7 +1269,7 @@
<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/a42e98b19/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1321,7 +1321,7 @@
<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/a42e98b19/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1357,7 +1357,7 @@
<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/a42e98b19/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1372,7 +1372,7 @@
<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/a42e98b19/web/src/runtime.ts#L37">runtime.ts:37</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L37">runtime.ts:37</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1387,7 +1387,7 @@
<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/a42e98b19/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1402,7 +1402,7 @@
<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/a42e98b19/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1417,7 +1417,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Base<span class="tsd-signature-symbol">:</span> <a href="classes/tvmobject.html" class="tsd-signature-type">TVMObject</a><span class="tsd-signature-symbol"> | </span><a href="classes/ndarray.html" class="tsd-signature-type">NDArray</a><span class="tsd-signature-symbol"> | </span><a href="classes/module.html" class="tsd-signature-type">Module</a><span class="tsd-signature-symbol"> | </span><a href="index.html#packedfunc" class="t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L781">runtime.ts:781</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L781">runtime.ts:781</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1435,7 +1435,7 @@
<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/a42e98b19/web/src/rpc_server.ts#L38">rpc_server.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/rpc_server.ts#L38">rpc_server.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1457,7 +1457,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1489,7 +1489,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1518,7 +1518,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1555,7 +1555,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1586,7 +1586,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1608,7 +1608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1639,7 +1639,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1661,7 +1661,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/runtime.ts#L1749">runtime.ts:1749</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L1749">runtime.ts:1749</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1726,7 +1726,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a42e98b19/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1748,7 +1748,7 @@
<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/a42e98b19/web/src/runtime.ts#L343">runtime.ts:343</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L343">runtime.ts:343</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1757,7 +1757,7 @@
<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/a42e98b19/web/src/runtime.ts#L344">runtime.ts:344</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L344">runtime.ts:344</a></li>
</ul>
</aside>
</section>
@@ -1767,7 +1767,7 @@
<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/a42e98b19/web/src/runtime.ts#L345">runtime.ts:345</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L345">runtime.ts:345</a></li>
</ul>
</aside>
</section>
@@ -1777,7 +1777,7 @@
<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/a42e98b19/web/src/runtime.ts#L346">runtime.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L346">runtime.ts:346</a></li>
</ul>
</aside>
</section>
@@ -1787,7 +1787,7 @@
<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/a42e98b19/web/src/runtime.ts#L347">runtime.ts:347</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L347">runtime.ts:347</a></li>
</ul>
</aside>
</section>
@@ -1798,7 +1798,7 @@
<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/a42e98b19/web/src/runtime.ts#L272">runtime.ts:272</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L272">runtime.ts:272</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1807,7 +1807,7 @@
<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/a42e98b19/web/src/runtime.ts#L273">runtime.ts:273</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L273">runtime.ts:273</a></li>
</ul>
</aside>
</section>
@@ -1817,7 +1817,7 @@
<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/a42e98b19/web/src/runtime.ts#L277">runtime.ts:277</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L277">runtime.ts:277</a></li>
</ul>
</aside>
</section>
@@ -1827,7 +1827,7 @@
<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/a42e98b19/web/src/runtime.ts#L274">runtime.ts:274</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L274">runtime.ts:274</a></li>
</ul>
</aside>
</section>
@@ -1837,7 +1837,7 @@
<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/a42e98b19/web/src/runtime.ts#L275">runtime.ts:275</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L275">runtime.ts:275</a></li>
</ul>
</aside>
</section>
@@ -1847,7 +1847,7 @@
<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/a42e98b19/web/src/runtime.ts#L276">runtime.ts:276</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L276">runtime.ts:276</a></li>
</ul>
</aside>
</section>
@@ -1858,7 +1858,7 @@
<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/a42e98b19/web/src/runtime.ts#L280">runtime.ts:280</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L280">runtime.ts:280</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1867,7 +1867,7 @@
<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/a42e98b19/web/src/runtime.ts#L283">runtime.ts:283</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L283">runtime.ts:283</a></li>
</ul>
</aside>
</section>
@@ -1877,7 +1877,7 @@
<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/a42e98b19/web/src/runtime.ts#L281">runtime.ts:281</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L281">runtime.ts:281</a></li>
</ul>
</aside>
</section>
@@ -1887,7 +1887,7 @@
<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/a42e98b19/web/src/runtime.ts#L282">runtime.ts:282</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L282">runtime.ts:282</a></li>
</ul>
</aside>
</section>
@@ -1897,7 +1897,7 @@
<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/a42e98b19/web/src/runtime.ts#L286">runtime.ts:286</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L286">runtime.ts:286</a></li>
</ul>
</aside>
</section>
@@ -1907,7 +1907,7 @@
<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/a42e98b19/web/src/runtime.ts#L284">runtime.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L284">runtime.ts:284</a></li>
</ul>
</aside>
</section>
@@ -1917,7 +1917,7 @@
<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/a42e98b19/web/src/runtime.ts#L285">runtime.ts:285</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L285">runtime.ts:285</a></li>
</ul>
</aside>
</section>
@@ -1927,7 +1927,7 @@
<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/a42e98b19/web/src/runtime.ts#L287">runtime.ts:287</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/runtime.ts#L287">runtime.ts:287</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index 3103cf03fc..a06f44659a 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -115,7 +115,7 @@
<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/a42e98b19/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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 8601871fc5..db264d34af 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/a42e98b19/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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 227fe54d0f..4a30c43402 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/a42e98b19/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/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/a42e98b19/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bc92a3ff6/web/src/types.ts#L39">types.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/langref/hybrid_script.html b/docs/reference/langref/hybrid_script.html
index 730a1d3190..1b7a82226d 100644
--- a/docs/reference/langref/hybrid_script.html
+++ b/docs/reference/langref/hybrid_script.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/langref/index.html b/docs/reference/langref/index.html
index 43fa454949..40a5e19bcc 100644
--- a/docs/reference/langref/index.html
+++ b/docs/reference/langref/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/langref/relay_adt.html b/docs/reference/langref/relay_adt.html
index a88d72bef2..239d2eadfd 100644
--- a/docs/reference/langref/relay_adt.html
+++ b/docs/reference/langref/relay_adt.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/langref/relay_expr.html b/docs/reference/langref/relay_expr.html
index cfb339616f..28fb8d5dab 100644
--- a/docs/reference/langref/relay_expr.html
+++ b/docs/reference/langref/relay_expr.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/langref/relay_op.html b/docs/reference/langref/relay_op.html
index dcb955325f..3f083755b6 100644
--- a/docs/reference/langref/relay_op.html
+++ b/docs/reference/langref/relay_op.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/langref/relay_pattern.html b/docs/reference/langref/relay_pattern.html
index cf6e77f14f..e229846b21 100644
--- a/docs/reference/langref/relay_pattern.html
+++ b/docs/reference/langref/relay_pattern.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/langref/relay_type.html b/docs/reference/langref/relay_type.html
index 259a4480a4..ebc4897f96 100644
--- a/docs/reference/langref/relay_type.html
+++ b/docs/reference/langref/relay_type.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/reference/publications.html b/docs/reference/publications.html
index 9a49c6fa72..1c8c533d77 100644
--- a/docs/reference/publications.html
+++ b/docs/reference/publications.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/search.html b/docs/search.html
index 5e6504e7fc..d061602cb3 100644
--- a/docs/search.html
+++ b/docs/search.html
@@ -202,6 +202,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/searchindex.js b/docs/searchindex.js
index f8e7ecde8e..2597bf9c25 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/microtvm/index.html b/docs/topic/microtvm/index.html
index 3c7830cbde..0638b2ec1f 100644
--- a/docs/topic/microtvm/index.html
+++ b/docs/topic/microtvm/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/topic/vta/dev/config.html b/docs/topic/vta/dev/config.html
index 0f66a886da..8808d4a1a9 100644
--- a/docs/topic/vta/dev/config.html
+++ b/docs/topic/vta/dev/config.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/topic/vta/dev/hardware.html b/docs/topic/vta/dev/hardware.html
index 87276cfbb7..c65e54cc2c 100644
--- a/docs/topic/vta/dev/hardware.html
+++ b/docs/topic/vta/dev/hardware.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/topic/vta/dev/index.html b/docs/topic/vta/dev/index.html
index b3607a5f74..6cd0602415 100644
--- a/docs/topic/vta/dev/index.html
+++ b/docs/topic/vta/dev/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/topic/vta/index.html b/docs/topic/vta/index.html
index d50a40e804..e2426f3b32 100644
--- a/docs/topic/vta/index.html
+++ b/docs/topic/vta/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/topic/vta/install.html b/docs/topic/vta/install.html
index 687dbd340d..ea12d291c8 100644
--- a/docs/topic/vta/install.html
+++ b/docs/topic/vta/install.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/topic/vta/tutorials/autotvm/index.html b/docs/topic/vta/tutorials/autotvm/index.html
index d4d89c5a54..c649b2c873 100644
--- a/docs/topic/vta/tutorials/autotvm/index.html
+++ b/docs/topic/vta/tutorials/autotvm/index.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
index 85f3d4bea7..b359f11ce2 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -199,6 +199,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
@@ -340,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">ΒΆ</a></h1>
-<p><strong>00:30.775</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:31.361</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,11 +354,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:30.768</p></td>
+<td><p>00:31.355</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/autotvm/tune_alu_vta.html b/docs/topic/vta/tutorials/autotvm/tune_alu_vta.html
index f23d983d25..61cd31afc0 100644
--- a/docs/topic/vta/tutorials/autotvm/tune_alu_vta.html
+++ b/docs/topic/vta/tutorials/autotvm/tune_alu_vta.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
+
</ol>
</div>
diff --git a/docs/topic/vta/tutorials/autotvm/tune_relay_vta.html b/docs/topic/vta/tutorials/autotvm/tune_relay_vta.html
index 257b198aa9..5a8421f61c 100644
--- a/docs/topic/vta/tutorials/autotvm/tune_relay_vta.html
+++ b/docs/topic/vta/tutorials/autotvm/tune_relay_vta.html
@@ -201,6 +201,11 @@
<li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.10.0/">v0.10.0</a></div></li>
+
+
+
+ <li><div class="version"><a style="font-size: 0.8em; padding: 4px" href="v0.11.0/">v0.11.0</a></div></li>
... 1129 lines suppressed ...