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 2021/09/15 22:18:33 UTC
[tvm-site] branch asf-site updated: Docs build at Wed Sep 15
18:18:24 EDT 2021
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 f974754 Docs build at Wed Sep 15 18:18:24 EDT 2021
f974754 is described below
commit f97475446b216df12b6b3835049a93c1c2b17f38
Author: tqchen <ti...@gmail.com>
AuthorDate: Wed Sep 15 18:18:25 2021 -0400
Docs build at Wed Sep 15 18:18:24 EDT 2021
---
docs/_images/sphx_glr_from_onnx_001.png | Bin 164348 -> 164343 bytes
docs/_images/sphx_glr_from_onnx_thumb.png | Bin 65645 -> 65645 bytes
docs/_images/sphx_glr_micro_autotune_thumb.png | Bin 35467 -> 26786 bytes
.../auto_scheduler/sg_execution_times.rst.txt | 16 +--
.../auto_scheduler/tune_conv2d_layer_cuda.rst.txt | 8 +-
.../auto_scheduler/tune_network_arm.rst.txt | 44 +++---
.../auto_scheduler/tune_network_cuda.rst.txt | 50 +++----
.../auto_scheduler/tune_network_mali.rst.txt | 44 +++---
.../auto_scheduler/tune_network_x86.rst.txt | 60 ++++-----
.../auto_scheduler/tune_sparse_x86.rst.txt | 41 +++---
.../tutorials/autotvm/sg_execution_times.rst.txt | 12 +-
.../tutorials/autotvm/tune_conv2d_cuda.rst.txt | 42 +++---
.../tutorials/dev/low_level_custom_pass.rst.txt | 4 +-
.../tutorials/dev/sg_execution_times.rst.txt | 10 +-
.../tutorials/dev/use_pass_instrument.rst.txt | 16 +--
docs/_sources/tutorials/frontend/build_gcn.rst.txt | 7 +-
.../frontend/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../tutorials/frontend/deploy_prequantized.rst.txt | 20 ++-
.../frontend/deploy_prequantized_tflite.rst.txt | 4 +-
.../tutorials/frontend/deploy_quantized.rst.txt | 5 +
.../tutorials/frontend/deploy_ssd_gluoncv.rst.txt | 4 +-
.../tutorials/frontend/from_caffe2.rst.txt | 16 +++
.../tutorials/frontend/from_darknet.rst.txt | 5 +
.../_sources/tutorials/frontend/from_mxnet.rst.txt | 1 +
docs/_sources/tutorials/frontend/from_onnx.rst.txt | 2 +-
.../tutorials/frontend/from_pytorch.rst.txt | 9 ++
.../tutorials/frontend/from_tensorflow.rst.txt | 149 +--------------------
.../tutorials/frontend/sg_execution_times.rst.txt | 40 +++---
.../get_started/auto_scheduler_matmul_x86.rst.txt | 3 +-
.../get_started/autotvm_relay_x86.rst.txt | 75 +++++------
.../get_started/cross_compilation_and_rpc.rst.txt | 2 +-
.../get_started/sg_execution_times.rst.txt | 20 +--
.../get_started/tensor_expr_get_started.rst.txt | 61 ++++-----
docs/_sources/tutorials/language/reduction.rst.txt | 4 +-
.../tutorials/language/schedule_primitives.rst.txt | 6 +-
.../tutorials/language/sg_execution_times.rst.txt | 18 +--
docs/_sources/tutorials/language/tensorize.rst.txt | 4 +-
.../tutorials/language/tuple_inputs.rst.txt | 16 +--
.../tutorials/micro/micro_autotune.rst.txt | 18 +--
docs/_sources/tutorials/micro/micro_tflite.rst.txt | 10 +-
.../tutorials/micro/sg_execution_times.rst.txt | 4 +-
.../tutorials/optimize/opt_conv_cuda.rst.txt | 2 +-
.../tutorials/optimize/opt_conv_tensorcore.rst.txt | 6 +-
docs/_sources/tutorials/optimize/opt_gemm.rst.txt | 16 +--
.../tutorials/optimize/sg_execution_times.rst.txt | 8 +-
docs/_sources/tutorials/topi/intro_topi.rst.txt | 2 +-
.../tutorials/topi/sg_execution_times.rst.txt | 4 +-
.../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 +-
.../_sources/vta/tutorials/matrix_multiply.rst.txt | 4 +-
.../vta/tutorials/optimize/convolution_opt.rst.txt | 4 +-
.../tutorials/optimize/matrix_multiply_opt.rst.txt | 4 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../vta/tutorials/sg_execution_times.rst.txt | 6 +-
docs/_static/documentation_options.js | 2 +-
.../javadoc/org/apache/tvm/class-use/Function.html | 16 +--
.../javadoc/org/apache/tvm/class-use/Module.html | 8 +-
.../org/apache/tvm/class-use/NDArrayBase.html | 4 +-
docs/api/links.html | 4 +-
docs/api/python/auto_scheduler.html | 10 +-
docs/api/python/autotvm.html | 4 +-
docs/api/python/contrib.html | 4 +-
docs/api/python/driver.html | 4 +-
docs/api/python/error.html | 4 +-
docs/api/python/graph_executor.html | 4 +-
docs/api/python/index.html | 4 +-
docs/api/python/ir.html | 4 +-
docs/api/python/micro.html | 4 +-
docs/api/python/ndarray.html | 4 +-
docs/api/python/relay/analysis.html | 4 +-
docs/api/python/relay/backend.html | 4 +-
docs/api/python/relay/dataflow_pattern.html | 4 +-
docs/api/python/relay/frontend.html | 11 +-
docs/api/python/relay/image.html | 4 +-
docs/api/python/relay/index.html | 4 +-
docs/api/python/relay/nn.html | 4 +-
docs/api/python/relay/testing.html | 4 +-
docs/api/python/relay/transform.html | 4 +-
docs/api/python/relay/vision.html | 4 +-
docs/api/python/rpc.html | 4 +-
docs/api/python/runtime.html | 4 +-
docs/api/python/target.html | 4 +-
docs/api/python/te.html | 4 +-
docs/api/python/tir.html | 4 +-
docs/api/python/topi.html | 4 +-
docs/api/python/vta/index.html | 4 +-
docs/api/typedoc/classes/bytestreamreader.html | 12 +-
docs/api/typedoc/classes/cachedcallstack.html | 34 ++---
docs/api/typedoc/classes/dldatatype.html | 12 +-
docs/api/typedoc/classes/dldevice.html | 10 +-
docs/api/typedoc/classes/environment.html | 12 +-
docs/api/typedoc/classes/ffilibrary.html | 20 +--
docs/api/typedoc/classes/graphexecutor.html | 16 +--
docs/api/typedoc/classes/instance.html | 40 +++---
docs/api/typedoc/classes/memory.html | 34 ++---
docs/api/typedoc/classes/module.html | 10 +-
docs/api/typedoc/classes/ndarray.html | 22 +--
docs/api/typedoc/classes/packedfunccell.html | 6 +-
docs/api/typedoc/classes/rpcserver.html | 14 +-
docs/api/typedoc/classes/scalar.html | 6 +-
docs/api/typedoc/classes/webgpucontext.html | 12 +-
docs/api/typedoc/enums/argtypecode.html | 30 ++---
docs/api/typedoc/enums/aynccallbackcode.html | 4 +-
docs/api/typedoc/enums/dldatatypecode.html | 8 +-
docs/api/typedoc/enums/rpcserverstate.html | 12 +-
docs/api/typedoc/enums/sizeof.html | 18 +--
docs/api/typedoc/index.html | 112 ++++++++--------
docs/api/typedoc/interfaces/disposable.html | 2 +-
docs/api/typedoc/interfaces/functioninfo.html | 6 +-
docs/api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/contribute/code_guide.html | 4 +-
docs/contribute/code_review.html | 4 +-
docs/contribute/committer_guide.html | 4 +-
docs/contribute/community.html | 4 +-
docs/contribute/document.html | 4 +-
docs/contribute/error_handling.html | 4 +-
docs/contribute/git_howto.html | 4 +-
docs/contribute/index.html | 4 +-
docs/contribute/pull_request.html | 4 +-
docs/contribute/release_process.html | 4 +-
docs/deploy/android.html | 4 +-
docs/deploy/arm_compute_lib.html | 4 +-
docs/deploy/bnns.html | 4 +-
docs/deploy/cpp_deploy.html | 4 +-
docs/deploy/hls.html | 4 +-
docs/deploy/index.html | 4 +-
docs/deploy/integrate.html | 4 +-
docs/deploy/tensorrt.html | 4 +-
docs/deploy/vitis_ai.html | 4 +-
docs/dev/benchmark.html | 4 +-
docs/dev/codebase_walkthrough.html | 4 +-
docs/dev/convert_layout.html | 4 +-
docs/dev/debugger.html | 4 +-
docs/dev/device_target_interactions.html | 4 +-
docs/dev/frontend/tensorflow.html | 4 +-
docs/dev/how_to.html | 4 +-
docs/dev/hybrid_script.html | 4 +-
docs/dev/index.html | 4 +-
docs/dev/inferbound.html | 4 +-
docs/dev/introduction_to_module_serialization.html | 4 +-
docs/dev/microtvm_design.html | 4 +-
docs/dev/model_library_format.html | 4 +-
docs/dev/pass_infra.html | 4 +-
docs/dev/pytest_target_parametrization.html | 4 +-
docs/dev/relay_add_op.html | 4 +-
docs/dev/relay_add_pass.html | 4 +-
docs/dev/relay_bring_your_own_codegen.html | 4 +-
docs/dev/relay_intro.html | 4 +-
docs/dev/relay_op_strategy.html | 4 +-
docs/dev/runtime.html | 4 +-
docs/dev/runtimes/vulkan.html | 4 +-
docs/dev/security.html | 4 +-
docs/dev/virtual_machine.html | 4 +-
docs/errors.html | 4 +-
docs/faq.html | 4 +-
docs/genindex.html | 4 +-
docs/index.html | 4 +-
docs/install/docker.html | 4 +-
docs/install/from_source.html | 4 +-
docs/install/index.html | 4 +-
docs/install/nnpack.html | 4 +-
docs/langref/hybrid_script.html | 4 +-
docs/langref/index.html | 4 +-
docs/langref/relay_adt.html | 4 +-
docs/langref/relay_expr.html | 4 +-
docs/langref/relay_op.html | 4 +-
docs/langref/relay_pattern.html | 4 +-
docs/langref/relay_type.html | 4 +-
docs/microtvm/index.html | 4 +-
docs/objects.inv | Bin 19940 -> 19926 bytes
docs/profiling/index.html | 4 +-
docs/profiling/papi.html | 4 +-
docs/py-modindex.html | 4 +-
docs/search.html | 4 +-
docs/searchindex.js | 2 +-
.../auto_scheduler/sg_execution_times.html | 18 +--
.../auto_scheduler/tune_conv2d_layer_cuda.html | 7 +-
.../tutorials/auto_scheduler/tune_network_arm.html | 48 +++----
.../auto_scheduler/tune_network_cuda.html | 54 ++++----
.../auto_scheduler/tune_network_mali.html | 48 +++----
.../tutorials/auto_scheduler/tune_network_x86.html | 64 ++++-----
docs/tutorials/auto_scheduler/tune_sparse_x86.html | 44 +++---
docs/tutorials/autotvm/sg_execution_times.html | 16 +--
docs/tutorials/autotvm/tune_conv2d_cuda.html | 46 +++----
docs/tutorials/autotvm/tune_relay_arm.html | 4 +-
docs/tutorials/autotvm/tune_relay_cuda.html | 4 +-
docs/tutorials/autotvm/tune_relay_mobile_gpu.html | 4 +-
docs/tutorials/autotvm/tune_relay_x86.html | 4 +-
docs/tutorials/dev/bring_your_own_datatypes.html | 4 +-
docs/tutorials/dev/low_level_custom_pass.html | 8 +-
docs/tutorials/dev/sg_execution_times.html | 14 +-
docs/tutorials/dev/use_pass_infra.html | 4 +-
docs/tutorials/dev/use_pass_instrument.html | 20 +--
docs/tutorials/frontend/build_gcn.html | 15 ++-
.../frontend/deploy_model_on_android.html | 6 +-
docs/tutorials/frontend/deploy_model_on_rasp.html | 4 +-
.../frontend/deploy_object_detection_pytorch.html | 52 ++++++-
docs/tutorials/frontend/deploy_prequantized.html | 20 ++-
.../frontend/deploy_prequantized_tflite.html | 8 +-
docs/tutorials/frontend/deploy_quantized.html | 5 +-
docs/tutorials/frontend/deploy_sparse.html | 4 +-
docs/tutorials/frontend/deploy_ssd_gluoncv.html | 31 ++++-
docs/tutorials/frontend/from_caffe2.html | 15 ++-
docs/tutorials/frontend/from_coreml.html | 4 +-
docs/tutorials/frontend/from_darknet.html | 5 +-
docs/tutorials/frontend/from_keras.html | 4 +-
docs/tutorials/frontend/from_mxnet.html | 7 +-
docs/tutorials/frontend/from_onnx.html | 6 +-
docs/tutorials/frontend/from_pytorch.html | 13 +-
docs/tutorials/frontend/from_tensorflow.html | 145 +-------------------
docs/tutorials/frontend/from_tflite.html | 4 +-
docs/tutorials/frontend/sg_execution_times.html | 44 +++---
docs/tutorials/frontend/using_external_lib.html | 4 +-
.../get_started/auto_scheduler_matmul_x86.html | 6 +-
docs/tutorials/get_started/autotvm_matmul_x86.html | 4 +-
docs/tutorials/get_started/autotvm_relay_x86.html | 134 ++++++++++++------
.../get_started/cross_compilation_and_rpc.html | 6 +-
docs/tutorials/get_started/install.html | 4 +-
docs/tutorials/get_started/introduction.html | 4 +-
docs/tutorials/get_started/relay_quick_start.html | 4 +-
docs/tutorials/get_started/sg_execution_times.html | 24 ++--
.../get_started/tensor_expr_get_started.html | 61 +++++----
.../get_started/tvmc_command_line_driver.html | 4 +-
docs/tutorials/index.html | 4 +-
docs/tutorials/language/extern_op.html | 4 +-
docs/tutorials/language/intrin_math.html | 4 +-
docs/tutorials/language/reduction.html | 8 +-
docs/tutorials/language/scan.html | 4 +-
docs/tutorials/language/schedule_primitives.html | 10 +-
docs/tutorials/language/sg_execution_times.html | 22 +--
docs/tutorials/language/tedd.html | 4 +-
docs/tutorials/language/tensorize.html | 8 +-
docs/tutorials/language/tuple_inputs.html | 20 +--
docs/tutorials/micro/micro_autotune.html | 44 +++---
docs/tutorials/micro/micro_reference_vm.html | 4 +-
docs/tutorials/micro/micro_tflite.html | 14 +-
docs/tutorials/micro/sg_execution_times.html | 8 +-
docs/tutorials/optimize/opt_conv_cuda.html | 6 +-
docs/tutorials/optimize/opt_conv_tensorcore.html | 10 +-
docs/tutorials/optimize/opt_gemm.html | 20 +--
docs/tutorials/optimize/sg_execution_times.html | 12 +-
docs/tutorials/topi/intro_topi.html | 6 +-
docs/tutorials/topi/sg_execution_times.html | 8 +-
docs/vta/dev/config.html | 4 +-
docs/vta/dev/hardware.html | 4 +-
docs/vta/dev/index.html | 4 +-
docs/vta/index.html | 4 +-
docs/vta/install.html | 4 +-
docs/vta/tutorials/autotvm/sg_execution_times.html | 10 +-
docs/vta/tutorials/autotvm/tune_alu_vta.html | 4 +-
docs/vta/tutorials/autotvm/tune_relay_vta.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 6 +-
docs/vta/tutorials/frontend/deploy_detection.html | 6 +-
.../vta/tutorials/frontend/sg_execution_times.html | 10 +-
docs/vta/tutorials/index.html | 4 +-
docs/vta/tutorials/matrix_multiply.html | 8 +-
docs/vta/tutorials/optimize/convolution_opt.html | 8 +-
.../tutorials/optimize/matrix_multiply_opt.html | 8 +-
.../vta/tutorials/optimize/sg_execution_times.html | 10 +-
docs/vta/tutorials/sg_execution_times.html | 10 +-
docs/vta/tutorials/vta_get_started.html | 4 +-
264 files changed, 1568 insertions(+), 1621 deletions(-)
diff --git a/docs/_images/sphx_glr_from_onnx_001.png b/docs/_images/sphx_glr_from_onnx_001.png
index c4edf1c..9b6e8e3 100644
Binary files a/docs/_images/sphx_glr_from_onnx_001.png and b/docs/_images/sphx_glr_from_onnx_001.png differ
diff --git a/docs/_images/sphx_glr_from_onnx_thumb.png b/docs/_images/sphx_glr_from_onnx_thumb.png
index 0416e96..669223c 100644
Binary files a/docs/_images/sphx_glr_from_onnx_thumb.png and b/docs/_images/sphx_glr_from_onnx_thumb.png differ
diff --git a/docs/_images/sphx_glr_micro_autotune_thumb.png b/docs/_images/sphx_glr_micro_autotune_thumb.png
index b06c4e6..233f8e6 100644
Binary files a/docs/_images/sphx_glr_micro_autotune_thumb.png and b/docs/_images/sphx_glr_micro_autotune_thumb.png differ
diff --git a/docs/_sources/tutorials/auto_scheduler/sg_execution_times.rst.txt b/docs/_sources/tutorials/auto_scheduler/sg_execution_times.rst.txt
index 5d6eca1..7b9f037 100644
--- a/docs/_sources/tutorials/auto_scheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorials/auto_scheduler/sg_execution_times.rst.txt
@@ -5,11 +5,11 @@
Computation times
=================
-**02:43.083** total execution time for **tutorials_auto_scheduler** files:
-
-- **00:54.913**: :ref:`sphx_glr_tutorials_auto_scheduler_tune_network_x86.py` (``tune_network_x86.py``)
-- **00:51.988**: :ref:`sphx_glr_tutorials_auto_scheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
-- **00:30.251**: :ref:`sphx_glr_tutorials_auto_scheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
-- **00:10.337**: :ref:`sphx_glr_tutorials_auto_scheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
-- **00:08.422**: :ref:`sphx_glr_tutorials_auto_scheduler_tune_network_mali.py` (``tune_network_mali.py``)
-- **00:07.172**: :ref:`sphx_glr_tutorials_auto_scheduler_tune_network_arm.py` (``tune_network_arm.py``)
+**04:07.859** total execution time for **tutorials_auto_scheduler** files:
+
+- **02:12.551**: :ref:`sphx_glr_tutorials_auto_scheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
+- **00:52.866**: :ref:`sphx_glr_tutorials_auto_scheduler_tune_network_x86.py` (``tune_network_x86.py``)
+- **00:30.958**: :ref:`sphx_glr_tutorials_auto_scheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
+- **00:17.657**: :ref:`sphx_glr_tutorials_auto_scheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
+- **00:07.020**: :ref:`sphx_glr_tutorials_auto_scheduler_tune_network_mali.py` (``tune_network_mali.py``)
+- **00:06.806**: :ref:`sphx_glr_tutorials_auto_scheduler_tune_network_arm.py` (``tune_network_arm.py``)
diff --git a/docs/_sources/tutorials/auto_scheduler/tune_conv2d_layer_cuda.rst.txt b/docs/_sources/tutorials/auto_scheduler/tune_conv2d_layer_cuda.rst.txt
index 53b9906..4a9a1ec 100644
--- a/docs/_sources/tutorials/auto_scheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/tutorials/auto_scheduler/tune_conv2d_layer_cuda.rst.txt
@@ -191,6 +191,7 @@ file and apply it.
+
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.
@@ -745,7 +746,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.275 ms
+ Execution time of this operator: 0.353 ms
@@ -1343,6 +1344,11 @@ In the example below we resume the status and do more 5 trials.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 2 minutes 12.551 seconds)
+
+
.. _sphx_glr_download_tutorials_auto_scheduler_tune_conv2d_layer_cuda.py:
diff --git a/docs/_sources/tutorials/auto_scheduler/tune_network_arm.rst.txt b/docs/_sources/tutorials/auto_scheduler/tune_network_arm.rst.txt
index 39ff416..6d0e132 100644
--- a/docs/_sources/tutorials/auto_scheduler/tune_network_arm.rst.txt
+++ b/docs/_sources/tutorials/auto_scheduler/tune_network_arm.rst.txt
@@ -304,14 +304,14 @@ The task scheduler will just optimize this objective.
Get model...
Extract tasks...
- ========== Task 0 (workload key: ["7d44c6e3c81cd80f61ff2265b2bae89a", [1, 1024], [1000, 1024], [1, 1000], [1, 1000]]) ==========
+ ========== Task 0 (workload key: ["7d44c6e3c81cd80f61ff2265b2bae89a", 1, 1024, 1000, 1024, 1, 1000, 1, 1000]) ==========
placeholder = PLACEHOLDER [1, 1024]
placeholder = PLACEHOLDER [1000, 1024]
T_matmul_NT(i, j) += (placeholder[i, k]*placeholder[j, k])
placeholder = PLACEHOLDER [1, 1000]
T_add(ax0, ax1) = (T_matmul_NT[ax0, ax1] + placeholder[ax0, ax1])
- ========== Task 1 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 28, 28, 128], [1, 1, 128, 256], [1, 1, 1, 256], [1, 28, 28, 256]]) ==========
+ ========== Task 1 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 28, 28, 128, 1, 1, 128, 256, 1, 1, 1, 256, 1, 28, 28, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 128, 256]
@@ -320,7 +320,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 2 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 28, 28, 256], [1, 1, 256, 256], [1, 1, 1, 256], [1, 28, 28, 256]]) ==========
+ ========== Task 2 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 28, 28, 256, 1, 1, 256, 256, 1, 1, 1, 256, 1, 28, 28, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 256]
@@ -329,7 +329,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 3 (workload key: ["06fce76bd84cb904eee50b905ca9449a", [1, 14, 14, 512], [3, 3, 512, 1], [1, 1, 1, 512], [1, 14, 14, 512]]) ==========
+ ========== Task 3 (workload key: ["06fce76bd84cb904eee50b905ca9449a", 1, 14, 14, 512, 3, 3, 512, 1, 1, 1, 1, 512, 1, 14, 14, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 512]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 15)) && (i2 >= 1)) && (i2 < 15)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 512, 1]
@@ -338,7 +338,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 4 (workload key: ["98418eda02701ddd175ad50e364a0638", [1, 224, 224, 3], [3, 3, 3, 32], [1, 112, 1, 1], [1, 112, 1, 1], [1, 112, 112, 32]]) ==========
+ ========== Task 4 (workload key: ["98418eda02701ddd175ad50e364a0638", 1, 224, 224, 3, 3, 3, 3, 32, 1, 112, 1, 1, 1, 112, 1, 1, 1, 112, 112, 32]) ==========
placeholder = PLACEHOLDER [1, 224, 224, 3]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 225)) && (i2 >= 1)) && (i2 < 225)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 3, 32]
@@ -349,7 +349,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (T_multiply[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, 0, 0])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 5 (workload key: ["c87ba68bc180312f5716af09a77ca15b", [1, 56, 56, 128], [3, 3, 128, 1], [1, 1, 1, 128], [1, 28, 28, 128]]) ==========
+ ========== Task 5 (workload key: ["c87ba68bc180312f5716af09a77ca15b", 1, 56, 56, 128, 3, 3, 128, 1, 1, 1, 1, 128, 1, 28, 28, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 128]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 57)) && (i2 >= 1)) && (i2 < 57)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 128, 1]
@@ -358,7 +358,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 6 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 14, 14, 512], [1, 1, 512, 512], [1, 1, 1, 512], [1, 14, 14, 512]]) ==========
+ ========== Task 6 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 14, 14, 512, 1, 1, 512, 512, 1, 1, 1, 512, 1, 14, 14, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 512]
@@ -367,7 +367,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 7 (workload key: ["06fce76bd84cb904eee50b905ca9449a", [1, 28, 28, 256], [3, 3, 256, 1], [1, 1, 1, 256], [1, 28, 28, 256]]) ==========
+ ========== Task 7 (workload key: ["06fce76bd84cb904eee50b905ca9449a", 1, 28, 28, 256, 3, 3, 256, 1, 1, 1, 1, 256, 1, 28, 28, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 256]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 29)) && (i2 >= 1)) && (i2 < 29)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 256, 1]
@@ -376,7 +376,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 8 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 7, 7, 1024], [1, 1, 1024, 1024], [1, 1, 1, 1024], [1, 7, 7, 1024]]) ==========
+ ========== Task 8 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 7, 7, 1024, 1, 1, 1024, 1024, 1, 1, 1, 1024, 1, 7, 7, 1024]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 1024]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 1024, 1024]
@@ -385,7 +385,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 9 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 56, 56, 128], [1, 1, 128, 128], [1, 1, 1, 128], [1, 56, 56, 128]]) ==========
+ ========== Task 9 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 56, 56, 128, 1, 1, 128, 128, 1, 1, 1, 128, 1, 56, 56, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 128]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 128, 128]
@@ -394,7 +394,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 10 (workload key: ["06fce76bd84cb904eee50b905ca9449a", [1, 56, 56, 128], [3, 3, 128, 1], [1, 1, 1, 128], [1, 56, 56, 128]]) ==========
+ ========== Task 10 (workload key: ["06fce76bd84cb904eee50b905ca9449a", 1, 56, 56, 128, 3, 3, 128, 1, 1, 1, 1, 128, 1, 56, 56, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 128]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 57)) && (i2 >= 1)) && (i2 < 57)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 128, 1]
@@ -403,7 +403,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 11 (workload key: ["c87ba68bc180312f5716af09a77ca15b", [1, 28, 28, 256], [3, 3, 256, 1], [1, 1, 1, 256], [1, 14, 14, 256]]) ==========
+ ========== Task 11 (workload key: ["c87ba68bc180312f5716af09a77ca15b", 1, 28, 28, 256, 3, 3, 256, 1, 1, 1, 1, 256, 1, 14, 14, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 256]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 29)) && (i2 >= 1)) && (i2 < 29)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 256, 1]
@@ -412,12 +412,12 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 12 (workload key: ["69115f188984ae34ede37c3b8ca40b43", [1, 7, 7, 1024], [1, 1, 1, 1024]]) ==========
+ ========== Task 12 (workload key: ["69115f188984ae34ede37c3b8ca40b43", 1, 7, 7, 1024, 1, 1, 1, 1024]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 1024]
tensor(ax0, ax1, ax2, ax3) += placeholder[ax0, ((ax1*7) + rv0), ((ax2*7) + rv1), ax3]
tensor(ax0, ax1, ax2, ax3) = (tensor[ax0, ax1, ax2, ax3]/(float32((select((bool)1, ((ax1 + 1)*7), (((ax1 + 1)*7) + 1)) - (ax1*7)))*float32((select((bool)1, ((ax2 + 1)*7), (((ax2 + 1)*7) + 1)) - (ax2*7)))))
- ========== Task 13 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 7, 7, 512], [1, 1, 512, 1024], [1, 1, 1, 1024], [1, 7, 7, 1024]]) ==========
+ ========== Task 13 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 7, 7, 512, 1, 1, 512, 1024, 1, 1, 1, 1024, 1, 7, 7, 1024]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 1024]
@@ -426,7 +426,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 14 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 14, 14, 256], [1, 1, 256, 512], [1, 1, 1, 512], [1, 14, 14, 512]]) ==========
+ ========== Task 14 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 14, 14, 256, 1, 1, 256, 512, 1, 1, 1, 512, 1, 14, 14, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 512]
@@ -435,7 +435,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 15 (workload key: ["c87ba68bc180312f5716af09a77ca15b", [1, 14, 14, 512], [3, 3, 512, 1], [1, 1, 1, 512], [1, 7, 7, 512]]) ==========
+ ========== Task 15 (workload key: ["c87ba68bc180312f5716af09a77ca15b", 1, 14, 14, 512, 3, 3, 512, 1, 1, 1, 1, 512, 1, 7, 7, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 512]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 15)) && (i2 >= 1)) && (i2 < 15)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 512, 1]
@@ -444,7 +444,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 16 (workload key: ["06fce76bd84cb904eee50b905ca9449a", [1, 7, 7, 1024], [3, 3, 1024, 1], [1, 1, 1, 1024], [1, 7, 7, 1024]]) ==========
+ ========== Task 16 (workload key: ["06fce76bd84cb904eee50b905ca9449a", 1, 7, 7, 1024, 3, 3, 1024, 1, 1, 1, 1, 1024, 1, 7, 7, 1024]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 1024]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 8)) && (i2 >= 1)) && (i2 < 8)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 1024, 1]
@@ -453,7 +453,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 17 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 56, 56, 64], [1, 1, 64, 128], [1, 1, 1, 128], [1, 56, 56, 128]]) ==========
+ ========== Task 17 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 56, 56, 64, 1, 1, 64, 128, 1, 1, 1, 128, 1, 56, 56, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 64, 128]
@@ -462,7 +462,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 18 (workload key: ["c87ba68bc180312f5716af09a77ca15b", [1, 112, 112, 64], [3, 3, 64, 1], [1, 1, 1, 64], [1, 56, 56, 64]]) ==========
+ ========== Task 18 (workload key: ["c87ba68bc180312f5716af09a77ca15b", 1, 112, 112, 64, 3, 3, 64, 1, 1, 1, 1, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 112, 112, 64]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 113)) && (i2 >= 1)) && (i2 < 113)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 64, 1]
@@ -471,14 +471,14 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 19 (workload key: ["d7b65649a4dd54becea0a52aabbc5af5", [1, 1000], [1, 1000]]) ==========
+ ========== Task 19 (workload key: ["d7b65649a4dd54becea0a52aabbc5af5", 1, 1000, 1, 1000]) ==========
placeholder = PLACEHOLDER [1, 1000]
T_softmax_maxelem(i0) max= placeholder[i0, k]
T_softmax_exp(i0, i1) = tir.exp((placeholder[i0, i1] - T_softmax_maxelem[i0]))
T_softmax_expsum(i0) += T_softmax_exp[i0, k]
T_softmax_norm(i0, i1) = (T_softmax_exp[i0, i1]/T_softmax_expsum[i0])
- ========== Task 20 (workload key: ["06fce76bd84cb904eee50b905ca9449a", [1, 112, 112, 32], [3, 3, 32, 1], [1, 1, 1, 32], [1, 112, 112, 32]]) ==========
+ ========== Task 20 (workload key: ["06fce76bd84cb904eee50b905ca9449a", 1, 112, 112, 32, 3, 3, 32, 1, 1, 1, 1, 32, 1, 112, 112, 32]) ==========
placeholder = PLACEHOLDER [1, 112, 112, 32]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 113)) && (i2 >= 1)) && (i2 < 113)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 32, 1]
@@ -487,7 +487,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 21 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 112, 112, 32], [1, 1, 32, 64], [1, 1, 1, 64], [1, 112, 112, 64]]) ==========
+ ========== Task 21 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 112, 112, 32, 1, 1, 32, 64, 1, 1, 1, 64, 1, 112, 112, 64]) ==========
placeholder = PLACEHOLDER [1, 112, 112, 32]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 32, 64]
diff --git a/docs/_sources/tutorials/auto_scheduler/tune_network_cuda.rst.txt b/docs/_sources/tutorials/auto_scheduler/tune_network_cuda.rst.txt
index bbb0c17..289476d 100644
--- a/docs/_sources/tutorials/auto_scheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/tutorials/auto_scheduler/tune_network_cuda.rst.txt
@@ -182,7 +182,7 @@ The task scheduler will just optimize this objective.
.. code-block:: none
Extract tasks...
- ========== Task 0 (workload key: ["d374e472bd9d8164892b9e28a0a8cb59", [1, 14, 14, 256], [4, 4, 256, 256], [1, 14, 14, 256], [1, 14, 14, 256]]) ==========
+ ========== Task 0 (workload key: ["d374e472bd9d8164892b9e28a0a8cb59", 1, 14, 14, 256, 4, 4, 256, 256, 1, 14, 14, 256, 1, 14, 14, 256]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 15)) && (i2 >= 1)) && (i2 < 15)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 49), ((floormod(floordiv(p, 7), 7)*2) + eps), ((floormod(p, 7)*2) + nu), ci]
@@ -196,14 +196,14 @@ The task scheduler will just optimize this objective.
placeholder = PLACEHOLDER [1, 14, 14, 256]
T_add(ax0, ax1, ax2, ax3) = (conv2d_winograd[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
- ========== Task 1 (workload key: ["d7b65649a4dd54becea0a52aabbc5af5", [1, 1000], [1, 1000]]) ==========
+ ========== Task 1 (workload key: ["d7b65649a4dd54becea0a52aabbc5af5", 1, 1000, 1, 1000]) ==========
placeholder = PLACEHOLDER [1, 1000]
T_softmax_maxelem(i0) max= placeholder[i0, k]
T_softmax_exp(i0, i1) = tir.exp((placeholder[i0, i1] - T_softmax_maxelem[i0]))
T_softmax_expsum(i0) += T_softmax_exp[i0, k]
T_softmax_norm(i0, i1) = (T_softmax_exp[i0, i1]/T_softmax_expsum[i0])
- ========== Task 2 (workload key: ["64b98c71af70a904fdbb81d7d4188d84", [1, 112, 112, 64], [1, 1, 1, 64], [1, 56, 56, 64]]) ==========
+ ========== Task 2 (workload key: ["64b98c71af70a904fdbb81d7d4188d84", 1, 112, 112, 64, 1, 1, 1, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 112, 112, 64]
pad_temp(ax0, ax1, ax2, ax3) = tir.if_then_else(((((ax1 >= 1) && (ax1 < 113)) && (ax2 >= 1)) && (ax2 < 113)), placeholder[ax0, (ax1 - 1), (ax2 - 1), ax3], -3.40282e+38f)
tensor(ax0, ax1, ax2, ax3) max= pad_temp[ax0, ((ax1*2) + rv0), ((ax2*2) + rv1), ax3]
@@ -211,13 +211,13 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (tensor[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 3 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", [1, 56, 56, 64], [1, 1, 64, 128], [1, 28, 28, 128]]) ==========
+ ========== Task 3 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", 1, 56, 56, 64, 1, 1, 64, 128, 1, 28, 28, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 64, 128]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, ((yy*2) + ry), ((xx*2) + rx), rc]*placeholder[ry, rx, rc, ff])
- ========== Task 4 (workload key: ["c4500b4e2fd04e695c32d2f31bbdc14a", [1, 28, 28, 128], [4, 4, 128, 128], [1, 28, 28, 128], [1, 1, 1, 128], [1, 28, 28, 128]]) ==========
+ ========== Task 4 (workload key: ["c4500b4e2fd04e695c32d2f31bbdc14a", 1, 28, 28, 128, 4, 4, 128, 128, 1, 28, 28, 128, 1, 1, 1, 128, 1, 28, 28, 128]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 29)) && (i2 >= 1)) && (i2 < 29)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 196), ((floormod(floordiv(p, 14), 14)*2) + eps), ((floormod(p, 14)*2) + nu), ci]
@@ -234,13 +234,13 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (T_add[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 5 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", [1, 28, 28, 128], [1, 1, 128, 256], [1, 14, 14, 256]]) ==========
+ ========== Task 5 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", 1, 28, 28, 128, 1, 1, 128, 256, 1, 14, 14, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 128, 256]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, ((yy*2) + ry), ((xx*2) + rx), rc]*placeholder[ry, rx, rc, ff])
- ========== Task 6 (workload key: ["e4cdf917b876dbdd64488c3818d9c141", [1, 28, 28, 128], [4, 4, 128, 128], [1, 1, 1, 128], [1, 28, 28, 128]]) ==========
+ ========== Task 6 (workload key: ["e4cdf917b876dbdd64488c3818d9c141", 1, 28, 28, 128, 4, 4, 128, 128, 1, 1, 1, 128, 1, 28, 28, 128]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 29)) && (i2 >= 1)) && (i2 < 29)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 196), ((floormod(floordiv(p, 14), 14)*2) + eps), ((floormod(p, 14)*2) + nu), ci]
@@ -255,7 +255,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (conv2d_winograd[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 7 (workload key: ["dac19035dd5fe9424ee8617421b9c817", [1, 28, 28, 128], [4, 4, 128, 128], [1, 28, 28, 128], [1, 28, 28, 128]]) ==========
+ ========== Task 7 (workload key: ["dac19035dd5fe9424ee8617421b9c817", 1, 28, 28, 128, 4, 4, 128, 128, 1, 28, 28, 128, 1, 28, 28, 128]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 29)) && (i2 >= 1)) && (i2 < 29)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 196), ((floormod(floordiv(p, 14), 14)*2) + eps), ((floormod(p, 14)*2) + nu), ci]
@@ -269,7 +269,7 @@ The task scheduler will just optimize this objective.
placeholder = PLACEHOLDER [1, 28, 28, 128]
T_add(ax0, ax1, ax2, ax3) = (conv2d_winograd[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
- ========== Task 8 (workload key: ["3ea73fb9b0364374730d09e068821f95", [1, 56, 56, 64], [6, 6, 64, 64], [1, 56, 56, 64], [1, 56, 56, 64]]) ==========
+ ========== Task 8 (workload key: ["3ea73fb9b0364374730d09e068821f95", 1, 56, 56, 64, 6, 6, 64, 64, 1, 56, 56, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 57)) && (i2 >= 1)) && (i2 < 57)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 196), ((floormod(floordiv(p, 14), 14)*4) + eps), ((floormod(p, 14)*4) + nu), ci]
@@ -283,7 +283,7 @@ The task scheduler will just optimize this objective.
placeholder = PLACEHOLDER [1, 56, 56, 64]
T_add(ax0, ax1, ax2, ax3) = (conv2d_winograd[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
- ========== Task 9 (workload key: ["d730bcd28f0920f6b97245e2a11bd8d6", [1, 7, 7, 512], [4, 4, 512, 512], [1, 7, 7, 512], [1, 7, 7, 512]]) ==========
+ ========== Task 9 (workload key: ["d730bcd28f0920f6b97245e2a11bd8d6", 1, 7, 7, 512, 4, 4, 512, 512, 1, 7, 7, 512, 1, 7, 7, 512]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 8)) && (i2 >= 1)) && (i2 < 8)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 16), ((floormod(floordiv(p, 4), 4)*2) + eps), ((floormod(p, 4)*2) + nu), ci]
@@ -297,7 +297,7 @@ The task scheduler will just optimize this objective.
placeholder = PLACEHOLDER [1, 7, 7, 512]
T_add(ax0, ax1, ax2, ax3) = (conv2d_winograd[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
- ========== Task 10 (workload key: ["12b88bedece6984af589a28b43e0f3c4", [1, 14, 14, 256], [3, 3, 256, 512], [1, 1, 1, 512], [1, 7, 7, 512]]) ==========
+ ========== Task 10 (workload key: ["12b88bedece6984af589a28b43e0f3c4", 1, 14, 14, 256, 3, 3, 256, 512, 1, 1, 1, 512, 1, 7, 7, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 15)) && (i2 >= 1)) && (i2 < 15)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 256, 512]
@@ -306,7 +306,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 11 (workload key: ["1e3c4211ffd2f2db91078ae4d04b779d", [1, 56, 56, 64], [6, 6, 64, 64], [1, 56, 56, 64], [1, 1, 1, 64], [1, 56, 56, 64]]) ==========
+ ========== Task 11 (workload key: ["1e3c4211ffd2f2db91078ae4d04b779d", 1, 56, 56, 64, 6, 6, 64, 64, 1, 56, 56, 64, 1, 1, 1, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 57)) && (i2 >= 1)) && (i2 < 57)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 196), ((floormod(floordiv(p, 14), 14)*4) + eps), ((floormod(p, 14)*4) + nu), ci]
@@ -323,12 +323,12 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (T_add[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 12 (workload key: ["69115f188984ae34ede37c3b8ca40b43", [1, 7, 7, 512], [1, 1, 1, 512]]) ==========
+ ========== Task 12 (workload key: ["69115f188984ae34ede37c3b8ca40b43", 1, 7, 7, 512, 1, 1, 1, 512]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
tensor(ax0, ax1, ax2, ax3) += placeholder[ax0, ((ax1*7) + rv0), ((ax2*7) + rv1), ax3]
tensor(ax0, ax1, ax2, ax3) = (tensor[ax0, ax1, ax2, ax3]/(float32((select((bool)1, ((ax1 + 1)*7), (((ax1 + 1)*7) + 1)) - (ax1*7)))*float32((select((bool)1, ((ax2 + 1)*7), (((ax2 + 1)*7) + 1)) - (ax2*7)))))
- ========== Task 13 (workload key: ["12b88bedece6984af589a28b43e0f3c4", [1, 56, 56, 64], [3, 3, 64, 128], [1, 1, 1, 128], [1, 28, 28, 128]]) ==========
+ ========== Task 13 (workload key: ["12b88bedece6984af589a28b43e0f3c4", 1, 56, 56, 64, 3, 3, 64, 128, 1, 1, 1, 128, 1, 28, 28, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 57)) && (i2 >= 1)) && (i2 < 57)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 64, 128]
@@ -337,7 +337,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 14 (workload key: ["f3b6c10fcc6ce01ff01add933e4d21e9", [1, 14, 14, 256], [4, 4, 256, 256], [1, 14, 14, 256], [1, 1, 1, 256], [1, 14, 14, 256]]) ==========
+ ========== Task 14 (workload key: ["f3b6c10fcc6ce01ff01add933e4d21e9", 1, 14, 14, 256, 4, 4, 256, 256, 1, 14, 14, 256, 1, 1, 1, 256, 1, 14, 14, 256]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 15)) && (i2 >= 1)) && (i2 < 15)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 49), ((floormod(floordiv(p, 7), 7)*2) + eps), ((floormod(p, 7)*2) + nu), ci]
@@ -354,7 +354,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (T_add[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 15 (workload key: ["b8b52b9be9df6102466a22a014c44c1f", [1, 14, 14, 256], [4, 4, 256, 256], [1, 1, 1, 256], [1, 14, 14, 256]]) ==========
+ ========== Task 15 (workload key: ["b8b52b9be9df6102466a22a014c44c1f", 1, 14, 14, 256, 4, 4, 256, 256, 1, 1, 1, 256, 1, 14, 14, 256]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 15)) && (i2 >= 1)) && (i2 < 15)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 49), ((floormod(floordiv(p, 7), 7)*2) + eps), ((floormod(p, 7)*2) + nu), ci]
@@ -369,7 +369,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (conv2d_winograd[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 16 (workload key: ["12b88bedece6984af589a28b43e0f3c4", [1, 28, 28, 128], [3, 3, 128, 256], [1, 1, 1, 256], [1, 14, 14, 256]]) ==========
+ ========== Task 16 (workload key: ["12b88bedece6984af589a28b43e0f3c4", 1, 28, 28, 128, 3, 3, 128, 256, 1, 1, 1, 256, 1, 14, 14, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 29)) && (i2 >= 1)) && (i2 < 29)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 128, 256]
@@ -378,7 +378,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 17 (workload key: ["ad6cecbf5d85cb1cda3c2bb7af170211", [1, 7, 7, 512], [4, 4, 512, 512], [1, 7, 7, 512], [1, 1, 1, 512], [1, 1, 1, 512], [1, 7, 7, 512]]) ==========
+ ========== Task 17 (workload key: ["ad6cecbf5d85cb1cda3c2bb7af170211", 1, 7, 7, 512, 4, 4, 512, 512, 1, 7, 7, 512, 1, 1, 1, 512, 1, 1, 1, 512, 1, 7, 7, 512]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 8)) && (i2 >= 1)) && (i2 < 8)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 16), ((floormod(floordiv(p, 4), 4)*2) + eps), ((floormod(p, 4)*2) + nu), ci]
@@ -397,7 +397,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (T_multiply[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 18 (workload key: ["3a69f9fbc63760d99e36b4c17b3bfc57", [1, 7, 7, 512], [4, 4, 512, 512], [1, 1, 1, 512], [1, 7, 7, 512]]) ==========
+ ========== Task 18 (workload key: ["3a69f9fbc63760d99e36b4c17b3bfc57", 1, 7, 7, 512, 4, 4, 512, 512, 1, 1, 1, 512, 1, 7, 7, 512]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 8)) && (i2 >= 1)) && (i2 < 8)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 16), ((floormod(floordiv(p, 4), 4)*2) + eps), ((floormod(p, 4)*2) + nu), ci]
@@ -412,7 +412,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (conv2d_winograd[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 19 (workload key: ["12b88bedece6984af589a28b43e0f3c4", [1, 224, 224, 3], [7, 7, 3, 64], [1, 1, 1, 64], [1, 112, 112, 64]]) ==========
+ ========== Task 19 (workload key: ["12b88bedece6984af589a28b43e0f3c4", 1, 224, 224, 3, 7, 7, 3, 64, 1, 1, 1, 64, 1, 112, 112, 64]) ==========
placeholder = PLACEHOLDER [1, 224, 224, 3]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 3) && (i1 < 227)) && (i2 >= 3)) && (i2 < 227)), placeholder[i0, (i1 - 3), (i2 - 3), i3], 0f)
placeholder = PLACEHOLDER [7, 7, 3, 64]
@@ -421,20 +421,20 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 20 (workload key: ["7006235cfc29b73be524cf390ed5a977", [1, 56, 56, 64], [1, 1, 64, 64], [1, 56, 56, 64]]) ==========
+ ========== Task 20 (workload key: ["7006235cfc29b73be524cf390ed5a977", 1, 56, 56, 64, 1, 1, 64, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 64, 64]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
- ========== Task 21 (workload key: ["7d44c6e3c81cd80f61ff2265b2bae89a", [1, 512], [1000, 512], [1, 1000], [1, 1000]]) ==========
+ ========== Task 21 (workload key: ["7d44c6e3c81cd80f61ff2265b2bae89a", 1, 512, 1000, 512, 1, 1000, 1, 1000]) ==========
placeholder = PLACEHOLDER [1, 512]
placeholder = PLACEHOLDER [1000, 512]
T_matmul_NT(i, j) += (placeholder[i, k]*placeholder[j, k])
placeholder = PLACEHOLDER [1, 1000]
T_add(ax0, ax1) = (T_matmul_NT[ax0, ax1] + placeholder[ax0, ax1])
- ========== Task 22 (workload key: ["b818b53148cd450f86569dfc3e04cb8a", [1, 56, 56, 64], [6, 6, 64, 64], [1, 1, 1, 64], [1, 56, 56, 64]]) ==========
+ ========== Task 22 (workload key: ["b818b53148cd450f86569dfc3e04cb8a", 1, 56, 56, 64, 6, 6, 64, 64, 1, 1, 1, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 57)) && (i2 >= 1)) && (i2 < 57)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 196), ((floormod(floordiv(p, 14), 14)*4) + eps), ((floormod(p, 14)*4) + nu), ci]
@@ -449,7 +449,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (conv2d_winograd[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 23 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", [1, 14, 14, 256], [1, 1, 256, 512], [1, 7, 7, 512]]) ==========
+ ========== Task 23 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", 1, 14, 14, 256, 1, 1, 256, 512, 1, 7, 7, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 512]
@@ -614,7 +614,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 1.6973 1.6973 1.6973 1.6972 0.0000
+ 3.1068 3.1042 3.1168 3.0995 0.0073
diff --git a/docs/_sources/tutorials/auto_scheduler/tune_network_mali.rst.txt b/docs/_sources/tutorials/auto_scheduler/tune_network_mali.rst.txt
index 6520763..65ab69f 100644
--- a/docs/_sources/tutorials/auto_scheduler/tune_network_mali.rst.txt
+++ b/docs/_sources/tutorials/auto_scheduler/tune_network_mali.rst.txt
@@ -207,14 +207,14 @@ The task scheduler will just optimize this objective.
.. code-block:: none
Extract tasks...
- ========== Task 0 (workload key: ["7d44c6e3c81cd80f61ff2265b2bae89a", [1, 1024], [1000, 1024], [1, 1000], [1, 1000]]) ==========
+ ========== Task 0 (workload key: ["7d44c6e3c81cd80f61ff2265b2bae89a", 1, 1024, 1000, 1024, 1, 1000, 1, 1000]) ==========
placeholder = PLACEHOLDER [1, 1024]
placeholder = PLACEHOLDER [1000, 1024]
T_matmul_NT(i, j) += (placeholder[i, k]*placeholder[j, k])
placeholder = PLACEHOLDER [1, 1000]
T_add(ax0, ax1) = (T_matmul_NT[ax0, ax1] + placeholder[ax0, ax1])
- ========== Task 1 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 28, 28, 128], [1, 1, 128, 256], [1, 1, 1, 256], [1, 28, 28, 256]]) ==========
+ ========== Task 1 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 28, 28, 128, 1, 1, 128, 256, 1, 1, 1, 256, 1, 28, 28, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 128, 256]
@@ -223,7 +223,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 2 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 28, 28, 256], [1, 1, 256, 256], [1, 1, 1, 256], [1, 28, 28, 256]]) ==========
+ ========== Task 2 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 28, 28, 256, 1, 1, 256, 256, 1, 1, 1, 256, 1, 28, 28, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 256]
@@ -232,7 +232,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 3 (workload key: ["06fce76bd84cb904eee50b905ca9449a", [1, 14, 14, 512], [3, 3, 512, 1], [1, 1, 1, 512], [1, 14, 14, 512]]) ==========
+ ========== Task 3 (workload key: ["06fce76bd84cb904eee50b905ca9449a", 1, 14, 14, 512, 3, 3, 512, 1, 1, 1, 1, 512, 1, 14, 14, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 512]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 15)) && (i2 >= 1)) && (i2 < 15)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 512, 1]
@@ -241,7 +241,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 4 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 14, 14, 512], [1, 1, 512, 512], [1, 1, 1, 512], [1, 14, 14, 512]]) ==========
+ ========== Task 4 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 14, 14, 512, 1, 1, 512, 512, 1, 1, 1, 512, 1, 14, 14, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 512]
@@ -250,7 +250,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 5 (workload key: ["c87ba68bc180312f5716af09a77ca15b", [1, 56, 56, 128], [3, 3, 128, 1], [1, 1, 1, 128], [1, 28, 28, 128]]) ==========
+ ========== Task 5 (workload key: ["c87ba68bc180312f5716af09a77ca15b", 1, 56, 56, 128, 3, 3, 128, 1, 1, 1, 1, 128, 1, 28, 28, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 128]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 57)) && (i2 >= 1)) && (i2 < 57)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 128, 1]
@@ -259,7 +259,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 6 (workload key: ["98418eda02701ddd175ad50e364a0638", [1, 224, 224, 3], [3, 3, 3, 32], [1, 112, 1, 1], [1, 112, 1, 1], [1, 112, 112, 32]]) ==========
+ ========== Task 6 (workload key: ["98418eda02701ddd175ad50e364a0638", 1, 224, 224, 3, 3, 3, 3, 32, 1, 112, 1, 1, 1, 112, 1, 1, 1, 112, 112, 32]) ==========
placeholder = PLACEHOLDER [1, 224, 224, 3]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 225)) && (i2 >= 1)) && (i2 < 225)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 3, 32]
@@ -270,7 +270,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (T_multiply[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, 0, 0])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 7 (workload key: ["06fce76bd84cb904eee50b905ca9449a", [1, 28, 28, 256], [3, 3, 256, 1], [1, 1, 1, 256], [1, 28, 28, 256]]) ==========
+ ========== Task 7 (workload key: ["06fce76bd84cb904eee50b905ca9449a", 1, 28, 28, 256, 3, 3, 256, 1, 1, 1, 1, 256, 1, 28, 28, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 256]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 29)) && (i2 >= 1)) && (i2 < 29)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 256, 1]
@@ -279,7 +279,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 8 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 7, 7, 1024], [1, 1, 1024, 1024], [1, 1, 1, 1024], [1, 7, 7, 1024]]) ==========
+ ========== Task 8 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 7, 7, 1024, 1, 1, 1024, 1024, 1, 1, 1, 1024, 1, 7, 7, 1024]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 1024]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 1024, 1024]
@@ -288,7 +288,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 9 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 56, 56, 128], [1, 1, 128, 128], [1, 1, 1, 128], [1, 56, 56, 128]]) ==========
+ ========== Task 9 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 56, 56, 128, 1, 1, 128, 128, 1, 1, 1, 128, 1, 56, 56, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 128]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 128, 128]
@@ -297,7 +297,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 10 (workload key: ["06fce76bd84cb904eee50b905ca9449a", [1, 56, 56, 128], [3, 3, 128, 1], [1, 1, 1, 128], [1, 56, 56, 128]]) ==========
+ ========== Task 10 (workload key: ["06fce76bd84cb904eee50b905ca9449a", 1, 56, 56, 128, 3, 3, 128, 1, 1, 1, 1, 128, 1, 56, 56, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 128]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 57)) && (i2 >= 1)) && (i2 < 57)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 128, 1]
@@ -306,7 +306,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 11 (workload key: ["c87ba68bc180312f5716af09a77ca15b", [1, 28, 28, 256], [3, 3, 256, 1], [1, 1, 1, 256], [1, 14, 14, 256]]) ==========
+ ========== Task 11 (workload key: ["c87ba68bc180312f5716af09a77ca15b", 1, 28, 28, 256, 3, 3, 256, 1, 1, 1, 1, 256, 1, 14, 14, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 256]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 29)) && (i2 >= 1)) && (i2 < 29)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 256, 1]
@@ -315,7 +315,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 12 (workload key: ["c87ba68bc180312f5716af09a77ca15b", [1, 14, 14, 512], [3, 3, 512, 1], [1, 1, 1, 512], [1, 7, 7, 512]]) ==========
+ ========== Task 12 (workload key: ["c87ba68bc180312f5716af09a77ca15b", 1, 14, 14, 512, 3, 3, 512, 1, 1, 1, 1, 512, 1, 7, 7, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 512]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 15)) && (i2 >= 1)) && (i2 < 15)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 512, 1]
@@ -324,7 +324,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 13 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 14, 14, 256], [1, 1, 256, 512], [1, 1, 1, 512], [1, 14, 14, 512]]) ==========
+ ========== Task 13 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 14, 14, 256, 1, 1, 256, 512, 1, 1, 1, 512, 1, 14, 14, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 512]
@@ -333,12 +333,12 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 14 (workload key: ["69115f188984ae34ede37c3b8ca40b43", [1, 7, 7, 1024], [1, 1, 1, 1024]]) ==========
+ ========== Task 14 (workload key: ["69115f188984ae34ede37c3b8ca40b43", 1, 7, 7, 1024, 1, 1, 1, 1024]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 1024]
tensor(ax0, ax1, ax2, ax3) += placeholder[ax0, ((ax1*7) + rv0), ((ax2*7) + rv1), ax3]
tensor(ax0, ax1, ax2, ax3) = (tensor[ax0, ax1, ax2, ax3]/(float32((select((bool)1, ((ax1 + 1)*7), (((ax1 + 1)*7) + 1)) - (ax1*7)))*float32((select((bool)1, ((ax2 + 1)*7), (((ax2 + 1)*7) + 1)) - (ax2*7)))))
- ========== Task 15 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 7, 7, 512], [1, 1, 512, 1024], [1, 1, 1, 1024], [1, 7, 7, 1024]]) ==========
+ ========== Task 15 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 7, 7, 512, 1, 1, 512, 1024, 1, 1, 1, 1024, 1, 7, 7, 1024]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 1024]
@@ -347,7 +347,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 16 (workload key: ["06fce76bd84cb904eee50b905ca9449a", [1, 7, 7, 1024], [3, 3, 1024, 1], [1, 1, 1, 1024], [1, 7, 7, 1024]]) ==========
+ ========== Task 16 (workload key: ["06fce76bd84cb904eee50b905ca9449a", 1, 7, 7, 1024, 3, 3, 1024, 1, 1, 1, 1, 1024, 1, 7, 7, 1024]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 1024]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 8)) && (i2 >= 1)) && (i2 < 8)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 1024, 1]
@@ -356,7 +356,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 17 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 56, 56, 64], [1, 1, 64, 128], [1, 1, 1, 128], [1, 56, 56, 128]]) ==========
+ ========== Task 17 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 56, 56, 64, 1, 1, 64, 128, 1, 1, 1, 128, 1, 56, 56, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 64, 128]
@@ -365,7 +365,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 18 (workload key: ["c87ba68bc180312f5716af09a77ca15b", [1, 112, 112, 64], [3, 3, 64, 1], [1, 1, 1, 64], [1, 56, 56, 64]]) ==========
+ ========== Task 18 (workload key: ["c87ba68bc180312f5716af09a77ca15b", 1, 112, 112, 64, 3, 3, 64, 1, 1, 1, 1, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 112, 112, 64]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 113)) && (i2 >= 1)) && (i2 < 113)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 64, 1]
@@ -374,14 +374,14 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 19 (workload key: ["d7b65649a4dd54becea0a52aabbc5af5", [1, 1000], [1, 1000]]) ==========
+ ========== Task 19 (workload key: ["d7b65649a4dd54becea0a52aabbc5af5", 1, 1000, 1, 1000]) ==========
placeholder = PLACEHOLDER [1, 1000]
T_softmax_maxelem(i0) max= placeholder[i0, k]
T_softmax_exp(i0, i1) = tir.exp((placeholder[i0, i1] - T_softmax_maxelem[i0]))
T_softmax_expsum(i0) += T_softmax_exp[i0, k]
T_softmax_norm(i0, i1) = (T_softmax_exp[i0, i1]/T_softmax_expsum[i0])
- ========== Task 20 (workload key: ["06fce76bd84cb904eee50b905ca9449a", [1, 112, 112, 32], [3, 3, 32, 1], [1, 1, 1, 32], [1, 112, 112, 32]]) ==========
+ ========== Task 20 (workload key: ["06fce76bd84cb904eee50b905ca9449a", 1, 112, 112, 32, 3, 3, 32, 1, 1, 1, 1, 32, 1, 112, 112, 32]) ==========
placeholder = PLACEHOLDER [1, 112, 112, 32]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 113)) && (i2 >= 1)) && (i2 < 113)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 32, 1]
@@ -390,7 +390,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 21 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 112, 112, 32], [1, 1, 32, 64], [1, 1, 1, 64], [1, 112, 112, 64]]) ==========
+ ========== Task 21 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 112, 112, 32, 1, 1, 32, 64, 1, 1, 1, 64, 1, 112, 112, 64]) ==========
placeholder = PLACEHOLDER [1, 112, 112, 32]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 32, 64]
diff --git a/docs/_sources/tutorials/auto_scheduler/tune_network_x86.rst.txt b/docs/_sources/tutorials/auto_scheduler/tune_network_x86.rst.txt
index 7f4e2ab..68ef50d 100644
--- a/docs/_sources/tutorials/auto_scheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/tutorials/auto_scheduler/tune_network_x86.rst.txt
@@ -205,13 +205,13 @@ The task scheduler will just optimize this objective.
Get model...
Extract tasks...
- ========== Task 0 (workload key: ["7006235cfc29b73be524cf390ed5a977", [1, 56, 56, 64], [1, 1, 64, 256], [1, 56, 56, 256]]) ==========
+ ========== Task 0 (workload key: ["7006235cfc29b73be524cf390ed5a977", 1, 56, 56, 64, 1, 1, 64, 256, 1, 56, 56, 256]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 64, 256]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
- ========== Task 1 (workload key: ["1b524af89dd867d26059e1f621cf987c", [1, 28, 28, 128], [1, 1, 128, 512], [1, 28, 28, 512], [1, 1, 1, 512], [1, 28, 28, 512]]) ==========
+ ========== Task 1 (workload key: ["1b524af89dd867d26059e1f621cf987c", 1, 28, 28, 128, 1, 1, 128, 512, 1, 28, 28, 512, 1, 1, 1, 512, 1, 28, 28, 512]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 128, 512]
@@ -222,7 +222,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (T_add[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 2 (workload key: ["12b88bedece6984af589a28b43e0f3c4", [1, 224, 224, 3], [7, 7, 3, 64], [1, 1, 1, 64], [1, 112, 112, 64]]) ==========
+ ========== Task 2 (workload key: ["12b88bedece6984af589a28b43e0f3c4", 1, 224, 224, 3, 7, 7, 3, 64, 1, 1, 1, 64, 1, 112, 112, 64]) ==========
placeholder = PLACEHOLDER [1, 224, 224, 3]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 3) && (i1 < 227)) && (i2 >= 3)) && (i2 < 227)), placeholder[i0, (i1 - 3), (i2 - 3), i3], 0f)
placeholder = PLACEHOLDER [7, 7, 3, 64]
@@ -231,7 +231,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 3 (workload key: ["1cc666833c122282e3fcf3595901b12b", [1, 28, 28, 128], [1, 1, 128, 512], [1, 28, 28, 512], [1, 28, 28, 512]]) ==========
+ ========== Task 3 (workload key: ["1cc666833c122282e3fcf3595901b12b", 1, 28, 28, 128, 1, 1, 128, 512, 1, 28, 28, 512, 1, 28, 28, 512]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 128, 512]
@@ -239,7 +239,7 @@ The task scheduler will just optimize this objective.
placeholder = PLACEHOLDER [1, 28, 28, 512]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
- ========== Task 4 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 56, 56, 256], [1, 1, 256, 64], [1, 1, 1, 64], [1, 56, 56, 64]]) ==========
+ ========== Task 4 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 56, 56, 256, 1, 1, 256, 64, 1, 1, 1, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 64]
@@ -248,7 +248,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 5 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 28, 28, 512], [1, 1, 512, 128], [1, 1, 1, 128], [1, 28, 28, 128]]) ==========
+ ========== Task 5 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 28, 28, 512, 1, 1, 512, 128, 1, 1, 1, 128, 1, 28, 28, 128]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 128]
@@ -257,7 +257,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 6 (workload key: ["de7d1695278cf52778b038e6573d7626", [1, 28, 28, 512], [1, 1, 512, 256], [1, 1, 1, 256], [1, 14, 14, 256]]) ==========
+ ========== Task 6 (workload key: ["de7d1695278cf52778b038e6573d7626", 1, 28, 28, 512, 1, 1, 512, 256, 1, 1, 1, 256, 1, 14, 14, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 256]
@@ -266,13 +266,13 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 7 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", [1, 56, 56, 256], [1, 1, 256, 512], [1, 28, 28, 512]]) ==========
+ ========== Task 7 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", 1, 56, 56, 256, 1, 1, 256, 512, 1, 28, 28, 512]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 512]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, ((yy*2) + ry), ((xx*2) + rx), rc]*placeholder[ry, rx, rc, ff])
- ========== Task 8 (workload key: ["1cc666833c122282e3fcf3595901b12b", [1, 14, 14, 256], [1, 1, 256, 1024], [1, 14, 14, 1024], [1, 14, 14, 1024]]) ==========
+ ========== Task 8 (workload key: ["1cc666833c122282e3fcf3595901b12b", 1, 14, 14, 256, 1, 1, 256, 1024, 1, 14, 14, 1024, 1, 14, 14, 1024]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 1024]
@@ -280,7 +280,7 @@ The task scheduler will just optimize this objective.
placeholder = PLACEHOLDER [1, 14, 14, 1024]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
- ========== Task 9 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 56, 56, 64], [1, 1, 64, 64], [1, 1, 1, 64], [1, 56, 56, 64]]) ==========
+ ========== Task 9 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 56, 56, 64, 1, 1, 64, 64, 1, 1, 1, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 64, 64]
@@ -289,13 +289,13 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 10 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", [1, 28, 28, 512], [1, 1, 512, 1024], [1, 14, 14, 1024]]) ==========
+ ========== Task 10 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", 1, 28, 28, 512, 1, 1, 512, 1024, 1, 14, 14, 1024]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 1024]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, ((yy*2) + ry), ((xx*2) + rx), rc]*placeholder[ry, rx, rc, ff])
- ========== Task 11 (workload key: ["2350d19dc42a0665244368384c66b3a5", [1, 7, 7, 512], [3, 3, 512, 512], [1, 1, 1, 512], [1, 7, 7, 512]]) ==========
+ ========== Task 11 (workload key: ["2350d19dc42a0665244368384c66b3a5", 1, 7, 7, 512, 3, 3, 512, 512, 1, 1, 1, 512, 1, 7, 7, 512]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 8)) && (i2 >= 1)) && (i2 < 8)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 512, 512]
@@ -304,7 +304,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 12 (workload key: ["1b524af89dd867d26059e1f621cf987c", [1, 56, 56, 64], [1, 1, 64, 256], [1, 56, 56, 256], [1, 1, 1, 256], [1, 56, 56, 256]]) ==========
+ ========== Task 12 (workload key: ["1b524af89dd867d26059e1f621cf987c", 1, 56, 56, 64, 1, 1, 64, 256, 1, 56, 56, 256, 1, 1, 1, 256, 1, 56, 56, 256]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 64, 256]
@@ -315,7 +315,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (T_add[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 13 (workload key: ["2350d19dc42a0665244368384c66b3a5", [1, 56, 56, 64], [3, 3, 64, 64], [1, 1, 1, 64], [1, 56, 56, 64]]) ==========
+ ========== Task 13 (workload key: ["2350d19dc42a0665244368384c66b3a5", 1, 56, 56, 64, 3, 3, 64, 64, 1, 1, 1, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 57)) && (i2 >= 1)) && (i2 < 57)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 64, 64]
@@ -324,7 +324,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 14 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 14, 14, 1024], [1, 1, 1024, 256], [1, 1, 1, 256], [1, 14, 14, 256]]) ==========
+ ========== Task 14 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 14, 14, 1024, 1, 1, 1024, 256, 1, 1, 1, 256, 1, 14, 14, 256]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 1024]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 1024, 256]
@@ -333,12 +333,12 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 15 (workload key: ["69115f188984ae34ede37c3b8ca40b43", [1, 7, 7, 2048], [1, 1, 1, 2048]]) ==========
+ ========== Task 15 (workload key: ["69115f188984ae34ede37c3b8ca40b43", 1, 7, 7, 2048, 1, 1, 1, 2048]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 2048]
tensor(ax0, ax1, ax2, ax3) += placeholder[ax0, ((ax1*7) + rv0), ((ax2*7) + rv1), ax3]
tensor(ax0, ax1, ax2, ax3) = (tensor[ax0, ax1, ax2, ax3]/(float32((select((bool)1, ((ax1 + 1)*7), (((ax1 + 1)*7) + 1)) - (ax1*7)))*float32((select((bool)1, ((ax2 + 1)*7), (((ax2 + 1)*7) + 1)) - (ax2*7)))))
- ========== Task 16 (workload key: ["1cc666833c122282e3fcf3595901b12b", [1, 56, 56, 64], [1, 1, 64, 256], [1, 56, 56, 256], [1, 56, 56, 256]]) ==========
+ ========== Task 16 (workload key: ["1cc666833c122282e3fcf3595901b12b", 1, 56, 56, 64, 1, 1, 64, 256, 1, 56, 56, 256, 1, 56, 56, 256]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 64, 256]
@@ -346,7 +346,7 @@ The task scheduler will just optimize this objective.
placeholder = PLACEHOLDER [1, 56, 56, 256]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
- ========== Task 17 (workload key: ["de7d1695278cf52778b038e6573d7626", [1, 56, 56, 256], [1, 1, 256, 128], [1, 1, 1, 128], [1, 28, 28, 128]]) ==========
+ ========== Task 17 (workload key: ["de7d1695278cf52778b038e6573d7626", 1, 56, 56, 256, 1, 1, 256, 128, 1, 1, 1, 128, 1, 28, 28, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 128]
@@ -355,7 +355,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 18 (workload key: ["de7d1695278cf52778b038e6573d7626", [1, 14, 14, 1024], [1, 1, 1024, 512], [1, 1, 1, 512], [1, 7, 7, 512]]) ==========
+ ========== Task 18 (workload key: ["de7d1695278cf52778b038e6573d7626", 1, 14, 14, 1024, 1, 1, 1024, 512, 1, 1, 1, 512, 1, 7, 7, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 1024]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 1024, 512]
@@ -364,7 +364,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 19 (workload key: ["ecec634b4882c5731f86cce3109db636", [1, 28, 28, 128], [6, 6, 128, 128], [1, 1, 1, 128], [1, 28, 28, 128]]) ==========
+ ========== Task 19 (workload key: ["ecec634b4882c5731f86cce3109db636", 1, 28, 28, 128, 6, 6, 128, 128, 1, 1, 1, 128, 1, 28, 28, 128]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 29)) && (i2 >= 1)) && (i2 < 29)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 49), ((floormod(floordiv(p, 7), 7)*4) + eps), ((floormod(p, 7)*4) + nu), ci]
@@ -379,7 +379,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (conv2d_winograd[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 20 (workload key: ["1cc666833c122282e3fcf3595901b12b", [1, 7, 7, 512], [1, 1, 512, 2048], [1, 7, 7, 2048], [1, 7, 7, 2048]]) ==========
+ ========== Task 20 (workload key: ["1cc666833c122282e3fcf3595901b12b", 1, 7, 7, 512, 1, 1, 512, 2048, 1, 7, 7, 2048, 1, 7, 7, 2048]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 2048]
@@ -387,7 +387,7 @@ The task scheduler will just optimize this objective.
placeholder = PLACEHOLDER [1, 7, 7, 2048]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
- ========== Task 21 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 7, 7, 2048], [1, 1, 2048, 512], [1, 1, 1, 512], [1, 7, 7, 512]]) ==========
+ ========== Task 21 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 7, 7, 2048, 1, 1, 2048, 512, 1, 1, 1, 512, 1, 7, 7, 512]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 2048]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 2048, 512]
@@ -396,7 +396,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 22 (workload key: ["875556d12d0be2269206a7775d5296a6", [1, 7, 7, 512], [1, 1, 512, 2048], [1, 7, 7, 2048], [1, 1, 1, 2048], [1, 1, 1, 2048], [1, 7, 7, 2048]]) ==========
+ ========== Task 22 (workload key: ["875556d12d0be2269206a7775d5296a6", 1, 7, 7, 512, 1, 1, 512, 2048, 1, 7, 7, 2048, 1, 1, 1, 2048, 1, 1, 1, 2048, 1, 7, 7, 2048]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 2048]
@@ -409,7 +409,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (T_multiply[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 23 (workload key: ["c68f92478eb18145106184c587d212b6", [1, 14, 14, 256], [6, 6, 256, 256], [1, 1, 1, 256], [1, 14, 14, 256]]) ==========
+ ========== Task 23 (workload key: ["c68f92478eb18145106184c587d212b6", 1, 14, 14, 256, 6, 6, 256, 256, 1, 1, 1, 256, 1, 14, 14, 256]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 15)) && (i2 >= 1)) && (i2 < 15)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 16), ((floormod(floordiv(p, 4), 4)*4) + eps), ((floormod(p, 4)*4) + nu), ci]
@@ -424,21 +424,21 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (conv2d_winograd[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 24 (workload key: ["7d44c6e3c81cd80f61ff2265b2bae89a", [1, 2048], [1000, 2048], [1, 1000], [1, 1000]]) ==========
+ ========== Task 24 (workload key: ["7d44c6e3c81cd80f61ff2265b2bae89a", 1, 2048, 1000, 2048, 1, 1000, 1, 1000]) ==========
placeholder = PLACEHOLDER [1, 2048]
placeholder = PLACEHOLDER [1000, 2048]
T_matmul_NT(i, j) += (placeholder[i, k]*placeholder[j, k])
placeholder = PLACEHOLDER [1, 1000]
T_add(ax0, ax1) = (T_matmul_NT[ax0, ax1] + placeholder[ax0, ax1])
- ========== Task 25 (workload key: ["d7b65649a4dd54becea0a52aabbc5af5", [1, 1000], [1, 1000]]) ==========
+ ========== Task 25 (workload key: ["d7b65649a4dd54becea0a52aabbc5af5", 1, 1000, 1, 1000]) ==========
placeholder = PLACEHOLDER [1, 1000]
T_softmax_maxelem(i0) max= placeholder[i0, k]
T_softmax_exp(i0, i1) = tir.exp((placeholder[i0, i1] - T_softmax_maxelem[i0]))
T_softmax_expsum(i0) += T_softmax_exp[i0, k]
T_softmax_norm(i0, i1) = (T_softmax_exp[i0, i1]/T_softmax_expsum[i0])
- ========== Task 26 (workload key: ["64b98c71af70a904fdbb81d7d4188d84", [1, 112, 112, 64], [1, 1, 1, 64], [1, 56, 56, 64]]) ==========
+ ========== Task 26 (workload key: ["64b98c71af70a904fdbb81d7d4188d84", 1, 112, 112, 64, 1, 1, 1, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 112, 112, 64]
pad_temp(ax0, ax1, ax2, ax3) = tir.if_then_else(((((ax1 >= 1) && (ax1 < 113)) && (ax2 >= 1)) && (ax2 < 113)), placeholder[ax0, (ax1 - 1), (ax2 - 1), ax3], -3.40282e+38f)
tensor(ax0, ax1, ax2, ax3) max= pad_temp[ax0, ((ax1*2) + rv0), ((ax2*2) + rv1), ax3]
@@ -446,7 +446,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (tensor[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 27 (workload key: ["1b524af89dd867d26059e1f621cf987c", [1, 14, 14, 256], [1, 1, 256, 1024], [1, 14, 14, 1024], [1, 1, 1, 1024], [1, 14, 14, 1024]]) ==========
+ ========== Task 27 (workload key: ["1b524af89dd867d26059e1f621cf987c", 1, 14, 14, 256, 1, 1, 256, 1024, 1, 14, 14, 1024, 1, 1, 1, 1024, 1, 14, 14, 1024]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 1024]
@@ -457,7 +457,7 @@ The task scheduler will just optimize this objective.
T_add(ax0, ax1, ax2, ax3) = (T_add[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
- ========== Task 28 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", [1, 14, 14, 1024], [1, 1, 1024, 2048], [1, 7, 7, 2048]]) ==========
+ ========== Task 28 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", 1, 14, 14, 1024, 1, 1, 1024, 2048, 1, 7, 7, 2048]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 1024]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 1024, 2048]
@@ -633,7 +633,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 561.6463 561.3978 563.6430 559.8980 1.5390
+ 552.8841 552.2991 554.2759 552.0773 0.9883
diff --git a/docs/_sources/tutorials/auto_scheduler/tune_sparse_x86.rst.txt b/docs/_sources/tutorials/auto_scheduler/tune_sparse_x86.rst.txt
index b1c835d..e0788f1 100644
--- a/docs/_sources/tutorials/auto_scheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/tutorials/auto_scheduler/tune_sparse_x86.rst.txt
@@ -330,6 +330,7 @@ file and apply it.
+
We can lower the schedule to see the IR after auto-scheduling.
The auto-scheduler correctly performs optimizations including multi-level tiling,
layout transformation, parallelization, vectorization, unrolling, and operator fusion.
@@ -355,26 +356,32 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
primfn(placeholder_5: handle, placeholder_6: handle, placeholder_7: handle, placeholder_8: handle, placeholder_9: handle, compute_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], []),
- placeholder_4: Buffer(placeholder_10: Pointer(float32), float32, [128, 256], []),
- placeholder_3: Buffer(placeholder_11: Pointer(float32), float32, [128, 512], []),
- placeholder_2: Buffer(placeholder_12: Pointer(int32), int32, [33], []),
- placeholder: Buffer(placeholder_13: Pointer(float32), float32, [4916, 16, 1], []),
- placeholder_1: Buffer(placeholder_14: Pointer(int32), int32, [4916], [])}
- buffer_map = {placeholder_6: placeholder, placeholder_7: placeholder_1, placeholder_8: placeholder_2, placeholder_9: placeholder_3, placeholder_5: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 128) {
- for (j.init: int32, 0, 16) {
- compute_3[((i.outer.inner*16) + j.init)] = 0f32
+ placeholder_2: Buffer(placeholder_10: Pointer(int32), int32, [4916], []),
+ placeholder: Buffer(placeholder_11: Pointer(float32), float32, [128, 512], []),
+ placeholder_4: Buffer(placeholder_12: Pointer(float32), float32, [4916, 16, 1], []),
+ placeholder_3: Buffer(placeholder_13: Pointer(int32), int32, [33], []),
+ placeholder_1: Buffer(placeholder_14: Pointer(float32), float32, [128, 256], [])}
+ buffer_map = {placeholder_9: placeholder, placeholder_5: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, compute_1: compute, placeholder_6: placeholder_4} {
+ for (i0.outer.i1.outer.fused: int32, 0, 512) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [128]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 4) {
+ for (j.init: int32, 0, 16) {
+ compute_3[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
+ }
}
- for (elem_idx: int32, 0, ((int32*)placeholder_12[(i0.outer.i1.outer.fused + 1)] - (int32*)placeholder_12[i0.outer.i1.outer.fused])) {
- for (j: int32, 0, 16) {
- compute_3[((i.outer.inner*16) + j)] = ((float32*)compute_3[((i.outer.inner*16) + j)] + ((float32*)placeholder_13[((((int32*)placeholder_12[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + j)]*max((float32*)placeholder_10[((i.outer.inner*256) + (int32*)placeholder_14[((int32*)placeholder_12[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, ((int32*)placeholder_13[(floormod(i0.outer.i1.outer.fused, 32) + 1)] - (int32*)placeholder_13[floormod(i0.outer.i1.outer.fused, 32)])) {
+ for (i.inner: int32, 0, 4) {
+ for (j: int32, 0, 16) {
+ compute_3[(((i.outer.inner*64) + (i.inner*16)) + j)] = ((float32*)compute_3[(((i.outer.inner*64) + (i.inner*16)) + j)] + ((float32*)placeholder_12[((((int32*)placeholder_13[floormod(i0.outer.i1.outer.fused, 32)]*16) + (elem_idx*16)) + j)]*max((float32*)placeholder_14[((((floordiv(i0.outer.i1.outer.fused, 32)*2048) + (i.outer.inner*1024)) + (i.inner*256)) + (int32*)placeholder_10[((int32*)placeholder_13[floormod(i0.outer.i1.outer.fused, 32)] + elem_idx)])], 0f32)))
+ }
}
}
}
- for (i0.inner: int32, 0, 128) {
- compute_2[ramp(((i0.inner*512) + (i0.outer.i1.outer.fused*16)), 1, 16)] = max(((float32x16*)compute_3[ramp((i0.inner*16), 1, 16)] + (float32x16*)placeholder_11[ramp(((i0.inner*512) + (i0.outer.i1.outer.fused*16)), 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 8) {
+ for (i1.inner: int32, 0, 16) {
+ compute_2[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16)) + i1.inner)] = max(((float32*)compute_3[((i0.inner*16) + i1.inner)] + (float32*)placeholder_11[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16)) + i1.inner)]), 0f32)
+ }
}
}
}
@@ -428,7 +435,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.277 ms
+ Execution time of this operator: 1.368 ms
diff --git a/docs/_sources/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/tutorials/autotvm/sg_execution_times.rst.txt
index dd076e8..08bc1a8 100644
--- a/docs/_sources/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:39.245** total execution time for **tutorials_autotvm** files:
+**00:39.734** total execution time for **tutorials_autotvm** files:
-- **00:38.648**: :ref:`sphx_glr_tutorials_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
-- **00:00.156**: :ref:`sphx_glr_tutorials_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
-- **00:00.148**: :ref:`sphx_glr_tutorials_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
-- **00:00.146**: :ref:`sphx_glr_tutorials_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
-- **00:00.146**: :ref:`sphx_glr_tutorials_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:39.040**: :ref:`sphx_glr_tutorials_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
+- **00:00.181**: :ref:`sphx_glr_tutorials_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
+- **00:00.172**: :ref:`sphx_glr_tutorials_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:00.171**: :ref:`sphx_glr_tutorials_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
+- **00:00.170**: :ref:`sphx_glr_tutorials_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
diff --git a/docs/_sources/tutorials/autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/tutorials/autotvm/tune_conv2d_cuda.rst.txt
index 5a51cb1..b6cac63 100644
--- a/docs/_sources/tutorials/autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/tutorials/autotvm/tune_conv2d_cuda.rst.txt
@@ -242,26 +242,26 @@ for this template
7 unroll_explicit: OtherOption([0, 1]) len=2
)
Get devices for measurement successfully!
- No: 1 GFLOPS: 0.00/0.00 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs [...]
- No: 2 GFLOPS: 0.00/0.00 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs [...]
- No: 3 GFLOPS: 0.00/0.00 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs [...]
- No: 4 GFLOPS: 0.00/0.00 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs [...]
- No: 5 GFLOPS: 0.00/0.00 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs [...]
- No: 6 GFLOPS: 201.58/201.58 result: MeasureResult(costs=(0.001148416731958763,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6018972396850586, timestamp=1631673064.161226) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
- No: 7 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs [...]
- No: 8 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs [...]
- No: 9 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs [...]
- No: 10 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(TimeoutError(),), error_no=MeasureErrorNo.BUILD_TIMEOUT, all_cost=10, timestamp=1631673060.8658895) [('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
- No: 11 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs [...]
- No: 12 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs [...]
- No: 13 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs [...]
- No: 14 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs [...]
- No: 15 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs [...]
- No: 16 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs [...]
- No: 17 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs [...]
- No: 18 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs [...]
- No: 19 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(RuntimeError('Traceback (most recent call last):\n 11: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 10: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 9: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm:: [...]
- No: 20 GFLOPS: 280.06/280.06 result: MeasureResult(costs=(0.0008266168206896552,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2443122863769531, timestamp=1631673072.5713875) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+ No: 1 GFLOPS: 0.00/0.00 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRet [...]
+ No: 2 GFLOPS: 0.00/0.00 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRet [...]
+ No: 3 GFLOPS: 0.00/0.00 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRet [...]
+ No: 4 GFLOPS: 0.00/0.00 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRet [...]
+ No: 5 GFLOPS: 0.00/0.00 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRet [...]
+ No: 6 GFLOPS: 89.05/89.05 result: MeasureResult(costs=(0.0025997949565217393,), error_no=0, all_cost=2.115823268890381, timestamp=1630092140.2873092) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+ No: 7 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRet [...]
+ No: 8 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRet [...]
+ No: 9 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRet [...]
+ No: 10 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(TimeoutError(),), error_no=6, all_cost=10, timestamp=1630092151.3702137) [('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
+ No: 11 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRet [...]
+ No: 12 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRet [...]
+ No: 13 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRet [...]
+ No: 14 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRet [...]
+ No: 15 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRet [...]
+ No: 16 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRet [...]
+ No: 17 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRet [...]
+ No: 18 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRet [...]
+ No: 19 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(RuntimeError('Traceback (most recent call last):\n 99: 0x00000000005099ff\n 98: 0x0000000000507cd3\n 97: _PyEval_EvalFrameDefault\n 96: 0x000000000050a3fc\n 95: 0x00000000005096c7\n 94: _PyEval_EvalFrameDefault\n 93: 0x000000000050a3fc\n 92: 0x00000000005096c7\n 91: _PyEval_EvalFrameDefault\n 90: 0x000000000050a3fc\n 89: 0x00000000005096c7\n 88: _PyEval_EvalFrameDefault\n 87: 0x000000000050a532\n 86: _PyObject [...]
+ No: 20 GFLOPS: 144.01/144.01 result: MeasureResult(costs=(0.0016075873015873017,), error_no=0, all_cost=1.4732651710510254, timestamp=1630092163.9221466) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
@@ -314,7 +314,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
- Time cost of this operator: 0.000934
+ Time cost of this operator: 0.002075
diff --git a/docs/_sources/tutorials/dev/low_level_custom_pass.rst.txt b/docs/_sources/tutorials/dev/low_level_custom_pass.rst.txt
index 69f7b32..7d13f7d 100644
--- a/docs/_sources/tutorials/dev/low_level_custom_pass.rst.txt
+++ b/docs/_sources/tutorials/dev/low_level_custom_pass.rst.txt
@@ -221,8 +221,8 @@ Thus, a good place to put this transformation pass is just after Phase 1.
primfn(a_1: handle, b_1: handle, c_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {c: Buffer(c_2: Pointer(float32), float32, [128], []),
- a: Buffer(a_2: Pointer(float32), float32, [128], []),
+ buffers = {a: Buffer(a_2: Pointer(float32), float32, [128], []),
+ c: Buffer(c_2: Pointer(float32), float32, [128], []),
b: Buffer(b_2: Pointer(float32), float32, [128], [])}
buffer_map = {a_1: a, b_1: b, c_1: c} {
for (i.outer: int32, 0, 16) {
diff --git a/docs/_sources/tutorials/dev/sg_execution_times.rst.txt b/docs/_sources/tutorials/dev/sg_execution_times.rst.txt
index e301c61..2194a53 100644
--- a/docs/_sources/tutorials/dev/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorials/dev/sg_execution_times.rst.txt
@@ -5,9 +5,9 @@
Computation times
=================
-**00:35.311** total execution time for **tutorials_dev** files:
+**00:49.008** total execution time for **tutorials_dev** files:
-- **00:31.575**: :ref:`sphx_glr_tutorials_dev_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
-- **00:02.244**: :ref:`sphx_glr_tutorials_dev_use_pass_instrument.py` (``use_pass_instrument.py``)
-- **00:01.344**: :ref:`sphx_glr_tutorials_dev_use_pass_infra.py` (``use_pass_infra.py``)
-- **00:00.148**: :ref:`sphx_glr_tutorials_dev_low_level_custom_pass.py` (``low_level_custom_pass.py``)
+- **00:49.008**: :ref:`sphx_glr_tutorials_dev_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_dev_low_level_custom_pass.py` (``low_level_custom_pass.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_dev_use_pass_infra.py` (``use_pass_infra.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_dev_use_pass_instrument.py` (``use_pass_instrument.py``)
diff --git a/docs/_sources/tutorials/dev/use_pass_instrument.rst.txt b/docs/_sources/tutorials/dev/use_pass_instrument.rst.txt
index eaa6578..e694db2 100644
--- a/docs/_sources/tutorials/dev/use_pass_instrument.rst.txt
+++ b/docs/_sources/tutorials/dev/use_pass_instrument.rst.txt
@@ -199,10 +199,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 3752us [3752us] (45.67%; 45.67%)
- FoldScaleAxis: 4464us [2us] (54.33%; 54.33%)
- FoldConstant: 4463us [920us] (54.31%; 99.96%)
- InferType: 3542us [3542us] (43.12%; 79.38%)
+ InferType: 5181us [5181us] (45.61%; 45.61%)
+ FoldScaleAxis: 6179us [2us] (54.39%; 54.39%)
+ FoldConstant: 6177us [1335us] (54.38%; 99.97%)
+ InferType: 4842us [4842us] (42.62%; 78.39%)
@@ -239,10 +239,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 3532us [3532us] (44.22%; 44.22%)
- FoldScaleAxis: 4455us [2us] (55.78%; 55.78%)
- FoldConstant: 4454us [969us] (55.76%; 99.97%)
- InferType: 3485us [3485us] (43.63%; 78.24%)
+ InferType: 4919us [4919us] (44.75%; 44.75%)
+ FoldScaleAxis: 6074us [2us] (55.25%; 55.25%)
+ FoldConstant: 6072us [1337us] (55.23%; 99.97%)
+ InferType: 4734us [4734us] (43.07%; 77.97%)
diff --git a/docs/_sources/tutorials/frontend/build_gcn.rst.txt b/docs/_sources/tutorials/frontend/build_gcn.rst.txt
index 5fe422d..4a27976 100644
--- a/docs/_sources/tutorials/frontend/build_gcn.rst.txt
+++ b/docs/_sources/tutorials/frontend/build_gcn.rst.txt
@@ -70,6 +70,8 @@ This part reuses the code from the above example.
.. code-block:: none
+ DGL backend not selected or invalid. Assuming PyTorch for now.
+ Setting the default backend to "pytorch". You can change it in the ~/.dgl/config.json file or export the DGLBACKEND environment variable. Valid options are: pytorch, mxnet, tensorflow (all lowercase)
Using backend: pytorch
@@ -155,6 +157,9 @@ Load the data and set up model parameters
.. code-block:: none
+ Downloading /workspace/.dgl/cora_v2.zip from https://data.dgl.ai/dataset/cora_v2.zip...
+ Extracting file to /workspace/.dgl/cora_v2
+ Finished data loading and preprocessing.
NumNodes: 2708
NumEdges: 10556
NumFeats: 1433
@@ -162,7 +167,7 @@ Load the data and set up model parameters
NumTrainingSamples: 140
NumValidationSamples: 500
NumTestSamples: 1000
- Done loading data from cached files.
+ Done saving data into cached files.
/usr/local/lib/python3.6/dist-packages/dgl/data/utils.py:285: UserWarning: Property dataset.graph will be deprecated, please use dataset[0] instead.
warnings.warn('Property {} will be deprecated, please use {} instead.'.format(old, new))
/usr/local/lib/python3.6/dist-packages/dgl/data/utils.py:285: UserWarning: Property dataset.feat will be deprecated, please use g.ndata['feat'] instead.
diff --git a/docs/_sources/tutorials/frontend/deploy_model_on_android.rst.txt b/docs/_sources/tutorials/frontend/deploy_model_on_android.rst.txt
index ce1bc0c..9618d6c 100644
--- a/docs/_sources/tutorials/frontend/deploy_model_on_android.rst.txt
+++ b/docs/_sources/tutorials/frontend/deploy_model_on_android.rst.txt
@@ -393,7 +393,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.3173 7.2984 7.3807 7.2587 0.0423
+ 11.0604 10.7861 12.7899 10.6342 0.6586
diff --git a/docs/_sources/tutorials/frontend/deploy_object_detection_pytorch.rst.txt b/docs/_sources/tutorials/frontend/deploy_object_detection_pytorch.rst.txt
index a1afc65..b7061a0 100644
--- a/docs/_sources/tutorials/frontend/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/tutorials/frontend/deploy_object_detection_pytorch.rst.txt
@@ -107,6 +107,8 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
+ Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
+
0%| | 0.00/170M [00:00<?, ?B/s]
0%| | 8.00k/170M [00:00<1:36:57, 30.6kB/s]
1%|1 | 2.31M/170M [00:00<00:20, 8.39MB/s]
4%|4 | 7.31M/170M [00:00<00:07, 22.9MB/s]
7%|7 | 12.0M/170M [00:00<00:05, 31.3MB/s]
9%|9 | 15.7M/170M [00:00<00:05, 30.0MB/s]
11%|#1 | 19.4M/170M [00:00<00:04, 32.4MB/s]
13%|#3 | 22.8M/170M [00:00<00:04, 31.7MB/s]
15%|#5 | 26.1M/170M [00:01<00:04, 30.5MB/s]
17%|#7 | 29.1M/170M [00:01<00:04, 30.3MB/s]
20%|## | 34.5M/170M [00:01<00:03, 37.5MB/s]
24%|##3 | 40.2M/170M [00:01<00:03, 43.9MB/s]
26%|##6 | 44.6M/170M [00:01<00:03, 43.0MB/s]
29%|##8 | 49.1M/170M [00:01<00:02, 44.3MB/s]
31%|###1 | 53.4M/170M [00:01<00:02, 44.5MB/s]
34%|###4 | 58.2M/170M [00:01<00:02, 46.1MB/s]
37%|###6 | 62.7M/170M [00:01<00:02, 42.7MB/s]
39%|###9 | 66.8M/170M [00:02<00:02, 42.
1MB/s]
42%|####1 | 70.9M/170M [00:02<00:02, 40.7MB/s]
44%|####4 | 75.5M/170M [00:02<00:02, 42.9MB/s]
47%|####6 | 79.6M/170M [00:02<00:02, 36.4MB/s]
50%|####9 | 84.3M/170M [00:02<00:02, 39.6MB/s]
53%|#####2 | 89.9M/170M [00:02<00:01, 44.8MB/s]
56%|#####5 | 94.4M/170M [00:02<00:01, 44.8MB/s]
58%|#####8 | 98.8M/170M [00:02<00:01, 44.0MB/s]
61%|###### | 103M/170M [00:02<00:01, 41.7MB/s]
63%|######3 | 107M/170M [00:03<00:01, 33.8MB/s]
66%|######5 | 111M/170M [00:03<00:01, 36.0MB/s]
68%|######8 | 116M/170M [00:03<00:01, 39.7MB/s]
71%|#######1 | 121M/170M [00:03<00:01, 42.3MB/s]
74%|#######3 | 125M/170M [00:03<00:01, 43.8MB/s]
76%|#######6 | 130M/170M [00:03<00:01, 31.9MB/s]
79%|#######8 | 133M/170M [00:03<00:01, 33.3MB/s]
81%|######## | 137M/170M [00:03<00:00, 35.0MB/s]
83%|########3 | 141M/170M [00:04<00:00, 37.2MB/s]
86%|########5 | 146M/170M [00:04<00:00, 38
.9MB/s]
88%|########8 | 150M/170M [00:04<00:00, 41.6MB/s]
91%|######### | 154M/170M [00:04<00:00, 38.4MB/s]
94%|#########4| 160M/170M [00:04<00:00, 43.7MB/s]
97%|#########6| 164M/170M [00:04<00:00, 42.7MB/s]
99%|#########9| 169M/170M [00:04<00:00, 42.2MB/s]
100%|##########| 170M/170M [00:04<00:00, 37.6MB/s]
/usr/local/lib/python3.6/dist-packages/torch/tensor.py:593: RuntimeWarning: Iterating over a tensor might cause the trace to be incorrect. Passing a tensor of different shape won't change the number of iterations executed (and might lead to errors or silently give incorrect results).
'incorrect results).', category=RuntimeWarning)
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py:3123: 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).
@@ -238,7 +240,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 42.237 seconds)
+ **Total running time of the script:** ( 6 minutes 34.821 seconds)
.. _sphx_glr_download_tutorials_frontend_deploy_object_detection_pytorch.py:
diff --git a/docs/_sources/tutorials/frontend/deploy_prequantized.rst.txt b/docs/_sources/tutorials/frontend/deploy_prequantized.rst.txt
index cf9ec7d..47bb3d5 100644
--- a/docs/_sources/tutorials/frontend/deploy_prequantized.rst.txt
+++ b/docs/_sources/tutorials/frontend/deploy_prequantized.rst.txt
@@ -180,6 +180,15 @@ training. Other models require a full post training calibration.
+.. rst-class:: sphx-glr-script-out
+
+ Out:
+
+ .. code-block:: none
+
+ Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
29%|##9 | 3.98M/13.6M [00:00<00:00, 41.7MB/s]
62%|######1 | 8.36M/13.6M [00:00<00:00, 44.2MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 63.1MB/s]
+
Quantize, trace and run the PyTorch Mobilenet v2 model
@@ -283,7 +292,7 @@ We should see identical labels printed.
.. code-block:: none
- PyTorch top3 labels: ['tiger cat', 'Egyptian cat', 'tabby, tabby cat']
+ PyTorch top3 labels: ['tiger cat', 'Egyptian cat', 'lynx, catamount']
TVM top3 labels: ['tiger cat', 'Egyptian cat', 'tabby, tabby cat']
@@ -307,7 +316,7 @@ output values are identical out of 1000 outputs from mobilenet v2.
.. code-block:: none
- 140 in 1000 raw floating outputs identical.
+ 132 in 1000 raw floating outputs identical.
@@ -334,7 +343,7 @@ 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)
- 18.4986 18.4725 19.6626 18.3014 0.1583
+ 39.4568 38.9747 58.8311 38.6383 2.0381
@@ -372,6 +381,11 @@ Deploy a quantized TFLite Model
TODO
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 37.273 seconds)
+
+
.. _sphx_glr_download_tutorials_frontend_deploy_prequantized.py:
diff --git a/docs/_sources/tutorials/frontend/deploy_prequantized_tflite.rst.txt b/docs/_sources/tutorials/frontend/deploy_prequantized_tflite.rst.txt
index aa8a01b..ccb3b1e 100644
--- a/docs/_sources/tutorials/frontend/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/tutorials/frontend/deploy_prequantized_tflite.rst.txt
@@ -352,7 +352,7 @@ 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)
- 34.6676 34.3071 55.0247 33.8788 2.1488
+ 72.0695 71.4769 89.6603 69.9658 2.3134
@@ -386,7 +386,7 @@ 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 9.880 seconds)
+ **Total running time of the script:** ( 2 minutes 19.036 seconds)
.. _sphx_glr_download_tutorials_frontend_deploy_prequantized_tflite.py:
diff --git a/docs/_sources/tutorials/frontend/deploy_quantized.rst.txt b/docs/_sources/tutorials/frontend/deploy_quantized.rst.txt
index 28e6f9d..a367ea8 100644
--- a/docs/_sources/tutorials/frontend/deploy_quantized.rst.txt
+++ b/docs/_sources/tutorials/frontend/deploy_quantized.rst.txt
@@ -210,6 +210,11 @@ We create a Relay VM to build and execute the model.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 24.981 seconds)
+
+
.. _sphx_glr_download_tutorials_frontend_deploy_quantized.py:
diff --git a/docs/_sources/tutorials/frontend/deploy_ssd_gluoncv.rst.txt b/docs/_sources/tutorials/frontend/deploy_ssd_gluoncv.rst.txt
index 92210d6..773bc51 100644
--- a/docs/_sources/tutorials/frontend/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/tutorials/frontend/deploy_ssd_gluoncv.rst.txt
@@ -136,6 +136,8 @@ Convert and compile model for CPU.
/usr/local/lib/python3.6/dist-packages/mxnet/gluon/block.py:1389: UserWarning: Cannot decide type for the following arguments. Consider providing them as input:
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]
2%|1 | 2136/132723 [00:00<00:14, 9070.09KB/s]
4%|3 | 4955/132723 [00:00<00:07, 16289.03KB/s]
8%|7 | 10343/132723 [00:00<00:04, 29460.18KB/s]
10%|# | 13908/132723 [00:00<00:04, 29404.22KB/s]
13%|#2 | 17223/132723 [00:00<00:04, 28235.72KB/s]
17%|#6 | 21954/132723 [00:00<00:03, 33744.53KB/s]
19%|#9 | 25584/132723 [00:00<00:03, 33127.69KB/s]
25%|##4 | 32757/132723 [00:01<00:02, 37422.81KB/s]
28%|##7 | 37099/132723 [00:01<00:02, 35875.46KB/s]
31%|### | 40711/132723 [00:01<00:02, 35048.87KB/s]
37%|###6 | 48894/132723 [00:01<00:01, 47232.76KB/s]
41%|#### | 53835/132723 [00:01<00:02, 38447.61KB/s]
48%|####8 | 64078/132723 [00:01<00:01, 53641.55KB/s]
53%|#####2 | 70129/132723 [00:01<00:01, 49190.34KB/s]
59%|#####9 | 78360/132723 [00:01<00:00, 57245.79KB/s]
64%|######3 | 8
4644/132723 [00:02<00:00, 51620.82KB/s]
71%|#######1 | 94737/132723 [00:02<00:00, 63687.46KB/s]
77%|#######6 | 101708/132723 [00:02<00:00, 39024.85KB/s]
84%|########4 | 111833/132723 [00:02<00:00, 50300.89KB/s]
89%|########9 | 118693/132723 [00:02<00:00, 46824.58KB/s]
97%|#########7| 128849/132723 [00:02<00:00, 57925.56KB/s]
100%|##########| 132723/132723 [00:03<00:00, 43823.76KB/s]
@@ -200,7 +202,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 44.102 seconds)
+ **Total running time of the script:** ( 3 minutes 23.389 seconds)
.. _sphx_glr_download_tutorials_frontend_deploy_ssd_gluoncv.py:
diff --git a/docs/_sources/tutorials/frontend/from_caffe2.rst.txt b/docs/_sources/tutorials/frontend/from_caffe2.rst.txt
index 79f5b61..265e2a5 100644
--- a/docs/_sources/tutorials/frontend/from_caffe2.rst.txt
+++ b/docs/_sources/tutorials/frontend/from_caffe2.rst.txt
@@ -50,6 +50,22 @@ We load a pretrained resnet50 classification model provided by Caffe2.
+.. rst-class:: sphx-glr-script-out
+
+ Out:
+
+ .. code-block:: none
+
+ Downloading from https://s3.amazonaws.com/download.caffe2.ai/models/resnet50/predict_net.pb
+ Writing to /workspace/.caffe2/models/resnet50/predict_net.pb
+
+ Downloading from https://s3.amazonaws.com/download.caffe2.ai/models/resnet50/init_net.pb
+ Writing to /workspace/.caffe2/models/resnet50/init_net.pb
+
+ Downloading from https://s3.amazonaws.com/download.caffe2.ai/models/resnet50/value_info.json
+ Writing to /workspace/.caffe2/models/resnet50/value_info.json
+
+
Load a test image
diff --git a/docs/_sources/tutorials/frontend/from_darknet.rst.txt b/docs/_sources/tutorials/frontend/from_darknet.rst.txt
index 1d8dd29..e49e4b8 100644
--- a/docs/_sources/tutorials/frontend/from_darknet.rst.txt
+++ b/docs/_sources/tutorials/frontend/from_darknet.rst.txt
@@ -285,6 +285,11 @@ The process is no different from other examples.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 22.353 seconds)
+
+
.. _sphx_glr_download_tutorials_frontend_from_darknet.py:
diff --git a/docs/_sources/tutorials/frontend/from_mxnet.rst.txt b/docs/_sources/tutorials/frontend/from_mxnet.rst.txt
index 51b8664..c431922 100644
--- a/docs/_sources/tutorials/frontend/from_mxnet.rst.txt
+++ b/docs/_sources/tutorials/frontend/from_mxnet.rst.txt
@@ -98,6 +98,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipfaa14738-16e4-4da0-8285-ae245f11b665 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/tutorials/frontend/from_onnx.rst.txt b/docs/_sources/tutorials/frontend/from_onnx.rst.txt
index a917c9e..b23c784 100644
--- a/docs/_sources/tutorials/frontend/from_onnx.rst.txt
+++ b/docs/_sources/tutorials/frontend/from_onnx.rst.txt
@@ -128,7 +128,7 @@ provides a static definition of the input size.
.. code-block:: none
- ../../python/tvm/relay/frontend/onnx.py:4206: UserWarning: Mismatched attribute type in ' : kernel_shape'
+ ../../python/tvm/relay/frontend/onnx.py:4025: UserWarning: Mismatched attribute type in ' : kernel_shape'
==> Context: Bad node spec: input: "1" input: "2" output: "11" op_type: "Conv" attribute { name: "kernel_shape" ints: 5 ints: 5 } attribute { name: "strides" ints: 1 ints: 1 } attribute { name: "pads" ints: 2 ints: 2 ints: 2 ints: 2 } attribute { name: "dilations" ints: 1 ints: 1 } attribute { name: "group" i: 1 }
warnings.warn(str(e))
diff --git a/docs/_sources/tutorials/frontend/from_pytorch.rst.txt b/docs/_sources/tutorials/frontend/from_pytorch.rst.txt
index a672a16..cea6e6a 100644
--- a/docs/_sources/tutorials/frontend/from_pytorch.rst.txt
+++ b/docs/_sources/tutorials/frontend/from_pytorch.rst.txt
@@ -72,6 +72,15 @@ Load a pretrained PyTorch model
+.. rst-class:: sphx-glr-script-out
+
+ Out:
+
+ .. code-block:: none
+
+ Downloading: "https://download.pytorch.org/models/resnet18-5c106cde.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-5c106cde.pth
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
28%|##8 | 12.6M/44.7M [00:00<00:00, 132MB/s]
77%|#######7 | 34.5M/44.7M [00:00<00:00, 189MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 194MB/s]
+
Load a test image
diff --git a/docs/_sources/tutorials/frontend/from_tensorflow.rst.txt b/docs/_sources/tutorials/frontend/from_tensorflow.rst.txt
index 9279808..1453dbb 100644
--- a/docs/_sources/tutorials/frontend/from_tensorflow.rst.txt
+++ b/docs/_sources/tutorials/frontend/from_tensorflow.rst.txt
@@ -233,150 +233,6 @@ Results:
-.. rst-class:: sphx-glr-script-out
-
- Out:
-
- .. code-block:: none
-
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
- conv2d NHWC layout is not optimized for x86 with autotvm.
-
Execute the portable graph on TVM
@@ -522,6 +378,11 @@ Run the corresponding model on tensorflow
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 20.985 seconds)
+
+
.. _sphx_glr_download_tutorials_frontend_from_tensorflow.py:
diff --git a/docs/_sources/tutorials/frontend/sg_execution_times.rst.txt b/docs/_sources/tutorials/frontend/sg_execution_times.rst.txt
index 3cac5c2..466ae67 100644
--- a/docs/_sources/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**12:48.781** total execution time for **tutorials_frontend** files:
+**00:20.583** total execution time for **tutorials_frontend** files:
-- **02:44.102**: :ref:`sphx_glr_tutorials_frontend_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
-- **02:09.880**: :ref:`sphx_glr_tutorials_frontend_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
-- **01:42.237**: :ref:`sphx_glr_tutorials_frontend_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
-- **00:58.362**: :ref:`sphx_glr_tutorials_frontend_deploy_prequantized.py` (``deploy_prequantized.py``)
-- **00:51.534**: :ref:`sphx_glr_tutorials_frontend_from_tensorflow.py` (``from_tensorflow.py``)
-- **00:49.915**: :ref:`sphx_glr_tutorials_frontend_deploy_quantized.py` (``deploy_quantized.py``)
-- **00:44.022**: :ref:`sphx_glr_tutorials_frontend_from_darknet.py` (``from_darknet.py``)
-- **00:33.724**: :ref:`sphx_glr_tutorials_frontend_from_caffe2.py` (``from_caffe2.py``)
-- **00:25.786**: :ref:`sphx_glr_tutorials_frontend_deploy_model_on_android.py` (``deploy_model_on_android.py``)
-- **00:22.924**: :ref:`sphx_glr_tutorials_frontend_from_tflite.py` (``from_tflite.py``)
-- **00:20.266**: :ref:`sphx_glr_tutorials_frontend_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
-- **00:18.185**: :ref:`sphx_glr_tutorials_frontend_from_coreml.py` (``from_coreml.py``)
-- **00:16.801**: :ref:`sphx_glr_tutorials_frontend_from_pytorch.py` (``from_pytorch.py``)
-- **00:15.877**: :ref:`sphx_glr_tutorials_frontend_from_mxnet.py` (``from_mxnet.py``)
-- **00:10.187**: :ref:`sphx_glr_tutorials_frontend_from_keras.py` (``from_keras.py``)
-- **00:02.287**: :ref:`sphx_glr_tutorials_frontend_using_external_lib.py` (``using_external_lib.py``)
-- **00:01.525**: :ref:`sphx_glr_tutorials_frontend_from_onnx.py` (``from_onnx.py``)
-- **00:01.027**: :ref:`sphx_glr_tutorials_frontend_build_gcn.py` (``build_gcn.py``)
-- **00:00.141**: :ref:`sphx_glr_tutorials_frontend_deploy_sparse.py` (``deploy_sparse.py``)
+- **00:18.527**: :ref:`sphx_glr_tutorials_frontend_from_keras.py` (``from_keras.py``)
+- **00:02.056**: :ref:`sphx_glr_tutorials_frontend_from_onnx.py` (``from_onnx.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_frontend_build_gcn.py` (``build_gcn.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_frontend_deploy_model_on_android.py` (``deploy_model_on_android.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_frontend_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_frontend_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_frontend_deploy_prequantized.py` (``deploy_prequantized.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_frontend_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_frontend_deploy_quantized.py` (``deploy_quantized.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_frontend_deploy_sparse.py` (``deploy_sparse.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_frontend_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_frontend_from_caffe2.py` (``from_caffe2.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_frontend_from_coreml.py` (``from_coreml.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_frontend_from_darknet.py` (``from_darknet.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_frontend_from_mxnet.py` (``from_mxnet.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_frontend_from_pytorch.py` (``from_pytorch.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_frontend_from_tensorflow.py` (``from_tensorflow.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_frontend_from_tflite.py` (``from_tflite.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_frontend_using_external_lib.py` (``using_external_lib.py``)
diff --git a/docs/_sources/tutorials/get_started/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorials/get_started/auto_scheduler_matmul_x86.rst.txt
index 13c6c0b..fa63d5b 100644
--- a/docs/_sources/tutorials/get_started/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorials/get_started/auto_scheduler_matmul_x86.rst.txt
@@ -186,6 +186,7 @@ trials, we can load the best schedule from the log file and apply it.
+
Inspecting the Optimized Schedule
---------------------------------
We can lower the schedule to see the IR after auto-scheduling. The
@@ -297,7 +298,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 21.160 ms
+ Execution time of this operator: 45.432 ms
diff --git a/docs/_sources/tutorials/get_started/autotvm_relay_x86.rst.txt b/docs/_sources/tutorials/get_started/autotvm_relay_x86.rst.txt
index e702ac7..48485c9 100644
--- a/docs/_sources/tutorials/get_started/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorials/get_started/autotvm_relay_x86.rst.txt
@@ -207,14 +207,6 @@ runtime module from the library.
-.. rst-class:: sphx-glr-script-out
-
- Out:
-
- .. code-block:: none
-
- One or more operators have not been tuned. Please tune your model for better performance. Use DEBUG logging level to see more details.
-
Execute on the TVM Runtime
@@ -280,7 +272,7 @@ standard deviation.
.. code-block:: none
- {'mean': 100.97112998832017, 'median': 100.64726648852229, 'std': 0.9355632830933527}
+ {'mean': 226.42689668997264, 'median': 226.24714619996666, 'std': 0.646916386317958}
@@ -324,8 +316,8 @@ for the model.
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.610551
- class='n02123159 tiger cat' with probability=0.367180
+ class='n02123045 tabby, tabby cat' with probability=0.610552
+ class='n02123159 tiger cat' with probability=0.367179
class='n02124075 Egyptian cat' with probability=0.019365
class='n02129604 tiger, Panthera tigris' with probability=0.001273
class='n04040759 radiator' with probability=0.000261
@@ -474,31 +466,32 @@ In the simplest form, tuning requires you to provide three things:
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 1/25] Current/Best: 13.44/ 26.27 GFLOPS | Progress: (10/10) | 95.13 s
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 1.81/ 1.81 GFLOPS | Progress: (10/10) | 36.88 s
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 42.58/ 74.66 GFLOPS | Progress: (10/10) | 37.79 s
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 53.23/ 96.78 GFLOPS | Progress: (10/10) | 9.82 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 6.82/ 60.22 GFLOPS | Progress: (10/10) | 16.41 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 69.75/ 69.75 GFLOPS | Progress: (10/10) | 14.71 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 64.33/ 90.56 GFLOPS | Progress: (10/10) | 15.68 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 41.50/ 65.29 GFLOPS | Progress: (10/10) | 33.51 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
-
[Task 9/25] Current/Best: 60.73/ 82.22 GFLOPS | Progress: (10/10) | 11.42 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 27.21/ 55.24 GFLOPS | Progress: (10/10) | 11.12 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 85.07/ 85.07 GFLOPS | Progress: (10/10) | 10.00 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 50.72/ 68.54 GFLOPS | Progress: (10/10) | 11.57 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 22.31/ 65.46 GFLOPS | Progress: (10/10) | 19.41 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 87.35/ 87.71 GFLOPS | Progress: (10/10) | 5.70 s Done.
-
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 15/25] Current/Best: 38.18/ 51.59 GFLOPS | Progress: (10/10) | 5.07 s Done.
-
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 16/25] Current/Best: 30.83/ 61.08 GFLOPS | Progress: (10/10) | 5.07 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 54.49/ 68.61 GFLOPS | Progress: (10/10) | 6.46 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 45.63/ 61.39 GFLOPS | Progress: (10/10) | 10.53 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 99.57/ 99.57 GFLOPS | Progress: (10/10) | 5.14 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 34.33/ 46.20 GFLOPS | Progress: (10/10) | 5.47 s Done.
-
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 21/25] Current/Best: 29.78/ 40.29 GFLOPS | Progress: (10/10) | 4.88 s Done.
-
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 22/25] Current/Best: 59.79/ 102.15 GFLOPS | Progress: (10/10) | 6.66 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 60.67/ 60.67 GFLOPS | Progress: (10/10) | 19.24 s
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 62.59/ 76.12 GFLOPS | Progress: (10/10) | 13.95 s Done.
- Done.
- Done.
- Done.
- Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 25/25] Current/Best: 11.04/ 47.06 GFLOPS | Progress: (10/10) | 36.98 s
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 1/25] Current/Best: 12.05/ 14.13 GFLOPS | Progress: (4/10) | 11.61 s
[Task 1/25] Current/Best: 14.75/ 14.75 GFLOPS | Progress: (8/10) | 22.10 s
[Task 1/25] Current/Best: 9.32/ 14.75 GFLOPS | Progress: (10/10) | 32.45 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 6.24/ 12.89 GFLOPS | Progress: (4/10) | 3.57 s
[Task 2/25] Current/Best: 19.53/ 19.53 GFLOPS | Progress: (8/10) | 12.75 s
[Task 2/25] Current/Best: 19.58/ 19.58 GFLOPS | Progress: (10/10) | 13.84 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 27.76/ 39.82 GFLOPS | Progress: (4/10) | 3.83 s
[Task 3/25] Current/Best: 23.57/ 46.16 GFLOPS | Progress: (8/10) | 6.40 s
[Task 3/25] Current/Best: 15.99/ 46.16 GFLOPS | Progress: (10/10) | 8.16 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 33.28/ 45.79 GFLOPS | Progress: (4/10) | 3.06 s
[Task 4/25] Current/Best: 28.97/ 45.79 GFLOPS | Progress: (8/10) | 5.45 s
[Task 4/25] Current/Best: 45.86/ 45.86 GFLOPS | Progress: (10/10) | 6.87 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 20.78/ 38.54 GFLOPS | Progress: (4/10) | 2.22 s
[Task 5/25] Current/Best: 47.72/ 47.72 GFLOPS | Progress: (8/10) | 3.87 s
[Task 5/25] Current/Best: 19.84/ 47.72 GFLOPS | Progress: (10/10) | 4.61 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 24.75/ 24.75 GFLOPS | Progress: (4/10) | 3.88 s
[Task 6/25] Current/Best: 36.38/ 46.07 GFLOPS | Progress: (8/10) | 6.43 s
[Task 6/25] Current/Best: 23.05/ 46.65 GFLOPS | Progress: (10/10) | 7.39 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 47.84/ 47.84 GFLOPS | Progress: (4/10) | 2.21 s
[Task 7/25] Current/Best: 34.60/ 47.84 GFLOPS | Progress: (8/10) | 3.98 s
[Task 7/25] Current/Best: 10.16/ 47.84 GFLOPS | Progress: (10/10) | 4.97 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 30.68/ 30.68 GFLOPS | Progress: (4/10) | 2.32 s
[Task 8/25] Current/Best: 37.35/ 45.33 GFLOPS | Progress: (8/10) | 5.31 s
[Task 8/25] Current/Best: 46.41/ 46.41 GFLOPS | Progress: (10/10) | 5.93 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 9/25] Current/Best: 8.46/ 42.93 GFLOPS | Progress: (4/10) | 3.18 s
[Task 9/25] Current/Best: 41.72/ 42.93 GFLOPS | Progress: (8/10) | 4.84 s
[Task 9/25] Current/Best: 43.40/ 43.40 GFLOPS | Progress: (10/10) | 6.23 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 33.50/ 36.81 GFLOPS | Progress: (4/10) | 2.17 s
[Task 10/25] Current/Best: 15.28/ 36.81 GFLOPS | Progress: (8/10) | 3.77 s
[Task 10/25] Current/Best: 16.60/ 36.81 GFLOPS | Progress: (10/10) | 5.26 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 46.46/ 46.46 GFLOPS | Progress: (4/10) | 3.53 s
[Task 11/25] Current/Best: 38.92/ 46.46 GFLOPS | Progress: (8/10) | 5.45 s
[Task 11/25] Current/Best: 27.07/ 46.46 GFLOPS | Progress: (10/10) | 6.57 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 34.53/ 39.45 GFLOPS | Progress: (4/10) | 2.36 s
[Task 12/25] Current/Best: 31.65/ 44.32 GFLOPS | Progress: (8/10) | 3.91 s
[Task 12/25] Current/Best: 17.73/ 44.32 GFLOPS | Progress: (10/10) | 7.64 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 25.99/ 35.90 GFLOPS | Progress: (4/10) | 2.10 s
[Task 13/25] Current/Best: 28.48/ 35.90 GFLOPS | Progress: (8/10) | 7.06 s
[Task 13/25] Current/Best: 35.65/ 38.45 GFLOPS | Progress: (10/10) | 7.77 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 29.02/ 47.75 GFLOPS | Progress: (4/10) | 2.58 s
[Task 14/25] Current/Best: 38.29/ 47.75 GFLOPS | Progress: (8/10) | 4.64 s
[Task 14/25] Current/Best: 30.86/ 47.75 GFLOPS | Progress: (10/10) | 5.71 s Done.
+
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 15/25] Current/Best: 41.66/ 43.09 GFLOPS | Progress: (4/10) | 2.09 s
[Task 15/25] Current/Best: 22.98/ 43.09 GFLOPS | Progress: (8/10) | 5.28 s
[Task 15/25] Current/Best: 12.10/ 43.09 GFLOPS | Progress: (10/10) | 6.04 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 16/25] Current/Best: 14.11/ 47.00 GFLOPS | Progress: (4/10) | 4.16 s
[Task 16/25] Current/Best: 40.78/ 47.00 GFLOPS | Progress: (8/10) | 5.93 s
[Task 16/25] Current/Best: 13.65/ 47.00 GFLOPS | Progress: (10/10) | 6.82 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 25.74/ 27.83 GFLOPS | Progress: (4/10) | 4.52 s
[Task 17/25] Current/Best: 46.56/ 46.56 GFLOPS | Progress: (8/10) | 5.98 s
[Task 17/25] Current/Best: 12.30/ 46.56 GFLOPS | Progress: (10/10) | 6.94 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 20.07/ 34.05 GFLOPS | Progress: (4/10) | 2.56 s
[Task 18/25] Current/Best: 26.35/ 42.79 GFLOPS | Progress: (8/10) | 5.79 s
[Task 18/25] Current/Best: 33.49/ 42.79 GFLOPS | Progress: (10/10) | 6.79 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 44.44/ 44.44 GFLOPS | Progress: (4/10) | 2.58 s
[Task 19/25] Current/Best: 45.86/ 45.86 GFLOPS | Progress: (8/10) | 4.22 s
[Task 19/25] Current/Best: 32.42/ 45.86 GFLOPS | Progress: (10/10) | 5.20 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 35.55/ 38.18 GFLOPS | Progress: (4/10) | 2.58 s
[Task 20/25] Current/Best: 38.55/ 38.55 GFLOPS | Progress: (8/10) | 4.25 s
[Task 20/25] Current/Best: 8.66/ 38.55 GFLOPS | Progress: (10/10) | 5.12 s Done.
+
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 21/25] Current/Best: 22.51/ 35.86 GFLOPS | Progress: (4/10) | 2.60 s
[Task 21/25] Current/Best: 11.92/ 37.32 GFLOPS | Progress: (8/10) | 3.97 s
[Task 21/25] Current/Best: 13.60/ 37.32 GFLOPS | Progress: (10/10) | 4.85 s Done.
+
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 22/25] Current/Best: 40.97/ 48.00 GFLOPS | Progress: (4/10) | 2.28 s
[Task 22/25] Current/Best: 28.80/ 48.86 GFLOPS | Progress: (8/10) | 4.65 s
[Task 22/25] Current/Best: 30.62/ 48.86 GFLOPS | Progress: (10/10) | 5.65 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 26.07/ 27.08 GFLOPS | Progress: (4/10) | 10.41 s
[Task 23/25] Current/Best: 9.40/ 29.51 GFLOPS | Progress: (8/10) | 12.53 s
[Task 23/25] Current/Best: 17.33/ 31.99 GFLOPS | Progress: (10/10) | 13.42 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 32.87/ 34.13 GFLOPS | Progress: (4/10) | 4.51 s
[Task 24/25] Current/Best: 14.52/ 34.13 GFLOPS | Progress: (8/10) | 11.00 s
[Task 24/25] Current/Best: 25.00/ 34.13 GFLOPS | Progress: (10/10) | 11.98 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 25/25] Current/Best: 41.42/ 41.42 GFLOPS | Progress: (4/10) | 2.39 s
[Task 25/25] Current/Best: 47.79/ 47.79 GFLOPS | Progress: (8/10) | 4.58 s
[Task 25/25] Current/Best: 21.79/ 47.79 GFLOPS | Progress: (10/10) | 5.46 s Done.
+
The output from this tuning process will look something like this:
@@ -596,8 +589,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.610552
- class='n02123159 tiger cat' with probability=0.367179
+ class='n02123045 tabby, tabby cat' with probability=0.610551
+ class='n02123159 tiger cat' with probability=0.367181
class='n02124075 Egyptian cat' with probability=0.019365
class='n02129604 tiger, Panthera tigris' with probability=0.001273
class='n04040759 radiator' with probability=0.000261
@@ -640,8 +633,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 92.08956629503518, 'median': 92.06980434246361, 'std': 0.34333013824885233}
- unoptimized: {'mean': 100.97112998832017, 'median': 100.64726648852229, 'std': 0.9355632830933527}
+ optimized: {'mean': 198.39967233001516, 'median': 198.3304240500729, 'std': 1.0845790622211036}
+ unoptimized: {'mean': 226.42689668997264, 'median': 226.24714619996666, 'std': 0.646916386317958}
@@ -661,7 +654,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 9 minutes 11.362 seconds)
+ **Total running time of the script:** ( 6 minutes 17.556 seconds)
.. _sphx_glr_download_tutorials_get_started_autotvm_relay_x86.py:
diff --git a/docs/_sources/tutorials/get_started/cross_compilation_and_rpc.rst.txt b/docs/_sources/tutorials/get_started/cross_compilation_and_rpc.rst.txt
index c357f5c..4c18a7a 100644
--- a/docs/_sources/tutorials/get_started/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorials/get_started/cross_compilation_and_rpc.rst.txt
@@ -235,7 +235,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.633e-07 secs/op
+ 1.21e-07 secs/op
diff --git a/docs/_sources/tutorials/get_started/sg_execution_times.rst.txt b/docs/_sources/tutorials/get_started/sg_execution_times.rst.txt
index 079e525..108e552 100644
--- a/docs/_sources/tutorials/get_started/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorials/get_started/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**11:29.665** total execution time for **tutorials_get_started** files:
+**08:43.899** total execution time for **tutorials_get_started** files:
-- **09:11.362**: :ref:`sphx_glr_tutorials_get_started_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
-- **01:19.733**: :ref:`sphx_glr_tutorials_get_started_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
-- **00:21.677**: :ref:`sphx_glr_tutorials_get_started_relay_quick_start.py` (``relay_quick_start.py``)
-- **00:19.898**: :ref:`sphx_glr_tutorials_get_started_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
-- **00:16.614**: :ref:`sphx_glr_tutorials_get_started_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
-- **00:00.266**: :ref:`sphx_glr_tutorials_get_started_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
-- **00:00.039**: :ref:`sphx_glr_tutorials_get_started_install.py` (``install.py``)
-- **00:00.039**: :ref:`sphx_glr_tutorials_get_started_introduction.py` (``introduction.py``)
-- **00:00.037**: :ref:`sphx_glr_tutorials_get_started_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
+- **06:17.556**: :ref:`sphx_glr_tutorials_get_started_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
+- **00:59.564**: :ref:`sphx_glr_tutorials_get_started_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
+- **00:32.871**: :ref:`sphx_glr_tutorials_get_started_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
+- **00:30.148**: :ref:`sphx_glr_tutorials_get_started_relay_quick_start.py` (``relay_quick_start.py``)
+- **00:23.501**: :ref:`sphx_glr_tutorials_get_started_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
+- **00:00.163**: :ref:`sphx_glr_tutorials_get_started_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
+- **00:00.032**: :ref:`sphx_glr_tutorials_get_started_introduction.py` (``introduction.py``)
+- **00:00.031**: :ref:`sphx_glr_tutorials_get_started_install.py` (``install.py``)
+- **00:00.031**: :ref:`sphx_glr_tutorials_get_started_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
diff --git a/docs/_sources/tutorials/get_started/tensor_expr_get_started.rst.txt b/docs/_sources/tutorials/get_started/tensor_expr_get_started.rst.txt
index 0be35f3..e981902 100644
--- a/docs/_sources/tutorials/get_started/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorials/get_started/tensor_expr_get_started.rst.txt
@@ -233,8 +233,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000005
- naive: 0.000004
+ Numpy running time: 0.000007
+ naive: 0.000006
@@ -324,7 +324,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000006
+ parallel: 0.000005
@@ -377,7 +377,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000019
+ vector: 0.000016
primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {C: Buffer(C_2: Pointer(float32), float32, [n: int32], [stride: int32], type="auto"),
@@ -425,10 +425,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 5.340729840099811e-06 1.0
- naive 3.968499999999999e-06 0.7430632364519366
- parallel 6.4731e-06 1.2120253586687744
- vector 1.90829e-05 3.573088430109276
+ numpy 7.028010004432872e-06 1.0
+ naive 5.6814e-06 0.8083938407054763
+ parallel 5.0607e-06 0.7200758104794951
+ vector 1.61654e-05 2.3001390137185034
@@ -596,7 +596,7 @@ The following code first performs the following steps:
.. code-block:: none
- ['myadd.o', 'myadd.so']
+ ['myadd.so', 'myadd.o']
@@ -817,7 +817,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.013535
+ Numpy running time: 0.007486
@@ -873,7 +873,7 @@ optimizations.
.. code-block:: none
- none: 5.343914
+ none: 3.297487
@@ -969,7 +969,7 @@ schedule.
.. code-block:: none
- blocking: 0.132706
+ blocking: 0.292408
@@ -1057,11 +1057,11 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.134709
+ vectorization: 0.325112
primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
- C: Buffer(C_2: Pointer(float32), float32, [1024, 1024], []),
+ buffers = {C: Buffer(C_2: Pointer(float32), float32, [1024, 1024], []),
+ A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
B: Buffer(B_2: Pointer(float32), float32, [1024, 1024], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (x.outer: int32, 0, 32) {
@@ -1125,7 +1125,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.065923
+ loop permutation: 0.113007
primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {C: Buffer(C_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1218,7 +1218,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.063657
+ array packing: 0.214044
primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {C: Buffer(C_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1305,7 +1305,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.063360
+ block caching: 0.199362
primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {C: Buffer(C_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1382,11 +1382,11 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.017113
+ parallelization: 0.061192
primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(float32), float32, [1024, 1024], []),
- A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
+ buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
+ C: Buffer(C_2: Pointer(float32), float32, [1024, 1024], []),
B: Buffer(B_2: Pointer(float32), float32, [1024, 1024], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
allocate(packedB: Pointer(global float32x32), float32x32, [32768]), storage_scope = global {
@@ -1454,13 +1454,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 5.3439138899 1.0
- blocking 0.1327056972 0.024833053064499008
- vectorization 0.1347089976 0.025207928191844572
- loop permutation 0.0659230783 0.012336104147298228
- array packing 0.063657088 0.011912072183706391
- block caching 0.06336020049999999 0.01185651599284764
- parallelization 0.0171132963 0.0032023899809359093
+ none 3.2974874185 1.0
+ blocking 0.2924084278 0.08867613145678481
+ vectorization 0.3251120154 0.0985938607607761
+ loop permutation 0.1130071469 0.034270683268112674
+ array packing 0.2140441853 0.06491129703759929
+ block caching 0.1993615194 0.06045861411980396
+ parallelization 0.06119195110000001 0.01855714467830653
@@ -1495,11 +1495,6 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 19.733 seconds)
-
-
.. _sphx_glr_download_tutorials_get_started_tensor_expr_get_started.py:
diff --git a/docs/_sources/tutorials/language/reduction.rst.txt b/docs/_sources/tutorials/language/reduction.rst.txt
index 45a21b0..8eb5332 100644
--- a/docs/_sources/tutorials/language/reduction.rst.txt
+++ b/docs/_sources/tutorials/language/reduction.rst.txt
@@ -430,8 +430,8 @@ Here is an example for 2D convolution with filter size = [3, 3] and strides = [1
primfn(Input_1: handle, Filter_1: handle, Output_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {Input: Buffer(Input_2: Pointer(float32), float32, [n: int32, n], [stride: int32, stride_1: int32], type="auto"),
- Output: Buffer(Output_2: Pointer(float32), float32, [(n - 2), (n - 2)], []),
+ buffers = {Output: Buffer(Output_2: Pointer(float32), float32, [(n: int32 - 2), (n - 2)], []),
+ Input: Buffer(Input_2: Pointer(float32), float32, [n, n], [stride: int32, stride_1: int32], type="auto"),
Filter: Buffer(Filter_2: Pointer(float32), float32, [3, 3], [])}
buffer_map = {Input_1: Input, Filter_1: Filter, Output_1: Output} {
for (i: int32, 0, (n - 2)) {
diff --git a/docs/_sources/tutorials/language/schedule_primitives.rst.txt b/docs/_sources/tutorials/language/schedule_primitives.rst.txt
index 6ee9d56..124e339 100644
--- a/docs/_sources/tutorials/language/schedule_primitives.rst.txt
+++ b/docs/_sources/tutorials/language/schedule_primitives.rst.txt
@@ -85,13 +85,13 @@ schedule computes tensor in a serial manner in a row-major order.
primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {A: Buffer(A_2: Pointer(float32), float32, [m: int32, n: int32], [stride: int32, stride_1: int32], type="auto"),
- C: Buffer(C_2: Pointer(float32), float32, [m, n], [stride_2: int32, stride_3: int32], type="auto"),
+ buffers = {C: Buffer(C_2: Pointer(float32), float32, [m: int32, n: int32], [stride: int32, stride_1: int32], type="auto"),
+ A: Buffer(A_2: Pointer(float32), float32, [m, n], [stride_2: int32, stride_3: int32], type="auto"),
B: Buffer(B_2: Pointer(float32), float32, [m, n], [stride_4: int32, stride_5: int32], type="auto")}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (i: int32, 0, m) {
for (j: int32, 0, n) {
- C_2[((i*stride_2) + (j*stride_3))] = ((float32*)A_2[((i*stride) + (j*stride_1))]*(float32*)B_2[((i*stride_4) + (j*stride_5))])
+ C_2[((i*stride) + (j*stride_1))] = ((float32*)A_2[((i*stride_2) + (j*stride_3))]*(float32*)B_2[((i*stride_4) + (j*stride_5))])
}
}
}
diff --git a/docs/_sources/tutorials/language/sg_execution_times.rst.txt b/docs/_sources/tutorials/language/sg_execution_times.rst.txt
index bd20d86..045327b 100644
--- a/docs/_sources/tutorials/language/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorials/language/sg_execution_times.rst.txt
@@ -5,13 +5,13 @@
Computation times
=================
-**00:05.534** total execution time for **tutorials_language** files:
+**00:04.897** total execution time for **tutorials_language** files:
-- **00:02.250**: :ref:`sphx_glr_tutorials_language_intrin_math.py` (``intrin_math.py``)
-- **00:01.114**: :ref:`sphx_glr_tutorials_language_tensorize.py` (``tensorize.py``)
-- **00:00.732**: :ref:`sphx_glr_tutorials_language_scan.py` (``scan.py``)
-- **00:00.696**: :ref:`sphx_glr_tutorials_language_reduction.py` (``reduction.py``)
-- **00:00.256**: :ref:`sphx_glr_tutorials_language_extern_op.py` (``extern_op.py``)
-- **00:00.168**: :ref:`sphx_glr_tutorials_language_schedule_primitives.py` (``schedule_primitives.py``)
-- **00:00.167**: :ref:`sphx_glr_tutorials_language_tedd.py` (``tedd.py``)
-- **00:00.152**: :ref:`sphx_glr_tutorials_language_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:01.724**: :ref:`sphx_glr_tutorials_language_intrin_math.py` (``intrin_math.py``)
+- **00:01.047**: :ref:`sphx_glr_tutorials_language_tensorize.py` (``tensorize.py``)
+- **00:00.651**: :ref:`sphx_glr_tutorials_language_reduction.py` (``reduction.py``)
+- **00:00.639**: :ref:`sphx_glr_tutorials_language_scan.py` (``scan.py``)
+- **00:00.282**: :ref:`sphx_glr_tutorials_language_extern_op.py` (``extern_op.py``)
+- **00:00.190**: :ref:`sphx_glr_tutorials_language_schedule_primitives.py` (``schedule_primitives.py``)
+- **00:00.184**: :ref:`sphx_glr_tutorials_language_tedd.py` (``tedd.py``)
+- **00:00.179**: :ref:`sphx_glr_tutorials_language_tuple_inputs.py` (``tuple_inputs.py``)
diff --git a/docs/_sources/tutorials/language/tensorize.rst.txt b/docs/_sources/tutorials/language/tensorize.rst.txt
index 130d7e5..eff455c 100644
--- a/docs/_sources/tutorials/language/tensorize.rst.txt
+++ b/docs/_sources/tutorials/language/tensorize.rst.txt
@@ -313,8 +313,8 @@ The importing needs to happen before the tensorized GEMV being executed.
A: Buffer(A_2: Pointer(float32), float32, [1024, 64], []),
B: Buffer(B_2: Pointer(float32), float32, [512, 64], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpc1vp5jds/input0.cc'
- source_filename = "/tmp/tmpc1vp5jds/input0.cc"
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp75lkgvp8/input0.cc'
+ source_filename = "/tmp/tmp75lkgvp8/input0.cc"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-pc-linux-gnu"
diff --git a/docs/_sources/tutorials/language/tuple_inputs.rst.txt b/docs/_sources/tutorials/language/tuple_inputs.rst.txt
index 3ce3cb7..fbfbb2d 100644
--- a/docs/_sources/tutorials/language/tuple_inputs.rst.txt
+++ b/docs/_sources/tutorials/language/tuple_inputs.rst.txt
@@ -65,14 +65,14 @@ together in the next schedule procedure.
primfn(A0_1: handle, A1_1: handle, B_2: handle, B_3: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {B: Buffer(B_4: Pointer(float32), float32, [m: int32, n: int32], [stride: int32, stride_1: int32], type="auto"),
- B_1: Buffer(B_5: Pointer(float32), float32, [m, n], [stride_2: int32, stride_3: int32], type="auto"),
- A0: Buffer(A0_2: Pointer(float32), float32, [m, n], [stride_4: int32, stride_5: int32], type="auto"),
+ A0: Buffer(A0_2: Pointer(float32), float32, [m, n], [stride_2: int32, stride_3: int32], type="auto"),
+ B_1: Buffer(B_5: Pointer(float32), float32, [m, n], [stride_4: int32, stride_5: int32], type="auto"),
A1: Buffer(A1_2: Pointer(float32), float32, [m, n], [stride_6: int32, stride_7: int32], type="auto")}
buffer_map = {A0_1: A0, A1_1: A1, B_2: B, B_3: B_1} {
for (i: int32, 0, m) {
for (j: int32, 0, n) {
- B_4[((i*stride) + (j*stride_1))] = ((float32*)A0_2[((i*stride_4) + (j*stride_5))] + 2f32)
- B_5[((i*stride_2) + (j*stride_3))] = ((float32*)A1_2[((i*stride_6) + (j*stride_7))]*3f32)
+ B_4[((i*stride) + (j*stride_1))] = ((float32*)A0_2[((i*stride_2) + (j*stride_3))] + 2f32)
+ B_5[((i*stride_4) + (j*stride_5))] = ((float32*)A1_2[((i*stride_6) + (j*stride_7))]*3f32)
}
}
}
@@ -136,15 +136,15 @@ with :py:func:`te.comm_reducer` as below:
primfn(idx_1: handle, val_1: handle, T_2: handle, T_3: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {T_1: Buffer(T_4: Pointer(int32), int32, [m: int32], [stride: int32], type="auto"),
- idx: Buffer(idx_2: Pointer(int32), int32, [m, n: int32], [stride_1: int32, stride_2: int32], type="auto"),
- T: Buffer(T_5: Pointer(int32), int32, [m], [stride_3: int32], type="auto"),
+ T: Buffer(T_5: Pointer(int32), int32, [m], [stride_1: int32], type="auto"),
+ idx: Buffer(idx_2: Pointer(int32), int32, [m, n: int32], [stride_2: int32, stride_3: int32], type="auto"),
val: Buffer(val_2: Pointer(int32), int32, [m, n], [stride_4: int32, stride_5: int32], type="auto")}
buffer_map = {idx_1: idx, val_1: val, T_2: T, T_3: T_1} {
for (i: int32, 0, m) {
- T_5[(i*stride_3)] = -1
+ T_5[(i*stride_1)] = -1
T_4[(i*stride)] = -2147483648
for (k: int32, 0, n) {
- T_5[(i*stride_3)] = @tir.if_then_else(((int32*)val_2[((i*stride_4) + (k*stride_5))] <= (int32*)T_4[(i*stride)]), (int32*)T_5[(i*stride_3)], (int32*)idx_2[((i*stride_1) + (k*stride_2))], dtype=int32)
+ T_5[(i*stride_1)] = @tir.if_then_else(((int32*)val_2[((i*stride_4) + (k*stride_5))] <= (int32*)T_4[(i*stride)]), (int32*)T_5[(i*stride_1)], (int32*)idx_2[((i*stride_2) + (k*stride_3))], dtype=int32)
T_4[(i*stride)] = @tir.if_then_else(((int32*)val_2[((i*stride_4) + (k*stride_5))] <= (int32*)T_4[(i*stride)]), (int32*)T_4[(i*stride)], (int32*)val_2[((i*stride_4) + (k*stride_5))], dtype=int32)
}
}
diff --git a/docs/_sources/tutorials/micro/micro_autotune.rst.txt b/docs/_sources/tutorials/micro/micro_autotune.rst.txt
index 911708c..15a10b8 100644
--- a/docs/_sources/tutorials/micro/micro_autotune.rst.txt
+++ b/docs/_sources/tutorials/micro/micro_autotune.rst.txt
@@ -208,7 +208,7 @@ Configuring microTVM
.. code-block:: none
-
Current/Best: 0.00/ 0.00 MFLOPS | Progress: (0/10) | 0.00 s
Current/Best: 248.33/ 248.33 MFLOPS | Progress: (1/10) | 5.04 s
Current/Best: 226.79/ 248.33 MFLOPS | Progress: (2/10) | 7.76 s
Current/Best: 167.17/ 248.33 MFLOPS | Progress: (3/10) | 11.54 s
Current/Best: 163.68/ 248.33 MFLOPS | Progress: (4/10) | 14.28 s
Current/Best: 186.74/ 248.33 MFLOPS | Progress: (5/10) | 17.99 s
Current/Best: 214.88/ 248.33 MFLOPS | Progress: (6/10) | 20.68 s
Current/Best: 237.07/ 248.33 MFLOPS | Progress: (7/10) | 24.46 s
Current/Best: 152.29/ 248.33 MFLOPS | Progress: (8/10) | 27.18 s
Current/Best: 203.71/ 248.33 MFLOPS | Progress: (9/10) | 31.03 s
Current/Best: 60.25/ 248.33 MFLOPS | Progress: (10/10) | 33.72 s Done.
+
Current/Best: 0.00/ 0.00 MFLOPS | Progress: (0/10) | 0.00 s
Current/Best: 221.97/ 221.97 MFLOPS | Progress: (1/10) | 5.48 s
Current/Best: 112.44/ 221.97 MFLOPS | Progress: (2/10) | 8.18 s
Current/Best: 114.36/ 221.97 MFLOPS | Progress: (3/10) | 12.06 s
Current/Best: 260.71/ 260.71 MFLOPS | Progress: (4/10) | 15.88 s
Current/Best: 265.12/ 265.12 MFLOPS | Progress: (5/10) | 19.71 s
Current/Best: 158.71/ 265.12 MFLOPS | Progress: (6/10) | 22.32 s
Current/Best: 247.02/ 265.12 MFLOPS | Progress: (7/10) | 24.95 s
Current/Best: 113.80/ 265.12 MFLOPS | Progress: (8/10) | 27.56 s
Current/Best: 281.78/ 281.78 MFLOPS | Progress: (9/10) | 30.17 s
Current/Best: 220.41/ 281.78 MFLOPS | Progress: (10/10) | 32.78 s Done.
@@ -269,10 +269,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 501.4 98.275 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 5.4 1.058 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.403 0.667 (1, 1, 10, 10, 3) 1 1
- Total_time - 510.203 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 295.7 98.681 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 3.024 1.009 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 0.93 0.31 (1, 1, 10, 10, 3) 1 1
+ Total_time - 299.653 - - - -
@@ -331,10 +331,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 347.0 97.334 (1, 6, 10, 10, 1) 2 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 6.1 1.711 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.403 0.955 (1, 1, 10, 10, 3) 1 1
- Total_time - 356.503 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 219.0 98.818 (1, 1, 10, 10, 6) 2 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.802 0.813 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 0.817 0.369 (1, 3, 10, 10, 1) 1 1
+ Total_time - 221.619 - - - -
diff --git a/docs/_sources/tutorials/micro/micro_tflite.rst.txt b/docs/_sources/tutorials/micro/micro_tflite.rst.txt
index f8ead0c..0835909 100644
--- a/docs/_sources/tutorials/micro/micro_tflite.rst.txt
+++ b/docs/_sources/tutorials/micro/micro_tflite.rst.txt
@@ -360,22 +360,22 @@ Now, compile the model for the target:
#ifdef __cplusplus
extern "C"
#endif
- TVM_DLL int32_t tvmgen_default_fused_nn_dense_add_nn_relu(void* args, void* arg_type_ids, int32_t num_args, void* out_ret_value, void* out_ret_tcode, void* resource_handle) {
+ TVM_DLL int32_t tvmgen_default_fused_reshape(void* args, void* arg_type_ids, int32_t num_args, void* out_ret_value, void* out_ret_tcode, void* resource_handle) {
void* arg0 = (((TVMValue*)args)[0].v_handle);
- .
- - ./src
- - ./src/relay.txt
- ./codegen
- ./codegen/host
- ./codegen/host/src
- - ./codegen/host/src/default_lib0.c
- ./codegen/host/src/default_lib1.c
+ - ./codegen/host/src/default_lib0.c
- ./parameters
- ./parameters/default.params
- - ./metadata.json
- ./executor-config
- ./executor-config/graph
- ./executor-config/graph/graph.json
+ - ./metadata.json
+ - ./src
+ - ./src/relay.txt
diff --git a/docs/_sources/tutorials/micro/sg_execution_times.rst.txt b/docs/_sources/tutorials/micro/sg_execution_times.rst.txt
index fa49db0..72ebeb7 100644
--- a/docs/_sources/tutorials/micro/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorials/micro/sg_execution_times.rst.txt
@@ -5,8 +5,8 @@
Computation times
=================
-**00:40.442** total execution time for **tutorials_micro** files:
+**00:39.703** total execution time for **tutorials_micro** files:
-- **00:40.442**: :ref:`sphx_glr_tutorials_micro_micro_autotune.py` (``micro_autotune.py``)
+- **00:39.703**: :ref:`sphx_glr_tutorials_micro_micro_autotune.py` (``micro_autotune.py``)
- **00:00.000**: :ref:`sphx_glr_tutorials_micro_micro_reference_vm.py` (``micro_reference_vm.py``)
- **00:00.000**: :ref:`sphx_glr_tutorials_micro_micro_tflite.py` (``micro_tflite.py``)
diff --git a/docs/_sources/tutorials/optimize/opt_conv_cuda.rst.txt b/docs/_sources/tutorials/optimize/opt_conv_cuda.rst.txt
index af29a46..4f3fb05 100644
--- a/docs/_sources/tutorials/optimize/opt_conv_cuda.rst.txt
+++ b/docs/_sources/tutorials/optimize/opt_conv_cuda.rst.txt
@@ -296,7 +296,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 14.026541 ms
+ Convolution: 54.178334 ms
diff --git a/docs/_sources/tutorials/optimize/opt_conv_tensorcore.rst.txt b/docs/_sources/tutorials/optimize/opt_conv_tensorcore.rst.txt
index bff795f..64d4dd6 100644
--- a/docs/_sources/tutorials/optimize/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/tutorials/optimize/opt_conv_tensorcore.rst.txt
@@ -405,8 +405,8 @@ one time.
primfn(A_1: handle, W_1: handle, Conv_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {A: Buffer(A_2: Pointer(float16), float16, [16, 14, 14, 16, 16, 16], []),
- Conv: Buffer(Conv_2: Pointer(float32), float32, [16, 14, 14, 32, 16, 16], []),
+ buffers = {Conv: Buffer(Conv_2: Pointer(float32), float32, [16, 14, 14, 32, 16, 16], []),
+ A: Buffer(A_2: Pointer(float16), float16, [16, 14, 14, 16, 16, 16], []),
W: Buffer(W_2: Pointer(float16), float16, [3, 3, 16, 32, 16, 16], [])}
buffer_map = {A_1: A, W_1: W, Conv_1: Conv} {
attr [IterVar(blockIdx.z: int32, (nullptr), "ThreadIndex", "blockIdx.z")] "thread_extent" = 196;
@@ -614,7 +614,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 4.535341 ms
+ conv2d with tensor core: 6.580490 ms
diff --git a/docs/_sources/tutorials/optimize/opt_gemm.rst.txt b/docs/_sources/tutorials/optimize/opt_gemm.rst.txt
index 8cc24be..dc1dcbf 100644
--- a/docs/_sources/tutorials/optimize/opt_gemm.rst.txt
+++ b/docs/_sources/tutorials/optimize/opt_gemm.rst.txt
@@ -118,8 +118,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.014014
- Baseline: 6.117077
+ Numpy running time: 0.009345
+ Baseline: 3.291115
@@ -207,7 +207,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.130019
+ Opt1: 0.310688
@@ -302,7 +302,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.131317
+ Opt2: 0.341067
@@ -390,7 +390,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.065470
+ Opt3: 0.111449
@@ -505,7 +505,7 @@ flattening.
.. code-block:: none
- Opt4: 0.064565
+ Opt4: 0.217310
@@ -619,7 +619,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.064228
+ Opt5: 0.215912
@@ -733,7 +733,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.018096
+ Opt6: 0.066558
diff --git a/docs/_sources/tutorials/optimize/sg_execution_times.rst.txt b/docs/_sources/tutorials/optimize/sg_execution_times.rst.txt
index f3c75f9..4b8d0d5 100644
--- a/docs/_sources/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,8 +5,8 @@
Computation times
=================
-**00:29.154** total execution time for **tutorials_optimize** files:
+**00:29.655** total execution time for **tutorials_optimize** files:
-- **00:27.061**: :ref:`sphx_glr_tutorials_optimize_opt_gemm.py` (``opt_gemm.py``)
-- **00:01.137**: :ref:`sphx_glr_tutorials_optimize_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
-- **00:00.956**: :ref:`sphx_glr_tutorials_optimize_opt_conv_cuda.py` (``opt_conv_cuda.py``)
+- **00:29.655**: :ref:`sphx_glr_tutorials_optimize_opt_gemm.py` (``opt_gemm.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_optimize_opt_conv_cuda.py` (``opt_conv_cuda.py``)
+- **00:00.000**: :ref:`sphx_glr_tutorials_optimize_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
diff --git a/docs/_sources/tutorials/topi/intro_topi.rst.txt b/docs/_sources/tutorials/topi/intro_topi.rst.txt
index ec4c9dc..c85f172 100644
--- a/docs/_sources/tutorials/topi/intro_topi.rst.txt
+++ b/docs/_sources/tutorials/topi/intro_topi.rst.txt
@@ -226,7 +226,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0xba784780)), stage(b, placeholder(b, 0xda4d2800)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+ [stage(a, placeholder(a, 0xd9c0fa00)), stage(b, placeholder(b, 0xe225cf70)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
diff --git a/docs/_sources/tutorials/topi/sg_execution_times.rst.txt b/docs/_sources/tutorials/topi/sg_execution_times.rst.txt
index e22d80d..d92fd6f 100644
--- a/docs/_sources/tutorials/topi/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorials/topi/sg_execution_times.rst.txt
@@ -5,6 +5,6 @@
Computation times
=================
-**00:00.782** total execution time for **tutorials_topi** files:
+**00:00.704** total execution time for **tutorials_topi** files:
-- **00:00.782**: :ref:`sphx_glr_tutorials_topi_intro_topi.py` (``intro_topi.py``)
+- **00:00.704**: :ref:`sphx_glr_tutorials_topi_intro_topi.py` (``intro_topi.py``)
diff --git a/docs/_sources/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/vta/tutorials/autotvm/sg_execution_times.rst.txt
index 74f5326..3a06795 100644
--- a/docs/_sources/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:19.286** total execution time for **vta_tutorials_autotvm** files:
+**00:17.724** total execution time for **vta_tutorials_autotvm** files:
-- **00:19.146**: :ref:`sphx_glr_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
-- **00:00.140**: :ref:`sphx_glr_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
+- **00:17.550**: :ref:`sphx_glr_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
+- **00:00.173**: :ref:`sphx_glr_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
diff --git a/docs/_sources/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/vta/tutorials/frontend/deploy_classification.rst.txt
index 86bd39c..db7d470 100644
--- a/docs/_sources/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -259,7 +259,7 @@ The compilation steps are:
.. code-block:: none
- resnet18_v1 inference graph built in 18.95s!
+ resnet18_v1 inference graph built in 32.45s!
diff --git a/docs/_sources/vta/tutorials/frontend/deploy_detection.rst.txt b/docs/_sources/vta/tutorials/frontend/deploy_detection.rst.txt
index 8764f7c..1fd9ca3 100644
--- a/docs/_sources/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -297,7 +297,7 @@ The compilation steps are:
.. code-block:: none
- yolov3-tiny inference graph built in 13.16s!
+ yolov3-tiny inference graph built in 13.01s!
diff --git a/docs/_sources/vta/tutorials/frontend/sg_execution_times.rst.txt b/docs/_sources/vta/tutorials/frontend/sg_execution_times.rst.txt
index 2f76a01..30e6515 100644
--- a/docs/_sources/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**01:16.053** total execution time for **vta_tutorials_frontend** files:
+**00:54.952** total execution time for **vta_tutorials_frontend** files:
-- **00:39.493**: :ref:`sphx_glr_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
-- **00:36.559**: :ref:`sphx_glr_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
+- **00:54.952**: :ref:`sphx_glr_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
+- **00:00.000**: :ref:`sphx_glr_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
diff --git a/docs/_sources/vta/tutorials/matrix_multiply.rst.txt b/docs/_sources/vta/tutorials/matrix_multiply.rst.txt
index b0d76e6..d634e88 100644
--- a/docs/_sources/vta/tutorials/matrix_multiply.rst.txt
+++ b/docs/_sources/vta/tutorials/matrix_multiply.rst.txt
@@ -529,8 +529,8 @@ by the VTA runtime JIT compiler.
primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(int8), int8, [1, 16, 1, 16], []),
- A: Buffer(A_2: Pointer(int8), int8, [1, 16, 1, 16], []),
+ buffers = {A: Buffer(A_2: Pointer(int8), int8, [1, 16, 1, 16], []),
+ C: Buffer(C_2: Pointer(int8), int8, [1, 16, 1, 16], []),
B: Buffer(B_2: Pointer(int8), int8, [16, 16, 16, 16], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
attr [IterVar(vta: int32, (nullptr), "ThreadIndex", "vta")] "coproc_scope" = 2 {
diff --git a/docs/_sources/vta/tutorials/optimize/convolution_opt.rst.txt b/docs/_sources/vta/tutorials/optimize/convolution_opt.rst.txt
index 8396b54..7b1f915 100644
--- a/docs/_sources/vta/tutorials/optimize/convolution_opt.rst.txt
+++ b/docs/_sources/vta/tutorials/optimize/convolution_opt.rst.txt
@@ -445,8 +445,8 @@ below.
primfn(data_1: handle, kernel_1: handle, res_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {data: Buffer(data_2: Pointer(int8), int8, [1, 16, 14, 14, 1, 16], []),
- res: Buffer(res_2: Pointer(int8), int8, [1, 16, 14, 14, 1, 16], []),
+ buffers = {res: Buffer(res_2: Pointer(int8), int8, [1, 16, 14, 14, 1, 16], []),
+ data: Buffer(data_2: Pointer(int8), int8, [1, 16, 14, 14, 1, 16], []),
kernel: Buffer(kernel_2: Pointer(int8), int8, [16, 16, 3, 3, 16, 16], [])}
buffer_map = {data_1: data, kernel_1: kernel, res_1: res} {
allocate(data_buf: Pointer(global int8), int8, [65536]), storage_scope = global;
diff --git a/docs/_sources/vta/tutorials/optimize/matrix_multiply_opt.rst.txt b/docs/_sources/vta/tutorials/optimize/matrix_multiply_opt.rst.txt
index a8900fb..ce51043 100644
--- a/docs/_sources/vta/tutorials/optimize/matrix_multiply_opt.rst.txt
+++ b/docs/_sources/vta/tutorials/optimize/matrix_multiply_opt.rst.txt
@@ -348,8 +348,8 @@ below:
primfn(data_1: handle, weight_1: handle, res_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {data: Buffer(data_2: Pointer(int8), int8, [1, 64, 1, 16], []),
- res: Buffer(res_2: Pointer(int8), int8, [1, 64, 1, 16], []),
+ buffers = {res: Buffer(res_2: Pointer(int8), int8, [1, 64, 1, 16], []),
+ data: Buffer(data_2: Pointer(int8), int8, [1, 64, 1, 16], []),
weight: Buffer(weight_2: Pointer(int8), int8, [64, 64, 16, 16], [])}
buffer_map = {data_1: data, weight_1: weight, res_1: res} {
allocate(data_buf: Pointer(global int8), int8, [1024]), storage_scope = global;
diff --git a/docs/_sources/vta/tutorials/optimize/sg_execution_times.rst.txt b/docs/_sources/vta/tutorials/optimize/sg_execution_times.rst.txt
index 83c7e2c..8e0a369 100644
--- a/docs/_sources/vta/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/vta/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:03.801** total execution time for **vta_tutorials_optimize** files:
+**00:03.387** total execution time for **vta_tutorials_optimize** files:
-- **00:03.254**: :ref:`sphx_glr_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
-- **00:00.547**: :ref:`sphx_glr_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
+- **00:02.915**: :ref:`sphx_glr_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
+- **00:00.472**: :ref:`sphx_glr_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
diff --git a/docs/_sources/vta/tutorials/sg_execution_times.rst.txt b/docs/_sources/vta/tutorials/sg_execution_times.rst.txt
index 7feb567..2609365 100644
--- a/docs/_sources/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/vta/tutorials/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:01.133** total execution time for **vta_tutorials** files:
+**00:00.856** total execution time for **vta_tutorials** files:
-- **00:00.576**: :ref:`sphx_glr_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
-- **00:00.557**: :ref:`sphx_glr_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
+- **00:00.436**: :ref:`sphx_glr_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
+- **00:00.420**: :ref:`sphx_glr_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
diff --git a/docs/_static/documentation_options.js b/docs/_static/documentation_options.js
index 992760b..864266b 100644
--- a/docs/_static/documentation_options.js
+++ b/docs/_static/documentation_options.js
@@ -1,6 +1,6 @@
var DOCUMENTATION_OPTIONS = {
URL_ROOT: document.getElementById("documentation_options").getAttribute('data-url_root'),
- VERSION: '0.8.dev1706+gdc2f70e3c',
+ VERSION: '0.8.dev0',
LANGUAGE: 'None',
COLLAPSE_INDEX: false,
BUILDER: 'html',
diff --git a/docs/api/javadoc/org/apache/tvm/class-use/Function.html b/docs/api/javadoc/org/apache/tvm/class-use/Function.html
index df56f50..5e836f7 100644
--- a/docs/api/javadoc/org/apache/tvm/class-use/Function.html
+++ b/docs/api/javadoc/org/apache/tvm/class-use/Function.html
@@ -112,14 +112,14 @@
<tbody>
<tr class="altColor">
<td class="colFirst"><code><a href="../../../../org/apache/tvm/Function.html" title="class in org.apache.tvm">Function</a></code></td>
-<td class="colLast"><span class="typeNameLabel">TVMValue.</span><code><span class="memberNameLink"><a href="../../../../org/apache/tvm/TVMValue.html#asFunction--">asFunction</a></span>()</code> </td>
-</tr>
-<tr class="rowColor">
-<td class="colFirst"><code><a href="../../../../org/apache/tvm/Function.html" title="class in org.apache.tvm">Function</a></code></td>
<td class="colLast"><span class="typeNameLabel">Function.</span><code><span class="memberNameLink"><a href="../../../../org/apache/tvm/Function.html#asFunction--">asFunction</a></span>()</code>
<div class="block">Easy for user to get the instance from returned TVMValue.</div>
</td>
</tr>
+<tr class="rowColor">
+<td class="colFirst"><code><a href="../../../../org/apache/tvm/Function.html" title="class in org.apache.tvm">Function</a></code></td>
+<td class="colLast"><span class="typeNameLabel">TVMValue.</span><code><span class="memberNameLink"><a href="../../../../org/apache/tvm/TVMValue.html#asFunction--">asFunction</a></span>()</code> </td>
+</tr>
<tr class="altColor">
<td class="colFirst"><code>static <a href="../../../../org/apache/tvm/Function.html" title="class in org.apache.tvm">Function</a></code></td>
<td class="colLast"><span class="typeNameLabel">Function.</span><code><span class="memberNameLink"><a href="../../../../org/apache/tvm/Function.html#convertFunc-org.apache.tvm.Function.Callback-">convertFunc</a></span>(<a href="../../../../org/apache/tvm/Function.Callback.html" title="interface in org.apache.tvm">Function.Callback</a> function)</code>
@@ -145,15 +145,15 @@
</td>
</tr>
<tr class="altColor">
+<td class="colFirst"><code><a href="../../../../org/apache/tvm/Function.html" title="class in org.apache.tvm">Function</a></code></td>
+<td class="colLast"><span class="typeNameLabel">Module.</span><code><span class="memberNameLink"><a href="../../../../org/apache/tvm/Module.html#getFunction-java.lang.String-">getFunction</a></span>(<a href="http://docs.oracle.com/javase/7/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</a> name)</code> </td>
+</tr>
+<tr class="rowColor">
<td class="colFirst"><code>static <a href="../../../../org/apache/tvm/Function.html" title="class in org.apache.tvm">Function</a></code></td>
<td class="colLast"><span class="typeNameLabel">Function.</span><code><span class="memberNameLink"><a href="../../../../org/apache/tvm/Function.html#getFunction-java.lang.String-">getFunction</a></span>(<a href="http://docs.oracle.com/javase/7/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</a> name)</code>
<div class="block">Get registered function.</div>
</td>
</tr>
-<tr class="rowColor">
-<td class="colFirst"><code><a href="../../../../org/apache/tvm/Function.html" title="class in org.apache.tvm">Function</a></code></td>
-<td class="colLast"><span class="typeNameLabel">Module.</span><code><span class="memberNameLink"><a href="../../../../org/apache/tvm/Module.html#getFunction-java.lang.String-">getFunction</a></span>(<a href="http://docs.oracle.com/javase/7/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</a> name)</code> </td>
-</tr>
<tr class="altColor">
<td class="colFirst"><code><a href="../../../../org/apache/tvm/Function.html" title="class in org.apache.tvm">Function</a></code></td>
<td class="colLast"><span class="typeNameLabel">Module.</span><code><span class="memberNameLink"><a href="../../../../org/apache/tvm/Module.html#getFunction-java.lang.String-boolean-">getFunction</a></span>(<a href="http://docs.oracle.com/javase/7/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</a> name,
diff --git a/docs/api/javadoc/org/apache/tvm/class-use/Module.html b/docs/api/javadoc/org/apache/tvm/class-use/Module.html
index a68d126..f60731a 100644
--- a/docs/api/javadoc/org/apache/tvm/class-use/Module.html
+++ b/docs/api/javadoc/org/apache/tvm/class-use/Module.html
@@ -112,14 +112,14 @@
<tbody>
<tr class="altColor">
<td class="colFirst"><code><a href="../../../../org/apache/tvm/Module.html" title="class in org.apache.tvm">Module</a></code></td>
-<td class="colLast"><span class="typeNameLabel">TVMValue.</span><code><span class="memberNameLink"><a href="../../../../org/apache/tvm/TVMValue.html#asModule--">asModule</a></span>()</code> </td>
-</tr>
-<tr class="rowColor">
-<td class="colFirst"><code><a href="../../../../org/apache/tvm/Module.html" title="class in org.apache.tvm">Module</a></code></td>
<td class="colLast"><span class="typeNameLabel">Module.</span><code><span class="memberNameLink"><a href="../../../../org/apache/tvm/Module.html#asModule--">asModule</a></span>()</code>
<div class="block">Easy for user to get the instance from returned TVMValue.</div>
</td>
</tr>
+<tr class="rowColor">
+<td class="colFirst"><code><a href="../../../../org/apache/tvm/Module.html" title="class in org.apache.tvm">Module</a></code></td>
+<td class="colLast"><span class="typeNameLabel">TVMValue.</span><code><span class="memberNameLink"><a href="../../../../org/apache/tvm/TVMValue.html#asModule--">asModule</a></span>()</code> </td>
+</tr>
<tr class="altColor">
<td class="colFirst"><code>static <a href="../../../../org/apache/tvm/Module.html" title="class in org.apache.tvm">Module</a></code></td>
<td class="colLast"><span class="typeNameLabel">Module.</span><code><span class="memberNameLink"><a href="../../../../org/apache/tvm/Module.html#load-java.lang.String-">load</a></span>(<a href="http://docs.oracle.com/javase/7/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</a> path)</code> </td>
diff --git a/docs/api/javadoc/org/apache/tvm/class-use/NDArrayBase.html b/docs/api/javadoc/org/apache/tvm/class-use/NDArrayBase.html
index 161b3e5..33a9c7a 100644
--- a/docs/api/javadoc/org/apache/tvm/class-use/NDArrayBase.html
+++ b/docs/api/javadoc/org/apache/tvm/class-use/NDArrayBase.html
@@ -119,11 +119,11 @@
<tbody>
<tr class="altColor">
<td class="colFirst"><code><a href="../../../../org/apache/tvm/NDArrayBase.html" title="class in org.apache.tvm">NDArrayBase</a></code></td>
-<td class="colLast"><span class="typeNameLabel">TVMValue.</span><code><span class="memberNameLink"><a href="../../../../org/apache/tvm/TVMValue.html#asNDArray--">asNDArray</a></span>()</code> </td>
+<td class="colLast"><span class="typeNameLabel">NDArrayBase.</span><code><span class="memberNameLink"><a href="../../../../org/apache/tvm/NDArrayBase.html#asNDArray--">asNDArray</a></span>()</code> </td>
</tr>
<tr class="rowColor">
<td class="colFirst"><code><a href="../../../../org/apache/tvm/NDArrayBase.html" title="class in org.apache.tvm">NDArrayBase</a></code></td>
-<td class="colLast"><span class="typeNameLabel">NDArrayBase.</span><code><span class="memberNameLink"><a href="../../../../org/apache/tvm/NDArrayBase.html#asNDArray--">asNDArray</a></span>()</code> </td>
+<td class="colLast"><span class="typeNameLabel">TVMValue.</span><code><span class="memberNameLink"><a href="../../../../org/apache/tvm/TVMValue.html#asNDArray--">asNDArray</a></span>()</code> </td>
</tr>
<tr class="altColor">
<td class="colFirst"><code><a href="../../../../org/apache/tvm/NDArrayBase.html" title="class in org.apache.tvm">NDArrayBase</a></code></td>
diff --git a/docs/api/links.html b/docs/api/links.html
index 212ba5f..5d48827 100644
--- a/docs/api/links.html
+++ b/docs/api/links.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Links to Other API References — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Links to Other API References — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/auto_scheduler.html b/docs/api/python/auto_scheduler.html
index 76d30de..8cdba68 100644
--- a/docs/api/python/auto_scheduler.html
+++ b/docs/api/python/auto_scheduler.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.auto_scheduler — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.auto_scheduler — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -1163,7 +1163,7 @@ initialization order?).</p>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.LocalBuilder">
-<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">LocalBuilder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">15</span></span></em>, <em class="sig-param"><span class="n"><sp [...]
+<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">LocalBuilder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">15</span></span></em>, <em class="sig-param"><span class="n"><sp [...]
<dd><p>LocalBuilder use local CPU cores to build programs in parallel.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
@@ -1718,7 +1718,7 @@ Can be the a function or the function name.</p></li>
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
@@ -1755,7 +1755,7 @@ the initial naive schedule (state).</p>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
diff --git a/docs/api/python/autotvm.html b/docs/api/python/autotvm.html
index 91b53fe..872046e 100644
--- a/docs/api/python/autotvm.html
+++ b/docs/api/python/autotvm.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.autotvm — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.autotvm — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/contrib.html b/docs/api/python/contrib.html
index 3220430..e64f05f 100644
--- a/docs/api/python/contrib.html
+++ b/docs/api/python/contrib.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.contrib — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.contrib — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/driver.html b/docs/api/python/driver.html
index abde031..a33196d 100644
--- a/docs/api/python/driver.html
+++ b/docs/api/python/driver.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.driver — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.driver — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/error.html b/docs/api/python/error.html
index 1ece2a7..78dc3c6 100644
--- a/docs/api/python/error.html
+++ b/docs/api/python/error.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.error — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.error — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/graph_executor.html b/docs/api/python/graph_executor.html
index 08e488f..47b45cb 100644
--- a/docs/api/python/graph_executor.html
+++ b/docs/api/python/graph_executor.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.contrib.graph_executor — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.contrib.graph_executor — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/index.html b/docs/api/python/index.html
index 08aec50..58dd226 100644
--- a/docs/api/python/index.html
+++ b/docs/api/python/index.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Python API — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Python API — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/ir.html b/docs/api/python/ir.html
index 002adf3..3d196b6 100644
--- a/docs/api/python/ir.html
+++ b/docs/api/python/ir.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.ir — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.ir — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/micro.html b/docs/api/python/micro.html
index d47cad6..6ec6f24 100644
--- a/docs/api/python/micro.html
+++ b/docs/api/python/micro.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.micro — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.micro — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/ndarray.html b/docs/api/python/ndarray.html
index 0807d09..0773c5c 100644
--- a/docs/api/python/ndarray.html
+++ b/docs/api/python/ndarray.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.runtime.ndarray — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.runtime.ndarray — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/relay/analysis.html b/docs/api/python/relay/analysis.html
index 5196d96..9f9fe83 100644
--- a/docs/api/python/relay/analysis.html
+++ b/docs/api/python/relay/analysis.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.relay.analysis — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.relay.analysis — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/relay/backend.html b/docs/api/python/relay/backend.html
index 56f31ed..c9cddf9 100644
--- a/docs/api/python/relay/backend.html
+++ b/docs/api/python/relay/backend.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.relay.backend — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.relay.backend — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/relay/dataflow_pattern.html b/docs/api/python/relay/dataflow_pattern.html
index f8d7b93..2af08ab 100644
--- a/docs/api/python/relay/dataflow_pattern.html
+++ b/docs/api/python/relay/dataflow_pattern.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.relay.dataflow_pattern — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.relay.dataflow_pattern — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/relay/frontend.html b/docs/api/python/relay/frontend.html
index 02199d9..fb916c1 100644
--- a/docs/api/python/relay/frontend.html
+++ b/docs/api/python/relay/frontend.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.relay.frontend — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.relay.frontend — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -637,7 +637,7 @@ to be transposed, may insert extra <cite>transpose</cite> to the original graph.
<dl class="py function">
<dt class="sig sig-object py" id="tvm.relay.frontend.from_pytorch">
-<span class="sig-prename descclassname"><span class="pre">tvm.relay.frontend.</span></span><span class="sig-name descname"><span class="pre">from_pytorch</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">script_module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_infos</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_convert_map</span></span><span class="o"><span class [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.relay.frontend.</span></span><span class="sig-name descname"><span class="pre">from_pytorch</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">script_module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_infos</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_convert_map</span></span><span class="o"><span class [...]
<dd><p>Load PyTorch model in the form of a scripted PyTorch model and convert into relay.
The companion parameters will be handled automatically.</p>
<dl class="field-list simple">
@@ -654,6 +654,11 @@ e.g.
or
[(‘input0’, ((1, 2), ‘int’)), (‘input1’, ((3, 4), ‘float’))]</p></li>
<li><p><strong>custom_convert_map</strong> (<em>Dictionary of str to Relay op</em>) – A custom op conversion map in the same format as _convert_map above</p></li>
+<li><p><strong>default_type</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.9)"><em>str</em></a>) – The default dtype to use when type information is not provided by PyTorch.</p></li>
+<li><p><strong>use_parser_friendly_name</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.9)"><em>bool</em></a>) – When True, replace ‘.’ with <a href="#id1"><span class="problematic" id="id2">`</span></a>_’ in a original parameter name.
+The Relay text parser treats a variable name followed by a period as a tuple element access,
+so a variable name like “dense.weight” cannot be parsed correctly.
+Use this option when you want to run the AnnotateSpans pass on the imported module.</p></li>
</ul>
</dd>
<dt class="field-even">Returns</dt>
diff --git a/docs/api/python/relay/image.html b/docs/api/python/relay/image.html
index 71c326a..a3740d1 100644
--- a/docs/api/python/relay/image.html
+++ b/docs/api/python/relay/image.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.relay.image — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.relay.image — tvm 0.8.dev0 documentation</title>
@@ -170,7 +170,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/relay/index.html b/docs/api/python/relay/index.html
index 3ff5f8d..be98c0f 100644
--- a/docs/api/python/relay/index.html
+++ b/docs/api/python/relay/index.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.relay — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.relay — tvm 0.8.dev0 documentation</title>
@@ -170,7 +170,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/relay/nn.html b/docs/api/python/relay/nn.html
index db2180d..568db9e 100644
--- a/docs/api/python/relay/nn.html
+++ b/docs/api/python/relay/nn.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.relay.nn — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.relay.nn — tvm 0.8.dev0 documentation</title>
@@ -170,7 +170,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/relay/testing.html b/docs/api/python/relay/testing.html
index 1bd9be1..5ccffeb 100644
--- a/docs/api/python/relay/testing.html
+++ b/docs/api/python/relay/testing.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.relay.testing — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.relay.testing — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/relay/transform.html b/docs/api/python/relay/transform.html
index 4db5ed6..5f10eec 100644
--- a/docs/api/python/relay/transform.html
+++ b/docs/api/python/relay/transform.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.relay.transform — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.relay.transform — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/relay/vision.html b/docs/api/python/relay/vision.html
index cd096b9..d412922 100644
--- a/docs/api/python/relay/vision.html
+++ b/docs/api/python/relay/vision.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.relay.vision — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.relay.vision — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/rpc.html b/docs/api/python/rpc.html
index 637d20b..5718442 100644
--- a/docs/api/python/rpc.html
+++ b/docs/api/python/rpc.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.rpc — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.rpc — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/runtime.html b/docs/api/python/runtime.html
index a11b713..3a14d6d 100644
--- a/docs/api/python/runtime.html
+++ b/docs/api/python/runtime.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.runtime — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.runtime — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/target.html b/docs/api/python/target.html
index fc11485..8c390ea 100644
--- a/docs/api/python/target.html
+++ b/docs/api/python/target.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.target — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.target — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/te.html b/docs/api/python/te.html
index 33e5a65..b6e5b08 100644
--- a/docs/api/python/te.html
+++ b/docs/api/python/te.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.te — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.te — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/tir.html b/docs/api/python/tir.html
index b329f52..b1ba6d2 100644
--- a/docs/api/python/tir.html
+++ b/docs/api/python/tir.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.tir — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.tir — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/topi.html b/docs/api/python/topi.html
index a5149ca..fb2a149 100644
--- a/docs/api/python/topi.html
+++ b/docs/api/python/topi.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>tvm.topi — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>tvm.topi — tvm 0.8.dev0 documentation</title>
@@ -170,7 +170,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/python/vta/index.html b/docs/api/python/vta/index.html
index 69d312a..ca410d3 100644
--- a/docs/api/python/vta/index.html
+++ b/docs/api/python/vta/index.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>vta — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>vta — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/api/typedoc/classes/bytestreamreader.html b/docs/api/typedoc/classes/bytestreamreader.html
index f6e99bc..b4623c9 100644
--- a/docs/api/typedoc/classes/bytestreamreader.html
+++ b/docs/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/dc2f70e3c/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -141,7 +141,7 @@
<div class="tsd-signature tsd-kind-icon">bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Uint8Array</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
</section>
@@ -151,7 +151,7 @@
<div class="tsd-signature tsd-kind-icon">offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
</ul>
</aside>
</section>
@@ -168,7 +168,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">Uint8Array</span></h4>
@@ -185,7 +185,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -202,7 +202,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/api/typedoc/classes/cachedcallstack.html b/docs/api/typedoc/classes/cachedcallstack.html
index 0a3cb55..48fcf0a 100644
--- a/docs/api/typedoc/classes/cachedcallstack.html
+++ b/docs/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/dc2f70e3c/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/memory.ts#L334">memory.ts:334</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
diff --git a/docs/api/typedoc/classes/dldatatype.html b/docs/api/typedoc/classes/dldatatype.html
index 5b8148e..d144136 100644
--- a/docs/api/typedoc/classes/dldatatype.html
+++ b/docs/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/dc2f70e3c/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L260">runtime.ts:260</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L258">runtime.ts:258</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L279">runtime.ts:279</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L270">runtime.ts:270</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/api/typedoc/classes/dldevice.html b/docs/api/typedoc/classes/dldevice.html
index 862c289..f3784b0 100644
--- a/docs/api/typedoc/classes/dldevice.html
+++ b/docs/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/dc2f70e3c/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L202">runtime.ts:202</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L200">runtime.ts:200</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L223">runtime.ts:223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L230">runtime.ts:230</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/api/typedoc/classes/environment.html b/docs/api/typedoc/classes/environment.html
index 0f9417f..6081cb9 100644
--- a/docs/api/typedoc/classes/environment.html
+++ b/docs/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/dc2f70e3c/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/environment.ts#L105">environment.ts:105</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/api/typedoc/classes/ffilibrary.html b/docs/api/typedoc/classes/ffilibrary.html
index a7b74d8..df629c2 100644
--- a/docs/api/typedoc/classes/ffilibrary.html
+++ b/docs/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/dc2f70e3c/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L49">runtime.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L46">runtime.ts:46</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L45">runtime.ts:45</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L44">runtime.ts:44</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L47">runtime.ts:47</a></li>
</ul>
</aside>
</section>
@@ -203,7 +203,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L76">runtime.ts:76</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L66">runtime.ts:66</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L84">runtime.ts:84</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L95">runtime.ts:95</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L72">runtime.ts:72</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/api/typedoc/classes/graphexecutor.html b/docs/api/typedoc/classes/graphexecutor.html
index fdd2835..1c749b2 100644
--- a/docs/api/typedoc/classes/graphexecutor.html
+++ b/docs/api/typedoc/classes/graphexecutor.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L583">runtime.ts:583</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">module<span class="tsd-signature-symbol">:</span> <a href="module.html" class="tsd-signature-type">Module</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L579">runtime.ts:579</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L654">runtime.ts:654</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L597">runtime.ts:597</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -241,7 +241,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L631">runtime.ts:631</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L644">runtime.ts:644</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -310,7 +310,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L621">runtime.ts:621</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L609">runtime.ts:609</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/api/typedoc/classes/instance.html b/docs/api/typedoc/classes/instance.html
index 7bdb148..497b3f3 100644
--- a/docs/api/typedoc/classes/instance.html
+++ b/docs/api/typedoc/classes/instance.html
@@ -139,7 +139,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L692">runtime.ts:692</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L684">runtime.ts:684</a></li>
</ul>
</aside>
</section>
@@ -212,7 +212,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L683">runtime.ts:683</a></li>
</ul>
</aside>
</section>
@@ -229,7 +229,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L994">runtime.ts:994</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -303,7 +303,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L924">runtime.ts:924</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -341,7 +341,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L732">runtime.ts:732</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -358,7 +358,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L952">runtime.ts:952</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -402,7 +402,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L816">runtime.ts:816</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -434,7 +434,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -465,7 +465,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L846">runtime.ts:846</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -497,7 +497,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L750">runtime.ts:750</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -520,7 +520,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -568,7 +568,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L789">runtime.ts:789</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -608,7 +608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L914">runtime.ts:914</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -646,7 +646,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L740">runtime.ts:740</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -722,7 +722,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L868">runtime.ts:868</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -754,7 +754,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L857">runtime.ts:857</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -786,7 +786,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L940">runtime.ts:940</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/api/typedoc/classes/memory.html b/docs/api/typedoc/classes/memory.html
index f6c15e9..e9af2e9 100644
--- a/docs/api/typedoc/classes/memory.html
+++ b/docs/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/dc2f70e3c/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/memory.ts#L175">memory.ts:175</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/api/typedoc/classes/module.html b/docs/api/typedoc/classes/module.html
index 670305d..3aaf7cb 100644
--- a/docs/api/typedoc/classes/module.html
+++ b/docs/api/typedoc/classes/module.html
@@ -124,7 +124,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L504">runtime.ts:504</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L502">runtime.ts:502</a></li>
</ul>
</aside>
</section>
@@ -187,7 +187,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L516">runtime.ts:516</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -204,7 +204,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L530">runtime.ts:530</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -236,7 +236,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L561">runtime.ts:561</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/api/typedoc/classes/ndarray.html b/docs/api/typedoc/classes/ndarray.html
index 512b1a5..dfbb723 100644
--- a/docs/api/typedoc/classes/ndarray.html
+++ b/docs/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/dc2f70e3c/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L304">runtime.ts:304</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L293">runtime.ts:293</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L289">runtime.ts:289</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L291">runtime.ts:291</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -240,7 +240,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L370">runtime.ts:370</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -273,7 +273,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L414">runtime.ts:414</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -305,7 +305,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -322,7 +322,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L474">runtime.ts:474</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -346,7 +346,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L443">runtime.ts:443</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/api/typedoc/classes/packedfunccell.html b/docs/api/typedoc/classes/packedfunccell.html
index 57b6603..12809ca 100644
--- a/docs/api/typedoc/classes/packedfunccell.html
+++ b/docs/api/typedoc/classes/packedfunccell.html
@@ -122,7 +122,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L158">runtime.ts:158</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
</section>
@@ -164,7 +164,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L165">runtime.ts:165</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
diff --git a/docs/api/typedoc/classes/rpcserver.html b/docs/api/typedoc/classes/rpcserver.html
index 2bd20b7..a50d2fe 100644
--- a/docs/api/typedoc/classes/rpcserver.html
+++ b/docs/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/dc2f70e3c/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
</ul>
</aside>
</section>
diff --git a/docs/api/typedoc/classes/scalar.html b/docs/api/typedoc/classes/scalar.html
index a02b1c9..5402606 100644
--- a/docs/api/typedoc/classes/scalar.html
+++ b/docs/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/dc2f70e3c/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/api/typedoc/classes/webgpucontext.html b/docs/api/typedoc/classes/webgpucontext.html
index 7492bcc..4945f51 100644
--- a/docs/api/typedoc/classes/webgpucontext.html
+++ b/docs/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/dc2f70e3c/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/api/typedoc/enums/argtypecode.html b/docs/api/typedoc/enums/argtypecode.html
index daf473c..775f7bd 100644
--- a/docs/api/typedoc/enums/argtypecode.html
+++ b/docs/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/dc2f70e3c/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
</section>
diff --git a/docs/api/typedoc/enums/aynccallbackcode.html b/docs/api/typedoc/enums/aynccallbackcode.html
index 6a329d7..3cc76d1 100644
--- a/docs/api/typedoc/enums/aynccallbackcode.html
+++ b/docs/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/dc2f70e3c/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L676">runtime.ts:676</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L675">runtime.ts:675</a></li>
</ul>
</aside>
</section>
diff --git a/docs/api/typedoc/enums/dldatatypecode.html b/docs/api/typedoc/enums/dldatatypecode.html
index 9457f93..d7440f9 100644
--- a/docs/api/typedoc/enums/dldatatypecode.html
+++ b/docs/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/dc2f70e3c/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L240">runtime.ts:240</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L243">runtime.ts:243</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L241">runtime.ts:241</a></li>
</ul>
</aside>
</section>
diff --git a/docs/api/typedoc/enums/rpcserverstate.html b/docs/api/typedoc/enums/rpcserverstate.html
index 1c1c120..0b7f4a4 100644
--- a/docs/api/typedoc/enums/rpcserverstate.html
+++ b/docs/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/dc2f70e3c/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
diff --git a/docs/api/typedoc/enums/sizeof.html b/docs/api/typedoc/enums/sizeof.html
index bd1ca7d..e0f40c4 100644
--- a/docs/api/typedoc/enums/sizeof.html
+++ b/docs/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/dc2f70e3c/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/api/typedoc/index.html b/docs/api/typedoc/index.html
index 9db8022..59ae220 100644
--- a/docs/api/typedoc/index.html
+++ b/docs/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L36">runtime.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L246">runtime.ts:246</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L247">runtime.ts:247</a></li>
</ul>
</aside>
</section>
@@ -1549,7 +1549,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
</section>
@@ -1559,7 +1559,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L249">runtime.ts:249</a></li>
</ul>
</aside>
</section>
@@ -1569,7 +1569,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L250">runtime.ts:250</a></li>
</ul>
</aside>
</section>
@@ -1580,7 +1580,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L175">runtime.ts:175</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1589,7 +1589,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L176">runtime.ts:176</a></li>
</ul>
</aside>
</section>
@@ -1599,7 +1599,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L180">runtime.ts:180</a></li>
</ul>
</aside>
</section>
@@ -1609,7 +1609,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L177">runtime.ts:177</a></li>
</ul>
</aside>
</section>
@@ -1619,7 +1619,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L178">runtime.ts:178</a></li>
</ul>
</aside>
</section>
@@ -1629,7 +1629,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L179">runtime.ts:179</a></li>
</ul>
</aside>
</section>
@@ -1640,7 +1640,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L183">runtime.ts:183</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1649,7 +1649,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L186">runtime.ts:186</a></li>
</ul>
</aside>
</section>
@@ -1659,7 +1659,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L184">runtime.ts:184</a></li>
</ul>
</aside>
</section>
@@ -1669,7 +1669,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L185">runtime.ts:185</a></li>
</ul>
</aside>
</section>
@@ -1679,7 +1679,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
</section>
@@ -1689,7 +1689,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L187">runtime.ts:187</a></li>
</ul>
</aside>
</section>
@@ -1699,7 +1699,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L188">runtime.ts:188</a></li>
</ul>
</aside>
</section>
@@ -1709,7 +1709,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/runtime.ts#L190">runtime.ts:190</a></li>
</ul>
</aside>
</section>
diff --git a/docs/api/typedoc/interfaces/disposable.html b/docs/api/typedoc/interfaces/disposable.html
index b7bfdc8..c624bd7 100644
--- a/docs/api/typedoc/interfaces/disposable.html
+++ b/docs/api/typedoc/interfaces/disposable.html
@@ -113,7 +113,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dc2f70e3c/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/types.ts#L52">types.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/api/typedoc/interfaces/functioninfo.html b/docs/api/typedoc/interfaces/functioninfo.html
index 2c1beeb..268ec00 100644
--- a/docs/api/typedoc/interfaces/functioninfo.html
+++ b/docs/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/dc2f70e3c/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
</ul>
</aside>
</section>
diff --git a/docs/api/typedoc/interfaces/libraryprovider.html b/docs/api/typedoc/interfaces/libraryprovider.html
index 6ab5682..01ba1b2 100644
--- a/docs/api/typedoc/interfaces/libraryprovider.html
+++ b/docs/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/dc2f70e3c/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/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/dc2f70e3c/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/57386a2da/web/src/types.ts#L39">types.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/contribute/code_guide.html b/docs/contribute/code_guide.html
index c8b2a4c..e2aebbe 100644
--- a/docs/contribute/code_guide.html
+++ b/docs/contribute/code_guide.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Code Guide and Tips — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Code Guide and Tips — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/contribute/code_review.html b/docs/contribute/code_review.html
index 4d337f4..7a85af6 100644
--- a/docs/contribute/code_review.html
+++ b/docs/contribute/code_review.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Perform Code Reviews — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Perform Code Reviews — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/contribute/committer_guide.html b/docs/contribute/committer_guide.html
index 5093274..05121ec 100644
--- a/docs/contribute/committer_guide.html
+++ b/docs/contribute/committer_guide.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Committer Guide — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Committer Guide — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/contribute/community.html b/docs/contribute/community.html
index c2ee70f..b3c3078 100644
--- a/docs/contribute/community.html
+++ b/docs/contribute/community.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>TVM Community Guideline — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>TVM Community Guideline — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/contribute/document.html b/docs/contribute/document.html
index 4306441..7564557 100644
--- a/docs/contribute/document.html
+++ b/docs/contribute/document.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Write Document and Tutorials — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Write Document and Tutorials — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/contribute/error_handling.html b/docs/contribute/error_handling.html
index 7a857cc..ceed046 100644
--- a/docs/contribute/error_handling.html
+++ b/docs/contribute/error_handling.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Error Handling Guide — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Error Handling Guide — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/contribute/git_howto.html b/docs/contribute/git_howto.html
index b1078c8..1471ffc 100644
--- a/docs/contribute/git_howto.html
+++ b/docs/contribute/git_howto.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Git Usage Tips — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Git Usage Tips — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/contribute/index.html b/docs/contribute/index.html
index 352924e..635b485 100644
--- a/docs/contribute/index.html
+++ b/docs/contribute/index.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Contribute to TVM — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Contribute to TVM — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/contribute/pull_request.html b/docs/contribute/pull_request.html
index bf4e48f..496034e 100644
--- a/docs/contribute/pull_request.html
+++ b/docs/contribute/pull_request.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Submit a Pull Request — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Submit a Pull Request — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/contribute/release_process.html b/docs/contribute/release_process.html
index 94ffbd8..9aa8773 100644
--- a/docs/contribute/release_process.html
+++ b/docs/contribute/release_process.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Apache TVM Release Process — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Apache TVM Release Process — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/deploy/android.html b/docs/deploy/android.html
index 689c4ee..a690000 100644
--- a/docs/deploy/android.html
+++ b/docs/deploy/android.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Deploy to Android — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Deploy to Android — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/deploy/arm_compute_lib.html b/docs/deploy/arm_compute_lib.html
index 44385f5..73aac05 100644
--- a/docs/deploy/arm_compute_lib.html
+++ b/docs/deploy/arm_compute_lib.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Relay Arm® Compute Library Integration — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Relay Arm® Compute Library Integration — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/deploy/bnns.html b/docs/deploy/bnns.html
index c7bcfb5..2067b63 100644
--- a/docs/deploy/bnns.html
+++ b/docs/deploy/bnns.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Relay BNNS Integration — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Relay BNNS Integration — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/deploy/cpp_deploy.html b/docs/deploy/cpp_deploy.html
index c2d4858..d556592 100644
--- a/docs/deploy/cpp_deploy.html
+++ b/docs/deploy/cpp_deploy.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Deploy TVM Module using C++ API — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Deploy TVM Module using C++ API — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/deploy/hls.html b/docs/deploy/hls.html
index 9ae376a..9d5228f 100644
--- a/docs/deploy/hls.html
+++ b/docs/deploy/hls.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>HLS Backend Example — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>HLS Backend Example — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/deploy/index.html b/docs/deploy/index.html
index 654cd81..685ed13 100644
--- a/docs/deploy/index.html
+++ b/docs/deploy/index.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Deploy and Integration — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Deploy and Integration — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/deploy/integrate.html b/docs/deploy/integrate.html
index e2b3e68..2e6a3a6 100644
--- a/docs/deploy/integrate.html
+++ b/docs/deploy/integrate.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Integrate TVM into Your Project — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Integrate TVM into Your Project — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/deploy/tensorrt.html b/docs/deploy/tensorrt.html
index 355a03a..6a4c834 100644
--- a/docs/deploy/tensorrt.html
+++ b/docs/deploy/tensorrt.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Relay TensorRT Integration — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Relay TensorRT Integration — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/deploy/vitis_ai.html b/docs/deploy/vitis_ai.html
index d3ece13..8bfbf2f 100644
--- a/docs/deploy/vitis_ai.html
+++ b/docs/deploy/vitis_ai.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Vitis-AI Integration — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Vitis-AI Integration — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/benchmark.html b/docs/dev/benchmark.html
index aae29d7..034863c 100644
--- a/docs/dev/benchmark.html
+++ b/docs/dev/benchmark.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Benchmark Performance Log Format — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Benchmark Performance Log Format — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/codebase_walkthrough.html b/docs/dev/codebase_walkthrough.html
index 6742e72..092236b 100644
--- a/docs/dev/codebase_walkthrough.html
+++ b/docs/dev/codebase_walkthrough.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>TVM Codebase Walkthrough by Example — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>TVM Codebase Walkthrough by Example — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/convert_layout.html b/docs/dev/convert_layout.html
index e402451..6dff864 100644
--- a/docs/dev/convert_layout.html
+++ b/docs/dev/convert_layout.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Convert Layout Pass — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Convert Layout Pass — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/debugger.html b/docs/dev/debugger.html
index 87cfc5b..71c26f5 100644
--- a/docs/dev/debugger.html
+++ b/docs/dev/debugger.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Debugger — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Debugger — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/device_target_interactions.html b/docs/dev/device_target_interactions.html
index 380c7da..a14208a 100644
--- a/docs/dev/device_target_interactions.html
+++ b/docs/dev/device_target_interactions.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Device/Target Interactions — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Device/Target Interactions — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/frontend/tensorflow.html b/docs/dev/frontend/tensorflow.html
index 493a212..f171c99 100644
--- a/docs/dev/frontend/tensorflow.html
+++ b/docs/dev/frontend/tensorflow.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>TensorFlow Frontend — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>TensorFlow Frontend — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/how_to.html b/docs/dev/how_to.html
index 483248a..4032a4d 100644
--- a/docs/dev/how_to.html
+++ b/docs/dev/how_to.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Developer How-To Guide — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Developer How-To Guide — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/hybrid_script.html b/docs/dev/hybrid_script.html
index c4e9561..7952275 100644
--- a/docs/dev/hybrid_script.html
+++ b/docs/dev/hybrid_script.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Hybrid Frontend Developer Guide — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Hybrid Frontend Developer Guide — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/index.html b/docs/dev/index.html
index e31cb98..bf89966 100644
--- a/docs/dev/index.html
+++ b/docs/dev/index.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Design and Architecture — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Design and Architecture — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/inferbound.html b/docs/dev/inferbound.html
index c03e979..b33d4f5 100644
--- a/docs/dev/inferbound.html
+++ b/docs/dev/inferbound.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>InferBound Pass — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>InferBound Pass — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/introduction_to_module_serialization.html b/docs/dev/introduction_to_module_serialization.html
index 67f4a4b..561ca9f 100644
--- a/docs/dev/introduction_to_module_serialization.html
+++ b/docs/dev/introduction_to_module_serialization.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Introduction to Module Serialization — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Introduction to Module Serialization — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/microtvm_design.html b/docs/dev/microtvm_design.html
index 9d22f36..9b8b240 100644
--- a/docs/dev/microtvm_design.html
+++ b/docs/dev/microtvm_design.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>microTVM Design Document — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>microTVM Design Document — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/model_library_format.html b/docs/dev/model_library_format.html
index 0944898..ab0a622 100644
--- a/docs/dev/model_library_format.html
+++ b/docs/dev/model_library_format.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Model Library Format — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Model Library Format — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/pass_infra.html b/docs/dev/pass_infra.html
index 9a07a99..42b8a4e 100644
--- a/docs/dev/pass_infra.html
+++ b/docs/dev/pass_infra.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Pass Infrastructure — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Pass Infrastructure — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/pytest_target_parametrization.html b/docs/dev/pytest_target_parametrization.html
index 5357f32..e58b284 100644
--- a/docs/dev/pytest_target_parametrization.html
+++ b/docs/dev/pytest_target_parametrization.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Python Target Parametrization — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Python Target Parametrization — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/relay_add_op.html b/docs/dev/relay_add_op.html
index b43b6f7..ef43962 100644
--- a/docs/dev/relay_add_op.html
+++ b/docs/dev/relay_add_op.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Adding an Operator to Relay — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Adding an Operator to Relay — tvm 0.8.dev0 documentation</title>
@@ -170,7 +170,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/relay_add_pass.html b/docs/dev/relay_add_pass.html
index cb54bbb..e69d668 100644
--- a/docs/dev/relay_add_pass.html
+++ b/docs/dev/relay_add_pass.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Adding a Compiler Pass to Relay — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Adding a Compiler Pass to Relay — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/relay_bring_your_own_codegen.html b/docs/dev/relay_bring_your_own_codegen.html
index c2890d7..a9038f4 100644
--- a/docs/dev/relay_bring_your_own_codegen.html
+++ b/docs/dev/relay_bring_your_own_codegen.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Bring Your Own Codegen To TVM — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Bring Your Own Codegen To TVM — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/relay_intro.html b/docs/dev/relay_intro.html
index 27d939f..d00690f 100644
--- a/docs/dev/relay_intro.html
+++ b/docs/dev/relay_intro.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Introduction to Relay IR — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Introduction to Relay IR — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/relay_op_strategy.html b/docs/dev/relay_op_strategy.html
index 2b717f4..b32027b 100644
--- a/docs/dev/relay_op_strategy.html
+++ b/docs/dev/relay_op_strategy.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Relay Operator Strategy — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Relay Operator Strategy — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/runtime.html b/docs/dev/runtime.html
index 89f69d1..8cfc2ff 100644
--- a/docs/dev/runtime.html
+++ b/docs/dev/runtime.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>TVM Runtime System — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>TVM Runtime System — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/runtimes/vulkan.html b/docs/dev/runtimes/vulkan.html
index 9f1387c..1ec24ed 100644
--- a/docs/dev/runtimes/vulkan.html
+++ b/docs/dev/runtimes/vulkan.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Vulkan Runtime — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Vulkan Runtime — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/security.html b/docs/dev/security.html
index 0ae4fdc..d4b948d 100644
--- a/docs/dev/security.html
+++ b/docs/dev/security.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Security Guide — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Security Guide — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/dev/virtual_machine.html b/docs/dev/virtual_machine.html
index 5a61044..26d36a4 100644
--- a/docs/dev/virtual_machine.html
+++ b/docs/dev/virtual_machine.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Putting the VM in TVM: The Relay Virtual Machine — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Putting the VM in TVM: The Relay Virtual Machine — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/errors.html b/docs/errors.html
index 4aa00a6..2234ae0 100644
--- a/docs/errors.html
+++ b/docs/errors.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>What do to when encountering TVM Errors — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>What do to when encountering TVM Errors — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/faq.html b/docs/faq.html
index bfac92f..16bd36b 100644
--- a/docs/faq.html
+++ b/docs/faq.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Frequently Asked Questions — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Frequently Asked Questions — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/genindex.html b/docs/genindex.html
index 19dfdb7..eff4a68 100644
--- a/docs/genindex.html
+++ b/docs/genindex.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Index — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Index — tvm 0.8.dev0 documentation</title>
@@ -167,7 +167,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/index.html b/docs/index.html
index 8e56258..6e21539 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>TVM Documentation — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>TVM Documentation — tvm 0.8.dev0 documentation</title>
@@ -168,7 +168,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/install/docker.html b/docs/install/docker.html
index 81fefd8..07fa245 100644
--- a/docs/install/docker.html
+++ b/docs/install/docker.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Docker Images — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Docker Images — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/install/from_source.html b/docs/install/from_source.html
index 879db2d..e94fef4 100644
--- a/docs/install/from_source.html
+++ b/docs/install/from_source.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Install from Source — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Install from Source — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/install/index.html b/docs/install/index.html
index f8853e2..cb756d0 100644
--- a/docs/install/index.html
+++ b/docs/install/index.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Installation — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Installation — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index d9a466d..e110d29 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>NNPACK Contrib Installation — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>NNPACK Contrib Installation — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/langref/hybrid_script.html b/docs/langref/hybrid_script.html
index 1d82d1b..3a52ef4 100644
--- a/docs/langref/hybrid_script.html
+++ b/docs/langref/hybrid_script.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Hybrid Frontend Language Reference — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Hybrid Frontend Language Reference — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/langref/index.html b/docs/langref/index.html
index 4e6f835..dc68932 100644
--- a/docs/langref/index.html
+++ b/docs/langref/index.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Language Reference — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Language Reference — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/langref/relay_adt.html b/docs/langref/relay_adt.html
index a497f2a..000e3a6 100644
--- a/docs/langref/relay_adt.html
+++ b/docs/langref/relay_adt.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Algebraic Data Types in Relay — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Algebraic Data Types in Relay — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/langref/relay_expr.html b/docs/langref/relay_expr.html
index f442df8..793f7dd 100644
--- a/docs/langref/relay_expr.html
+++ b/docs/langref/relay_expr.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Expressions in Relay — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Expressions in Relay — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/langref/relay_op.html b/docs/langref/relay_op.html
index 2c9180b..59d3c67 100644
--- a/docs/langref/relay_op.html
+++ b/docs/langref/relay_op.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Relay Core Tensor Operators — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Relay Core Tensor Operators — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/langref/relay_pattern.html b/docs/langref/relay_pattern.html
index f265f7d..6f43e73 100644
--- a/docs/langref/relay_pattern.html
+++ b/docs/langref/relay_pattern.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Pattern Matching in Relay — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Pattern Matching in Relay — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/langref/relay_type.html b/docs/langref/relay_type.html
index 8260b5e..c085ee4 100644
--- a/docs/langref/relay_type.html
+++ b/docs/langref/relay_type.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Relay’s Type System — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Relay’s Type System — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/microtvm/index.html b/docs/microtvm/index.html
index cd96544..a3dba21 100644
--- a/docs/microtvm/index.html
+++ b/docs/microtvm/index.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>microTVM: TVM on bare-metal — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>microTVM: TVM on bare-metal — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/objects.inv b/docs/objects.inv
index e204561..741511b 100644
Binary files a/docs/objects.inv and b/docs/objects.inv differ
diff --git a/docs/profiling/index.html b/docs/profiling/index.html
index 5cbc2c5..89c43d4 100644
--- a/docs/profiling/index.html
+++ b/docs/profiling/index.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Profiling Deep Learning Models — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Profiling Deep Learning Models — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/profiling/papi.html b/docs/profiling/papi.html
index 75b6b51..047992a 100644
--- a/docs/profiling/papi.html
+++ b/docs/profiling/papi.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Getting Started With PAPI — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Getting Started With PAPI — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/py-modindex.html b/docs/py-modindex.html
index 7fcb4cb..35f2a42 100644
--- a/docs/py-modindex.html
+++ b/docs/py-modindex.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Python Module Index — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Python Module Index — tvm 0.8.dev0 documentation</title>
@@ -170,7 +170,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/search.html b/docs/search.html
index 69a7540..4aa7370 100644
--- a/docs/search.html
+++ b/docs/search.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Search — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Search — tvm 0.8.dev0 documentation</title>
@@ -170,7 +170,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/searchindex.js b/docs/searchindex.js
index b41db9e..022adf3 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["api/links","api/python/auto_scheduler","api/python/autotvm","api/python/contrib","api/python/driver","api/python/error","api/python/graph_executor","api/python/index","api/python/ir","api/python/micro","api/python/ndarray","api/python/relay/analysis","api/python/relay/backend","api/python/relay/dataflow_pattern","api/python/relay/frontend","api/python/relay/image","api/python/relay/index","api/python/relay/nn","api/python/relay/testing","api/python/relay/trans [...]
\ No newline at end of file
+Search.setIndex({docnames:["api/links","api/python/auto_scheduler","api/python/autotvm","api/python/contrib","api/python/driver","api/python/error","api/python/graph_executor","api/python/index","api/python/ir","api/python/micro","api/python/ndarray","api/python/relay/analysis","api/python/relay/backend","api/python/relay/dataflow_pattern","api/python/relay/frontend","api/python/relay/image","api/python/relay/index","api/python/relay/nn","api/python/relay/testing","api/python/relay/trans [...]
\ No newline at end of file
diff --git a/docs/tutorials/auto_scheduler/sg_execution_times.html b/docs/tutorials/auto_scheduler/sg_execution_times.html
index a9745fe..da3d6e2 100644
--- a/docs/tutorials/auto_scheduler/sg_execution_times.html
+++ b/docs/tutorials/auto_scheduler/sg_execution_times.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Computation times — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Computation times — tvm 0.8.dev0 documentation</title>
@@ -167,7 +167,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -308,14 +308,14 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorials-auto-scheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>02:43.083</strong> total execution time for <strong>tutorials_auto_scheduler</strong> files:</p>
+<p><strong>04:07.859</strong> total execution time for <strong>tutorials_auto_scheduler</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:54.913</strong>: <a class="reference internal" href="tune_network_x86.html#sphx-glr-tutorials-auto-scheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></li>
-<li><p><strong>00:51.988</strong>: <a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-tutorials-auto-scheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></li>
-<li><p><strong>00:30.251</strong>: <a class="reference internal" href="tune_network_cuda.html#sphx-glr-tutorials-auto-scheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></li>
-<li><p><strong>00:10.337</strong>: <a class="reference internal" href="tune_sparse_x86.html#sphx-glr-tutorials-auto-scheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></li>
-<li><p><strong>00:08.422</strong>: <a class="reference internal" href="tune_network_mali.html#sphx-glr-tutorials-auto-scheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></li>
-<li><p><strong>00:07.172</strong>: <a class="reference internal" href="tune_network_arm.html#sphx-glr-tutorials-auto-scheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></li>
+<li><p><strong>02:12.551</strong>: <a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-tutorials-auto-scheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></li>
+<li><p><strong>00:52.866</strong>: <a class="reference internal" href="tune_network_x86.html#sphx-glr-tutorials-auto-scheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></li>
+<li><p><strong>00:30.958</strong>: <a class="reference internal" href="tune_network_cuda.html#sphx-glr-tutorials-auto-scheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></li>
+<li><p><strong>00:17.657</strong>: <a class="reference internal" href="tune_sparse_x86.html#sphx-glr-tutorials-auto-scheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></li>
+<li><p><strong>00:07.020</strong>: <a class="reference internal" href="tune_network_mali.html#sphx-glr-tutorials-auto-scheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></li>
+<li><p><strong>00:06.806</strong>: <a class="reference internal" href="tune_network_arm.html#sphx-glr-tutorials-auto-scheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/tutorials/auto_scheduler/tune_conv2d_layer_cuda.html b/docs/tutorials/auto_scheduler/tune_conv2d_layer_cuda.html
index c9a961a..d027c85 100644
--- a/docs/tutorials/auto_scheduler/tune_conv2d_layer_cuda.html
+++ b/docs/tutorials/auto_scheduler/tune_conv2d_layer_cuda.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Auto-scheduling a Convolution Layer for GPU — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Auto-scheduling a Convolution Layer for GPU — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -971,7 +971,7 @@ primfn(data_1: handle, kernel_1: handle, bias_1: handle, compute_1: handle) ->
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.275 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.353 ms
</pre></div>
</div>
</div>
@@ -1536,6 +1536,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 12.551 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorials-auto-scheduler-tune-conv2d-layer-cuda-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/678f3c372a599a18d909aed0fefb30be/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/tutorials/auto_scheduler/tune_network_arm.html b/docs/tutorials/auto_scheduler/tune_network_arm.html
index c6109f1..caa71ff 100644
--- a/docs/tutorials/auto_scheduler/tune_network_arm.html
+++ b/docs/tutorials/auto_scheduler/tune_network_arm.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Auto-scheduling a Neural Network for ARM CPU — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Auto-scheduling a Neural Network for ARM CPU — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -567,14 +567,14 @@ The task scheduler will just optimize this objective.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get model...
Extract tasks...
-========== Task 0 (workload key: ["7d44c6e3c81cd80f61ff2265b2bae89a", [1, 1024], [1000, 1024], [1, 1000], [1, 1000]]) ==========
+========== Task 0 (workload key: ["7d44c6e3c81cd80f61ff2265b2bae89a", 1, 1024, 1000, 1024, 1, 1000, 1, 1000]) ==========
placeholder = PLACEHOLDER [1, 1024]
placeholder = PLACEHOLDER [1000, 1024]
T_matmul_NT(i, j) += (placeholder[i, k]*placeholder[j, k])
placeholder = PLACEHOLDER [1, 1000]
T_add(ax0, ax1) = (T_matmul_NT[ax0, ax1] + placeholder[ax0, ax1])
-========== Task 1 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 28, 28, 128], [1, 1, 128, 256], [1, 1, 1, 256], [1, 28, 28, 256]]) ==========
+========== Task 1 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 28, 28, 128, 1, 1, 128, 256, 1, 1, 1, 256, 1, 28, 28, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 128, 256]
@@ -583,7 +583,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 256]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 2 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 28, 28, 256], [1, 1, 256, 256], [1, 1, 1, 256], [1, 28, 28, 256]]) ==========
+========== Task 2 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 28, 28, 256, 1, 1, 256, 256, 1, 1, 1, 256, 1, 28, 28, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 256]
@@ -592,7 +592,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 256]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 3 (workload key: ["06fce76bd84cb904eee50b905ca9449a", [1, 14, 14, 512], [3, 3, 512, 1], [1, 1, 1, 512], [1, 14, 14, 512]]) ==========
+========== Task 3 (workload key: ["06fce76bd84cb904eee50b905ca9449a", 1, 14, 14, 512, 3, 3, 512, 1, 1, 1, 1, 512, 1, 14, 14, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 512]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 15)) && (i2 >= 1)) && (i2 < 15)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 512, 1]
@@ -601,7 +601,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 512]
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 4 (workload key: ["98418eda02701ddd175ad50e364a0638", [1, 224, 224, 3], [3, 3, 3, 32], [1, 112, 1, 1], [1, 112, 1, 1], [1, 112, 112, 32]]) ==========
+========== Task 4 (workload key: ["98418eda02701ddd175ad50e364a0638", 1, 224, 224, 3, 3, 3, 3, 32, 1, 112, 1, 1, 1, 112, 1, 1, 1, 112, 112, 32]) ==========
placeholder = PLACEHOLDER [1, 224, 224, 3]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 225)) && (i2 >= 1)) && (i2 < 225)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 3, 32]
@@ -612,7 +612,7 @@ placeholder = PLACEHOLDER [1, 112, 1, 1]
T_add(ax0, ax1, ax2, ax3) = (T_multiply[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, 0, 0])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 5 (workload key: ["c87ba68bc180312f5716af09a77ca15b", [1, 56, 56, 128], [3, 3, 128, 1], [1, 1, 1, 128], [1, 28, 28, 128]]) ==========
+========== Task 5 (workload key: ["c87ba68bc180312f5716af09a77ca15b", 1, 56, 56, 128, 3, 3, 128, 1, 1, 1, 1, 128, 1, 28, 28, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 128]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 57)) && (i2 >= 1)) && (i2 < 57)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 128, 1]
@@ -621,7 +621,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 128]
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 6 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 14, 14, 512], [1, 1, 512, 512], [1, 1, 1, 512], [1, 14, 14, 512]]) ==========
+========== Task 6 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 14, 14, 512, 1, 1, 512, 512, 1, 1, 1, 512, 1, 14, 14, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 512]
@@ -630,7 +630,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 512]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 7 (workload key: ["06fce76bd84cb904eee50b905ca9449a", [1, 28, 28, 256], [3, 3, 256, 1], [1, 1, 1, 256], [1, 28, 28, 256]]) ==========
+========== Task 7 (workload key: ["06fce76bd84cb904eee50b905ca9449a", 1, 28, 28, 256, 3, 3, 256, 1, 1, 1, 1, 256, 1, 28, 28, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 256]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 29)) && (i2 >= 1)) && (i2 < 29)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 256, 1]
@@ -639,7 +639,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 256]
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 8 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 7, 7, 1024], [1, 1, 1024, 1024], [1, 1, 1, 1024], [1, 7, 7, 1024]]) ==========
+========== Task 8 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 7, 7, 1024, 1, 1, 1024, 1024, 1, 1, 1, 1024, 1, 7, 7, 1024]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 1024]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 1024, 1024]
@@ -648,7 +648,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 1024]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 9 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 56, 56, 128], [1, 1, 128, 128], [1, 1, 1, 128], [1, 56, 56, 128]]) ==========
+========== Task 9 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 56, 56, 128, 1, 1, 128, 128, 1, 1, 1, 128, 1, 56, 56, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 128]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 128, 128]
@@ -657,7 +657,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 128]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 10 (workload key: ["06fce76bd84cb904eee50b905ca9449a", [1, 56, 56, 128], [3, 3, 128, 1], [1, 1, 1, 128], [1, 56, 56, 128]]) ==========
+========== Task 10 (workload key: ["06fce76bd84cb904eee50b905ca9449a", 1, 56, 56, 128, 3, 3, 128, 1, 1, 1, 1, 128, 1, 56, 56, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 128]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 57)) && (i2 >= 1)) && (i2 < 57)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 128, 1]
@@ -666,7 +666,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 128]
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 11 (workload key: ["c87ba68bc180312f5716af09a77ca15b", [1, 28, 28, 256], [3, 3, 256, 1], [1, 1, 1, 256], [1, 14, 14, 256]]) ==========
+========== Task 11 (workload key: ["c87ba68bc180312f5716af09a77ca15b", 1, 28, 28, 256, 3, 3, 256, 1, 1, 1, 1, 256, 1, 14, 14, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 256]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 29)) && (i2 >= 1)) && (i2 < 29)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 256, 1]
@@ -675,12 +675,12 @@ placeholder = PLACEHOLDER [1, 1, 1, 256]
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 12 (workload key: ["69115f188984ae34ede37c3b8ca40b43", [1, 7, 7, 1024], [1, 1, 1, 1024]]) ==========
+========== Task 12 (workload key: ["69115f188984ae34ede37c3b8ca40b43", 1, 7, 7, 1024, 1, 1, 1, 1024]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 1024]
tensor(ax0, ax1, ax2, ax3) += placeholder[ax0, ((ax1*7) + rv0), ((ax2*7) + rv1), ax3]
tensor(ax0, ax1, ax2, ax3) = (tensor[ax0, ax1, ax2, ax3]/(float32((select((bool)1, ((ax1 + 1)*7), (((ax1 + 1)*7) + 1)) - (ax1*7)))*float32((select((bool)1, ((ax2 + 1)*7), (((ax2 + 1)*7) + 1)) - (ax2*7)))))
-========== Task 13 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 7, 7, 512], [1, 1, 512, 1024], [1, 1, 1, 1024], [1, 7, 7, 1024]]) ==========
+========== Task 13 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 7, 7, 512, 1, 1, 512, 1024, 1, 1, 1, 1024, 1, 7, 7, 1024]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 1024]
@@ -689,7 +689,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 1024]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 14 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 14, 14, 256], [1, 1, 256, 512], [1, 1, 1, 512], [1, 14, 14, 512]]) ==========
+========== Task 14 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 14, 14, 256, 1, 1, 256, 512, 1, 1, 1, 512, 1, 14, 14, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 512]
@@ -698,7 +698,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 512]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 15 (workload key: ["c87ba68bc180312f5716af09a77ca15b", [1, 14, 14, 512], [3, 3, 512, 1], [1, 1, 1, 512], [1, 7, 7, 512]]) ==========
+========== Task 15 (workload key: ["c87ba68bc180312f5716af09a77ca15b", 1, 14, 14, 512, 3, 3, 512, 1, 1, 1, 1, 512, 1, 7, 7, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 512]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 15)) && (i2 >= 1)) && (i2 < 15)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 512, 1]
@@ -707,7 +707,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 512]
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 16 (workload key: ["06fce76bd84cb904eee50b905ca9449a", [1, 7, 7, 1024], [3, 3, 1024, 1], [1, 1, 1, 1024], [1, 7, 7, 1024]]) ==========
+========== Task 16 (workload key: ["06fce76bd84cb904eee50b905ca9449a", 1, 7, 7, 1024, 3, 3, 1024, 1, 1, 1, 1, 1024, 1, 7, 7, 1024]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 1024]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 8)) && (i2 >= 1)) && (i2 < 8)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 1024, 1]
@@ -716,7 +716,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 1024]
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 17 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 56, 56, 64], [1, 1, 64, 128], [1, 1, 1, 128], [1, 56, 56, 128]]) ==========
+========== Task 17 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 56, 56, 64, 1, 1, 64, 128, 1, 1, 1, 128, 1, 56, 56, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 64, 128]
@@ -725,7 +725,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 128]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 18 (workload key: ["c87ba68bc180312f5716af09a77ca15b", [1, 112, 112, 64], [3, 3, 64, 1], [1, 1, 1, 64], [1, 56, 56, 64]]) ==========
+========== Task 18 (workload key: ["c87ba68bc180312f5716af09a77ca15b", 1, 112, 112, 64, 3, 3, 64, 1, 1, 1, 1, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 112, 112, 64]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 113)) && (i2 >= 1)) && (i2 < 113)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 64, 1]
@@ -734,14 +734,14 @@ placeholder = PLACEHOLDER [1, 1, 1, 64]
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 19 (workload key: ["d7b65649a4dd54becea0a52aabbc5af5", [1, 1000], [1, 1000]]) ==========
+========== Task 19 (workload key: ["d7b65649a4dd54becea0a52aabbc5af5", 1, 1000, 1, 1000]) ==========
placeholder = PLACEHOLDER [1, 1000]
T_softmax_maxelem(i0) max= placeholder[i0, k]
T_softmax_exp(i0, i1) = tir.exp((placeholder[i0, i1] - T_softmax_maxelem[i0]))
T_softmax_expsum(i0) += T_softmax_exp[i0, k]
T_softmax_norm(i0, i1) = (T_softmax_exp[i0, i1]/T_softmax_expsum[i0])
-========== Task 20 (workload key: ["06fce76bd84cb904eee50b905ca9449a", [1, 112, 112, 32], [3, 3, 32, 1], [1, 1, 1, 32], [1, 112, 112, 32]]) ==========
+========== Task 20 (workload key: ["06fce76bd84cb904eee50b905ca9449a", 1, 112, 112, 32, 3, 3, 32, 1, 1, 1, 1, 32, 1, 112, 112, 32]) ==========
placeholder = PLACEHOLDER [1, 112, 112, 32]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 113)) && (i2 >= 1)) && (i2 < 113)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 32, 1]
@@ -750,7 +750,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 32]
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 21 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 112, 112, 32], [1, 1, 32, 64], [1, 1, 1, 64], [1, 112, 112, 64]]) ==========
+========== Task 21 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 112, 112, 32, 1, 1, 32, 64, 1, 1, 1, 64, 1, 112, 112, 64]) ==========
placeholder = PLACEHOLDER [1, 112, 112, 32]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 32, 64]
diff --git a/docs/tutorials/auto_scheduler/tune_network_cuda.html b/docs/tutorials/auto_scheduler/tune_network_cuda.html
index cadb619..4489ca4 100644
--- a/docs/tutorials/auto_scheduler/tune_network_cuda.html
+++ b/docs/tutorials/auto_scheduler/tune_network_cuda.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Auto-scheduling a Neural Network for NVIDIA GPU — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Auto-scheduling a Neural Network for NVIDIA GPU — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -465,7 +465,7 @@ The task scheduler will just optimize this objective.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Extract tasks...
-========== Task 0 (workload key: ["d374e472bd9d8164892b9e28a0a8cb59", [1, 14, 14, 256], [4, 4, 256, 256], [1, 14, 14, 256], [1, 14, 14, 256]]) ==========
+========== Task 0 (workload key: ["d374e472bd9d8164892b9e28a0a8cb59", 1, 14, 14, 256, 4, 4, 256, 256, 1, 14, 14, 256, 1, 14, 14, 256]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 15)) && (i2 >= 1)) && (i2 < 15)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 49), ((floormod(floordiv(p, 7), 7)*2) + eps), ((floormod(p, 7)*2) + nu), ci]
@@ -479,14 +479,14 @@ conv2d_winograd(n, h, w, co) = inverse[floormod(h, 2), floormod(w, 2), ((((n*7)*
placeholder = PLACEHOLDER [1, 14, 14, 256]
T_add(ax0, ax1, ax2, ax3) = (conv2d_winograd[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
-========== Task 1 (workload key: ["d7b65649a4dd54becea0a52aabbc5af5", [1, 1000], [1, 1000]]) ==========
+========== Task 1 (workload key: ["d7b65649a4dd54becea0a52aabbc5af5", 1, 1000, 1, 1000]) ==========
placeholder = PLACEHOLDER [1, 1000]
T_softmax_maxelem(i0) max= placeholder[i0, k]
T_softmax_exp(i0, i1) = tir.exp((placeholder[i0, i1] - T_softmax_maxelem[i0]))
T_softmax_expsum(i0) += T_softmax_exp[i0, k]
T_softmax_norm(i0, i1) = (T_softmax_exp[i0, i1]/T_softmax_expsum[i0])
-========== Task 2 (workload key: ["64b98c71af70a904fdbb81d7d4188d84", [1, 112, 112, 64], [1, 1, 1, 64], [1, 56, 56, 64]]) ==========
+========== Task 2 (workload key: ["64b98c71af70a904fdbb81d7d4188d84", 1, 112, 112, 64, 1, 1, 1, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 112, 112, 64]
pad_temp(ax0, ax1, ax2, ax3) = tir.if_then_else(((((ax1 >= 1) && (ax1 < 113)) && (ax2 >= 1)) && (ax2 < 113)), placeholder[ax0, (ax1 - 1), (ax2 - 1), ax3], -3.40282e+38f)
tensor(ax0, ax1, ax2, ax3) max= pad_temp[ax0, ((ax1*2) + rv0), ((ax2*2) + rv1), ax3]
@@ -494,13 +494,13 @@ placeholder = PLACEHOLDER [1, 1, 1, 64]
T_add(ax0, ax1, ax2, ax3) = (tensor[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 3 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", [1, 56, 56, 64], [1, 1, 64, 128], [1, 28, 28, 128]]) ==========
+========== Task 3 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", 1, 56, 56, 64, 1, 1, 64, 128, 1, 28, 28, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 64, 128]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, ((yy*2) + ry), ((xx*2) + rx), rc]*placeholder[ry, rx, rc, ff])
-========== Task 4 (workload key: ["c4500b4e2fd04e695c32d2f31bbdc14a", [1, 28, 28, 128], [4, 4, 128, 128], [1, 28, 28, 128], [1, 1, 1, 128], [1, 28, 28, 128]]) ==========
+========== Task 4 (workload key: ["c4500b4e2fd04e695c32d2f31bbdc14a", 1, 28, 28, 128, 4, 4, 128, 128, 1, 28, 28, 128, 1, 1, 1, 128, 1, 28, 28, 128]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 29)) && (i2 >= 1)) && (i2 < 29)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 196), ((floormod(floordiv(p, 14), 14)*2) + eps), ((floormod(p, 14)*2) + nu), ci]
@@ -517,13 +517,13 @@ placeholder = PLACEHOLDER [1, 1, 1, 128]
T_add(ax0, ax1, ax2, ax3) = (T_add[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 5 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", [1, 28, 28, 128], [1, 1, 128, 256], [1, 14, 14, 256]]) ==========
+========== Task 5 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", 1, 28, 28, 128, 1, 1, 128, 256, 1, 14, 14, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 128, 256]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, ((yy*2) + ry), ((xx*2) + rx), rc]*placeholder[ry, rx, rc, ff])
-========== Task 6 (workload key: ["e4cdf917b876dbdd64488c3818d9c141", [1, 28, 28, 128], [4, 4, 128, 128], [1, 1, 1, 128], [1, 28, 28, 128]]) ==========
+========== Task 6 (workload key: ["e4cdf917b876dbdd64488c3818d9c141", 1, 28, 28, 128, 4, 4, 128, 128, 1, 1, 1, 128, 1, 28, 28, 128]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 29)) && (i2 >= 1)) && (i2 < 29)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 196), ((floormod(floordiv(p, 14), 14)*2) + eps), ((floormod(p, 14)*2) + nu), ci]
@@ -538,7 +538,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 128]
T_add(ax0, ax1, ax2, ax3) = (conv2d_winograd[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 7 (workload key: ["dac19035dd5fe9424ee8617421b9c817", [1, 28, 28, 128], [4, 4, 128, 128], [1, 28, 28, 128], [1, 28, 28, 128]]) ==========
+========== Task 7 (workload key: ["dac19035dd5fe9424ee8617421b9c817", 1, 28, 28, 128, 4, 4, 128, 128, 1, 28, 28, 128, 1, 28, 28, 128]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 29)) && (i2 >= 1)) && (i2 < 29)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 196), ((floormod(floordiv(p, 14), 14)*2) + eps), ((floormod(p, 14)*2) + nu), ci]
@@ -552,7 +552,7 @@ conv2d_winograd(n, h, w, co) = inverse[floormod(h, 2), floormod(w, 2), ((((n*14)
placeholder = PLACEHOLDER [1, 28, 28, 128]
T_add(ax0, ax1, ax2, ax3) = (conv2d_winograd[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
-========== Task 8 (workload key: ["3ea73fb9b0364374730d09e068821f95", [1, 56, 56, 64], [6, 6, 64, 64], [1, 56, 56, 64], [1, 56, 56, 64]]) ==========
+========== Task 8 (workload key: ["3ea73fb9b0364374730d09e068821f95", 1, 56, 56, 64, 6, 6, 64, 64, 1, 56, 56, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 57)) && (i2 >= 1)) && (i2 < 57)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 196), ((floormod(floordiv(p, 14), 14)*4) + eps), ((floormod(p, 14)*4) + nu), ci]
@@ -566,7 +566,7 @@ conv2d_winograd(n, h, w, co) = inverse[floormod(h, 4), floormod(w, 4), ((((n*14)
placeholder = PLACEHOLDER [1, 56, 56, 64]
T_add(ax0, ax1, ax2, ax3) = (conv2d_winograd[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
-========== Task 9 (workload key: ["d730bcd28f0920f6b97245e2a11bd8d6", [1, 7, 7, 512], [4, 4, 512, 512], [1, 7, 7, 512], [1, 7, 7, 512]]) ==========
+========== Task 9 (workload key: ["d730bcd28f0920f6b97245e2a11bd8d6", 1, 7, 7, 512, 4, 4, 512, 512, 1, 7, 7, 512, 1, 7, 7, 512]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 8)) && (i2 >= 1)) && (i2 < 8)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 16), ((floormod(floordiv(p, 4), 4)*2) + eps), ((floormod(p, 4)*2) + nu), ci]
@@ -580,7 +580,7 @@ conv2d_winograd(n, h, w, co) = inverse[floormod(h, 2), floormod(w, 2), ((((n*4)*
placeholder = PLACEHOLDER [1, 7, 7, 512]
T_add(ax0, ax1, ax2, ax3) = (conv2d_winograd[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
-========== Task 10 (workload key: ["12b88bedece6984af589a28b43e0f3c4", [1, 14, 14, 256], [3, 3, 256, 512], [1, 1, 1, 512], [1, 7, 7, 512]]) ==========
+========== Task 10 (workload key: ["12b88bedece6984af589a28b43e0f3c4", 1, 14, 14, 256, 3, 3, 256, 512, 1, 1, 1, 512, 1, 7, 7, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 15)) && (i2 >= 1)) && (i2 < 15)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 256, 512]
@@ -589,7 +589,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 512]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 11 (workload key: ["1e3c4211ffd2f2db91078ae4d04b779d", [1, 56, 56, 64], [6, 6, 64, 64], [1, 56, 56, 64], [1, 1, 1, 64], [1, 56, 56, 64]]) ==========
+========== Task 11 (workload key: ["1e3c4211ffd2f2db91078ae4d04b779d", 1, 56, 56, 64, 6, 6, 64, 64, 1, 56, 56, 64, 1, 1, 1, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 57)) && (i2 >= 1)) && (i2 < 57)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 196), ((floormod(floordiv(p, 14), 14)*4) + eps), ((floormod(p, 14)*4) + nu), ci]
@@ -606,12 +606,12 @@ placeholder = PLACEHOLDER [1, 1, 1, 64]
T_add(ax0, ax1, ax2, ax3) = (T_add[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 12 (workload key: ["69115f188984ae34ede37c3b8ca40b43", [1, 7, 7, 512], [1, 1, 1, 512]]) ==========
+========== Task 12 (workload key: ["69115f188984ae34ede37c3b8ca40b43", 1, 7, 7, 512, 1, 1, 1, 512]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
tensor(ax0, ax1, ax2, ax3) += placeholder[ax0, ((ax1*7) + rv0), ((ax2*7) + rv1), ax3]
tensor(ax0, ax1, ax2, ax3) = (tensor[ax0, ax1, ax2, ax3]/(float32((select((bool)1, ((ax1 + 1)*7), (((ax1 + 1)*7) + 1)) - (ax1*7)))*float32((select((bool)1, ((ax2 + 1)*7), (((ax2 + 1)*7) + 1)) - (ax2*7)))))
-========== Task 13 (workload key: ["12b88bedece6984af589a28b43e0f3c4", [1, 56, 56, 64], [3, 3, 64, 128], [1, 1, 1, 128], [1, 28, 28, 128]]) ==========
+========== Task 13 (workload key: ["12b88bedece6984af589a28b43e0f3c4", 1, 56, 56, 64, 3, 3, 64, 128, 1, 1, 1, 128, 1, 28, 28, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 57)) && (i2 >= 1)) && (i2 < 57)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 64, 128]
@@ -620,7 +620,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 128]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 14 (workload key: ["f3b6c10fcc6ce01ff01add933e4d21e9", [1, 14, 14, 256], [4, 4, 256, 256], [1, 14, 14, 256], [1, 1, 1, 256], [1, 14, 14, 256]]) ==========
+========== Task 14 (workload key: ["f3b6c10fcc6ce01ff01add933e4d21e9", 1, 14, 14, 256, 4, 4, 256, 256, 1, 14, 14, 256, 1, 1, 1, 256, 1, 14, 14, 256]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 15)) && (i2 >= 1)) && (i2 < 15)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 49), ((floormod(floordiv(p, 7), 7)*2) + eps), ((floormod(p, 7)*2) + nu), ci]
@@ -637,7 +637,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 256]
T_add(ax0, ax1, ax2, ax3) = (T_add[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 15 (workload key: ["b8b52b9be9df6102466a22a014c44c1f", [1, 14, 14, 256], [4, 4, 256, 256], [1, 1, 1, 256], [1, 14, 14, 256]]) ==========
+========== Task 15 (workload key: ["b8b52b9be9df6102466a22a014c44c1f", 1, 14, 14, 256, 4, 4, 256, 256, 1, 1, 1, 256, 1, 14, 14, 256]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 15)) && (i2 >= 1)) && (i2 < 15)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 49), ((floormod(floordiv(p, 7), 7)*2) + eps), ((floormod(p, 7)*2) + nu), ci]
@@ -652,7 +652,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 256]
T_add(ax0, ax1, ax2, ax3) = (conv2d_winograd[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 16 (workload key: ["12b88bedece6984af589a28b43e0f3c4", [1, 28, 28, 128], [3, 3, 128, 256], [1, 1, 1, 256], [1, 14, 14, 256]]) ==========
+========== Task 16 (workload key: ["12b88bedece6984af589a28b43e0f3c4", 1, 28, 28, 128, 3, 3, 128, 256, 1, 1, 1, 256, 1, 14, 14, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 29)) && (i2 >= 1)) && (i2 < 29)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 128, 256]
@@ -661,7 +661,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 256]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 17 (workload key: ["ad6cecbf5d85cb1cda3c2bb7af170211", [1, 7, 7, 512], [4, 4, 512, 512], [1, 7, 7, 512], [1, 1, 1, 512], [1, 1, 1, 512], [1, 7, 7, 512]]) ==========
+========== Task 17 (workload key: ["ad6cecbf5d85cb1cda3c2bb7af170211", 1, 7, 7, 512, 4, 4, 512, 512, 1, 7, 7, 512, 1, 1, 1, 512, 1, 1, 1, 512, 1, 7, 7, 512]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 8)) && (i2 >= 1)) && (i2 < 8)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 16), ((floormod(floordiv(p, 4), 4)*2) + eps), ((floormod(p, 4)*2) + nu), ci]
@@ -680,7 +680,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 512]
T_add(ax0, ax1, ax2, ax3) = (T_multiply[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 18 (workload key: ["3a69f9fbc63760d99e36b4c17b3bfc57", [1, 7, 7, 512], [4, 4, 512, 512], [1, 1, 1, 512], [1, 7, 7, 512]]) ==========
+========== Task 18 (workload key: ["3a69f9fbc63760d99e36b4c17b3bfc57", 1, 7, 7, 512, 4, 4, 512, 512, 1, 1, 1, 512, 1, 7, 7, 512]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 8)) && (i2 >= 1)) && (i2 < 8)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 16), ((floormod(floordiv(p, 4), 4)*2) + eps), ((floormod(p, 4)*2) + nu), ci]
@@ -695,7 +695,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 512]
T_add(ax0, ax1, ax2, ax3) = (conv2d_winograd[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 19 (workload key: ["12b88bedece6984af589a28b43e0f3c4", [1, 224, 224, 3], [7, 7, 3, 64], [1, 1, 1, 64], [1, 112, 112, 64]]) ==========
+========== Task 19 (workload key: ["12b88bedece6984af589a28b43e0f3c4", 1, 224, 224, 3, 7, 7, 3, 64, 1, 1, 1, 64, 1, 112, 112, 64]) ==========
placeholder = PLACEHOLDER [1, 224, 224, 3]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 3) && (i1 < 227)) && (i2 >= 3)) && (i2 < 227)), placeholder[i0, (i1 - 3), (i2 - 3), i3], 0f)
placeholder = PLACEHOLDER [7, 7, 3, 64]
@@ -704,20 +704,20 @@ placeholder = PLACEHOLDER [1, 1, 1, 64]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 20 (workload key: ["7006235cfc29b73be524cf390ed5a977", [1, 56, 56, 64], [1, 1, 64, 64], [1, 56, 56, 64]]) ==========
+========== Task 20 (workload key: ["7006235cfc29b73be524cf390ed5a977", 1, 56, 56, 64, 1, 1, 64, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 64, 64]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
-========== Task 21 (workload key: ["7d44c6e3c81cd80f61ff2265b2bae89a", [1, 512], [1000, 512], [1, 1000], [1, 1000]]) ==========
+========== Task 21 (workload key: ["7d44c6e3c81cd80f61ff2265b2bae89a", 1, 512, 1000, 512, 1, 1000, 1, 1000]) ==========
placeholder = PLACEHOLDER [1, 512]
placeholder = PLACEHOLDER [1000, 512]
T_matmul_NT(i, j) += (placeholder[i, k]*placeholder[j, k])
placeholder = PLACEHOLDER [1, 1000]
T_add(ax0, ax1) = (T_matmul_NT[ax0, ax1] + placeholder[ax0, ax1])
-========== Task 22 (workload key: ["b818b53148cd450f86569dfc3e04cb8a", [1, 56, 56, 64], [6, 6, 64, 64], [1, 1, 1, 64], [1, 56, 56, 64]]) ==========
+========== Task 22 (workload key: ["b818b53148cd450f86569dfc3e04cb8a", 1, 56, 56, 64, 6, 6, 64, 64, 1, 1, 1, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 57)) && (i2 >= 1)) && (i2 < 57)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 196), ((floormod(floordiv(p, 14), 14)*4) + eps), ((floormod(p, 14)*4) + nu), ci]
@@ -732,7 +732,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 64]
T_add(ax0, ax1, ax2, ax3) = (conv2d_winograd[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 23 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", [1, 14, 14, 256], [1, 1, 256, 512], [1, 7, 7, 512]]) ==========
+========== Task 23 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", 1, 14, 14, 256, 1, 1, 256, 512, 1, 7, 7, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 512]
@@ -868,7 +868,7 @@ 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)
- 1.6973 1.6973 1.6973 1.6972 0.0000
+ 3.1068 3.1042 3.1168 3.0995 0.0073
</pre></div>
</div>
</div>
diff --git a/docs/tutorials/auto_scheduler/tune_network_mali.html b/docs/tutorials/auto_scheduler/tune_network_mali.html
index 729ed3b..0e38eca 100644
--- a/docs/tutorials/auto_scheduler/tune_network_mali.html
+++ b/docs/tutorials/auto_scheduler/tune_network_mali.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Auto-scheduling a Neural Network for mali GPU — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Auto-scheduling a Neural Network for mali GPU — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -480,14 +480,14 @@ The task scheduler will just optimize this objective.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Extract tasks...
-========== Task 0 (workload key: ["7d44c6e3c81cd80f61ff2265b2bae89a", [1, 1024], [1000, 1024], [1, 1000], [1, 1000]]) ==========
+========== Task 0 (workload key: ["7d44c6e3c81cd80f61ff2265b2bae89a", 1, 1024, 1000, 1024, 1, 1000, 1, 1000]) ==========
placeholder = PLACEHOLDER [1, 1024]
placeholder = PLACEHOLDER [1000, 1024]
T_matmul_NT(i, j) += (placeholder[i, k]*placeholder[j, k])
placeholder = PLACEHOLDER [1, 1000]
T_add(ax0, ax1) = (T_matmul_NT[ax0, ax1] + placeholder[ax0, ax1])
-========== Task 1 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 28, 28, 128], [1, 1, 128, 256], [1, 1, 1, 256], [1, 28, 28, 256]]) ==========
+========== Task 1 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 28, 28, 128, 1, 1, 128, 256, 1, 1, 1, 256, 1, 28, 28, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 128, 256]
@@ -496,7 +496,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 256]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 2 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 28, 28, 256], [1, 1, 256, 256], [1, 1, 1, 256], [1, 28, 28, 256]]) ==========
+========== Task 2 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 28, 28, 256, 1, 1, 256, 256, 1, 1, 1, 256, 1, 28, 28, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 256]
@@ -505,7 +505,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 256]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 3 (workload key: ["06fce76bd84cb904eee50b905ca9449a", [1, 14, 14, 512], [3, 3, 512, 1], [1, 1, 1, 512], [1, 14, 14, 512]]) ==========
+========== Task 3 (workload key: ["06fce76bd84cb904eee50b905ca9449a", 1, 14, 14, 512, 3, 3, 512, 1, 1, 1, 1, 512, 1, 14, 14, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 512]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 15)) && (i2 >= 1)) && (i2 < 15)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 512, 1]
@@ -514,7 +514,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 512]
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 4 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 14, 14, 512], [1, 1, 512, 512], [1, 1, 1, 512], [1, 14, 14, 512]]) ==========
+========== Task 4 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 14, 14, 512, 1, 1, 512, 512, 1, 1, 1, 512, 1, 14, 14, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 512]
@@ -523,7 +523,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 512]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 5 (workload key: ["c87ba68bc180312f5716af09a77ca15b", [1, 56, 56, 128], [3, 3, 128, 1], [1, 1, 1, 128], [1, 28, 28, 128]]) ==========
+========== Task 5 (workload key: ["c87ba68bc180312f5716af09a77ca15b", 1, 56, 56, 128, 3, 3, 128, 1, 1, 1, 1, 128, 1, 28, 28, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 128]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 57)) && (i2 >= 1)) && (i2 < 57)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 128, 1]
@@ -532,7 +532,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 128]
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 6 (workload key: ["98418eda02701ddd175ad50e364a0638", [1, 224, 224, 3], [3, 3, 3, 32], [1, 112, 1, 1], [1, 112, 1, 1], [1, 112, 112, 32]]) ==========
+========== Task 6 (workload key: ["98418eda02701ddd175ad50e364a0638", 1, 224, 224, 3, 3, 3, 3, 32, 1, 112, 1, 1, 1, 112, 1, 1, 1, 112, 112, 32]) ==========
placeholder = PLACEHOLDER [1, 224, 224, 3]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 225)) && (i2 >= 1)) && (i2 < 225)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 3, 32]
@@ -543,7 +543,7 @@ placeholder = PLACEHOLDER [1, 112, 1, 1]
T_add(ax0, ax1, ax2, ax3) = (T_multiply[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, 0, 0])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 7 (workload key: ["06fce76bd84cb904eee50b905ca9449a", [1, 28, 28, 256], [3, 3, 256, 1], [1, 1, 1, 256], [1, 28, 28, 256]]) ==========
+========== Task 7 (workload key: ["06fce76bd84cb904eee50b905ca9449a", 1, 28, 28, 256, 3, 3, 256, 1, 1, 1, 1, 256, 1, 28, 28, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 256]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 29)) && (i2 >= 1)) && (i2 < 29)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 256, 1]
@@ -552,7 +552,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 256]
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 8 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 7, 7, 1024], [1, 1, 1024, 1024], [1, 1, 1, 1024], [1, 7, 7, 1024]]) ==========
+========== Task 8 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 7, 7, 1024, 1, 1, 1024, 1024, 1, 1, 1, 1024, 1, 7, 7, 1024]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 1024]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 1024, 1024]
@@ -561,7 +561,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 1024]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 9 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 56, 56, 128], [1, 1, 128, 128], [1, 1, 1, 128], [1, 56, 56, 128]]) ==========
+========== Task 9 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 56, 56, 128, 1, 1, 128, 128, 1, 1, 1, 128, 1, 56, 56, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 128]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 128, 128]
@@ -570,7 +570,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 128]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 10 (workload key: ["06fce76bd84cb904eee50b905ca9449a", [1, 56, 56, 128], [3, 3, 128, 1], [1, 1, 1, 128], [1, 56, 56, 128]]) ==========
+========== Task 10 (workload key: ["06fce76bd84cb904eee50b905ca9449a", 1, 56, 56, 128, 3, 3, 128, 1, 1, 1, 1, 128, 1, 56, 56, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 128]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 57)) && (i2 >= 1)) && (i2 < 57)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 128, 1]
@@ -579,7 +579,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 128]
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 11 (workload key: ["c87ba68bc180312f5716af09a77ca15b", [1, 28, 28, 256], [3, 3, 256, 1], [1, 1, 1, 256], [1, 14, 14, 256]]) ==========
+========== Task 11 (workload key: ["c87ba68bc180312f5716af09a77ca15b", 1, 28, 28, 256, 3, 3, 256, 1, 1, 1, 1, 256, 1, 14, 14, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 256]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 29)) && (i2 >= 1)) && (i2 < 29)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 256, 1]
@@ -588,7 +588,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 256]
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 12 (workload key: ["c87ba68bc180312f5716af09a77ca15b", [1, 14, 14, 512], [3, 3, 512, 1], [1, 1, 1, 512], [1, 7, 7, 512]]) ==========
+========== Task 12 (workload key: ["c87ba68bc180312f5716af09a77ca15b", 1, 14, 14, 512, 3, 3, 512, 1, 1, 1, 1, 512, 1, 7, 7, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 512]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 15)) && (i2 >= 1)) && (i2 < 15)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 512, 1]
@@ -597,7 +597,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 512]
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 13 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 14, 14, 256], [1, 1, 256, 512], [1, 1, 1, 512], [1, 14, 14, 512]]) ==========
+========== Task 13 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 14, 14, 256, 1, 1, 256, 512, 1, 1, 1, 512, 1, 14, 14, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 512]
@@ -606,12 +606,12 @@ placeholder = PLACEHOLDER [1, 1, 1, 512]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 14 (workload key: ["69115f188984ae34ede37c3b8ca40b43", [1, 7, 7, 1024], [1, 1, 1, 1024]]) ==========
+========== Task 14 (workload key: ["69115f188984ae34ede37c3b8ca40b43", 1, 7, 7, 1024, 1, 1, 1, 1024]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 1024]
tensor(ax0, ax1, ax2, ax3) += placeholder[ax0, ((ax1*7) + rv0), ((ax2*7) + rv1), ax3]
tensor(ax0, ax1, ax2, ax3) = (tensor[ax0, ax1, ax2, ax3]/(float32((select((bool)1, ((ax1 + 1)*7), (((ax1 + 1)*7) + 1)) - (ax1*7)))*float32((select((bool)1, ((ax2 + 1)*7), (((ax2 + 1)*7) + 1)) - (ax2*7)))))
-========== Task 15 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 7, 7, 512], [1, 1, 512, 1024], [1, 1, 1, 1024], [1, 7, 7, 1024]]) ==========
+========== Task 15 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 7, 7, 512, 1, 1, 512, 1024, 1, 1, 1, 1024, 1, 7, 7, 1024]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 1024]
@@ -620,7 +620,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 1024]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 16 (workload key: ["06fce76bd84cb904eee50b905ca9449a", [1, 7, 7, 1024], [3, 3, 1024, 1], [1, 1, 1, 1024], [1, 7, 7, 1024]]) ==========
+========== Task 16 (workload key: ["06fce76bd84cb904eee50b905ca9449a", 1, 7, 7, 1024, 3, 3, 1024, 1, 1, 1, 1, 1024, 1, 7, 7, 1024]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 1024]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 8)) && (i2 >= 1)) && (i2 < 8)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 1024, 1]
@@ -629,7 +629,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 1024]
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 17 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 56, 56, 64], [1, 1, 64, 128], [1, 1, 1, 128], [1, 56, 56, 128]]) ==========
+========== Task 17 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 56, 56, 64, 1, 1, 64, 128, 1, 1, 1, 128, 1, 56, 56, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 64, 128]
@@ -638,7 +638,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 128]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 18 (workload key: ["c87ba68bc180312f5716af09a77ca15b", [1, 112, 112, 64], [3, 3, 64, 1], [1, 1, 1, 64], [1, 56, 56, 64]]) ==========
+========== Task 18 (workload key: ["c87ba68bc180312f5716af09a77ca15b", 1, 112, 112, 64, 3, 3, 64, 1, 1, 1, 1, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 112, 112, 64]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 113)) && (i2 >= 1)) && (i2 < 113)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 64, 1]
@@ -647,14 +647,14 @@ placeholder = PLACEHOLDER [1, 1, 1, 64]
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 19 (workload key: ["d7b65649a4dd54becea0a52aabbc5af5", [1, 1000], [1, 1000]]) ==========
+========== Task 19 (workload key: ["d7b65649a4dd54becea0a52aabbc5af5", 1, 1000, 1, 1000]) ==========
placeholder = PLACEHOLDER [1, 1000]
T_softmax_maxelem(i0) max= placeholder[i0, k]
T_softmax_exp(i0, i1) = tir.exp((placeholder[i0, i1] - T_softmax_maxelem[i0]))
T_softmax_expsum(i0) += T_softmax_exp[i0, k]
T_softmax_norm(i0, i1) = (T_softmax_exp[i0, i1]/T_softmax_expsum[i0])
-========== Task 20 (workload key: ["06fce76bd84cb904eee50b905ca9449a", [1, 112, 112, 32], [3, 3, 32, 1], [1, 1, 1, 32], [1, 112, 112, 32]]) ==========
+========== Task 20 (workload key: ["06fce76bd84cb904eee50b905ca9449a", 1, 112, 112, 32, 3, 3, 32, 1, 1, 1, 1, 32, 1, 112, 112, 32]) ==========
placeholder = PLACEHOLDER [1, 112, 112, 32]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 113)) && (i2 >= 1)) && (i2 < 113)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 32, 1]
@@ -663,7 +663,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 32]
T_add(ax0, ax1, ax2, ax3) = (DepthwiseConv2d[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 21 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 112, 112, 32], [1, 1, 32, 64], [1, 1, 1, 64], [1, 112, 112, 64]]) ==========
+========== Task 21 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 112, 112, 32, 1, 1, 32, 64, 1, 1, 1, 64, 1, 112, 112, 64]) ==========
placeholder = PLACEHOLDER [1, 112, 112, 32]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 32, 64]
diff --git a/docs/tutorials/auto_scheduler/tune_network_x86.html b/docs/tutorials/auto_scheduler/tune_network_x86.html
index 5832ae7..cc172ec 100644
--- a/docs/tutorials/auto_scheduler/tune_network_x86.html
+++ b/docs/tutorials/auto_scheduler/tune_network_x86.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Auto-scheduling a Neural Network for x86 CPU — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Auto-scheduling a Neural Network for x86 CPU — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -488,13 +488,13 @@ The task scheduler will just optimize this objective.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get model...
Extract tasks...
-========== Task 0 (workload key: ["7006235cfc29b73be524cf390ed5a977", [1, 56, 56, 64], [1, 1, 64, 256], [1, 56, 56, 256]]) ==========
+========== Task 0 (workload key: ["7006235cfc29b73be524cf390ed5a977", 1, 56, 56, 64, 1, 1, 64, 256, 1, 56, 56, 256]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 64, 256]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
-========== Task 1 (workload key: ["1b524af89dd867d26059e1f621cf987c", [1, 28, 28, 128], [1, 1, 128, 512], [1, 28, 28, 512], [1, 1, 1, 512], [1, 28, 28, 512]]) ==========
+========== Task 1 (workload key: ["1b524af89dd867d26059e1f621cf987c", 1, 28, 28, 128, 1, 1, 128, 512, 1, 28, 28, 512, 1, 1, 1, 512, 1, 28, 28, 512]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 128, 512]
@@ -505,7 +505,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 512]
T_add(ax0, ax1, ax2, ax3) = (T_add[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 2 (workload key: ["12b88bedece6984af589a28b43e0f3c4", [1, 224, 224, 3], [7, 7, 3, 64], [1, 1, 1, 64], [1, 112, 112, 64]]) ==========
+========== Task 2 (workload key: ["12b88bedece6984af589a28b43e0f3c4", 1, 224, 224, 3, 7, 7, 3, 64, 1, 1, 1, 64, 1, 112, 112, 64]) ==========
placeholder = PLACEHOLDER [1, 224, 224, 3]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 3) && (i1 < 227)) && (i2 >= 3)) && (i2 < 227)), placeholder[i0, (i1 - 3), (i2 - 3), i3], 0f)
placeholder = PLACEHOLDER [7, 7, 3, 64]
@@ -514,7 +514,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 64]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 3 (workload key: ["1cc666833c122282e3fcf3595901b12b", [1, 28, 28, 128], [1, 1, 128, 512], [1, 28, 28, 512], [1, 28, 28, 512]]) ==========
+========== Task 3 (workload key: ["1cc666833c122282e3fcf3595901b12b", 1, 28, 28, 128, 1, 1, 128, 512, 1, 28, 28, 512, 1, 28, 28, 512]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 128, 512]
@@ -522,7 +522,7 @@ Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*place
placeholder = PLACEHOLDER [1, 28, 28, 512]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
-========== Task 4 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 56, 56, 256], [1, 1, 256, 64], [1, 1, 1, 64], [1, 56, 56, 64]]) ==========
+========== Task 4 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 56, 56, 256, 1, 1, 256, 64, 1, 1, 1, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 64]
@@ -531,7 +531,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 64]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 5 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 28, 28, 512], [1, 1, 512, 128], [1, 1, 1, 128], [1, 28, 28, 128]]) ==========
+========== Task 5 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 28, 28, 512, 1, 1, 512, 128, 1, 1, 1, 128, 1, 28, 28, 128]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 128]
@@ -540,7 +540,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 128]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 6 (workload key: ["de7d1695278cf52778b038e6573d7626", [1, 28, 28, 512], [1, 1, 512, 256], [1, 1, 1, 256], [1, 14, 14, 256]]) ==========
+========== Task 6 (workload key: ["de7d1695278cf52778b038e6573d7626", 1, 28, 28, 512, 1, 1, 512, 256, 1, 1, 1, 256, 1, 14, 14, 256]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 256]
@@ -549,13 +549,13 @@ placeholder = PLACEHOLDER [1, 1, 1, 256]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 7 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", [1, 56, 56, 256], [1, 1, 256, 512], [1, 28, 28, 512]]) ==========
+========== Task 7 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", 1, 56, 56, 256, 1, 1, 256, 512, 1, 28, 28, 512]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 512]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, ((yy*2) + ry), ((xx*2) + rx), rc]*placeholder[ry, rx, rc, ff])
-========== Task 8 (workload key: ["1cc666833c122282e3fcf3595901b12b", [1, 14, 14, 256], [1, 1, 256, 1024], [1, 14, 14, 1024], [1, 14, 14, 1024]]) ==========
+========== Task 8 (workload key: ["1cc666833c122282e3fcf3595901b12b", 1, 14, 14, 256, 1, 1, 256, 1024, 1, 14, 14, 1024, 1, 14, 14, 1024]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 1024]
@@ -563,7 +563,7 @@ Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*place
placeholder = PLACEHOLDER [1, 14, 14, 1024]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
-========== Task 9 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 56, 56, 64], [1, 1, 64, 64], [1, 1, 1, 64], [1, 56, 56, 64]]) ==========
+========== Task 9 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 56, 56, 64, 1, 1, 64, 64, 1, 1, 1, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 64, 64]
@@ -572,13 +572,13 @@ placeholder = PLACEHOLDER [1, 1, 1, 64]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 10 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", [1, 28, 28, 512], [1, 1, 512, 1024], [1, 14, 14, 1024]]) ==========
+========== Task 10 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", 1, 28, 28, 512, 1, 1, 512, 1024, 1, 14, 14, 1024]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 1024]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, ((yy*2) + ry), ((xx*2) + rx), rc]*placeholder[ry, rx, rc, ff])
-========== Task 11 (workload key: ["2350d19dc42a0665244368384c66b3a5", [1, 7, 7, 512], [3, 3, 512, 512], [1, 1, 1, 512], [1, 7, 7, 512]]) ==========
+========== Task 11 (workload key: ["2350d19dc42a0665244368384c66b3a5", 1, 7, 7, 512, 3, 3, 512, 512, 1, 1, 1, 512, 1, 7, 7, 512]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 8)) && (i2 >= 1)) && (i2 < 8)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 512, 512]
@@ -587,7 +587,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 512]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 12 (workload key: ["1b524af89dd867d26059e1f621cf987c", [1, 56, 56, 64], [1, 1, 64, 256], [1, 56, 56, 256], [1, 1, 1, 256], [1, 56, 56, 256]]) ==========
+========== Task 12 (workload key: ["1b524af89dd867d26059e1f621cf987c", 1, 56, 56, 64, 1, 1, 64, 256, 1, 56, 56, 256, 1, 1, 1, 256, 1, 56, 56, 256]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 64, 256]
@@ -598,7 +598,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 256]
T_add(ax0, ax1, ax2, ax3) = (T_add[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 13 (workload key: ["2350d19dc42a0665244368384c66b3a5", [1, 56, 56, 64], [3, 3, 64, 64], [1, 1, 1, 64], [1, 56, 56, 64]]) ==========
+========== Task 13 (workload key: ["2350d19dc42a0665244368384c66b3a5", 1, 56, 56, 64, 3, 3, 64, 64, 1, 1, 1, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 57)) && (i2 >= 1)) && (i2 < 57)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 64, 64]
@@ -607,7 +607,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 64]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 14 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 14, 14, 1024], [1, 1, 1024, 256], [1, 1, 1, 256], [1, 14, 14, 256]]) ==========
+========== Task 14 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 14, 14, 1024, 1, 1, 1024, 256, 1, 1, 1, 256, 1, 14, 14, 256]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 1024]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 1024, 256]
@@ -616,12 +616,12 @@ placeholder = PLACEHOLDER [1, 1, 1, 256]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 15 (workload key: ["69115f188984ae34ede37c3b8ca40b43", [1, 7, 7, 2048], [1, 1, 1, 2048]]) ==========
+========== Task 15 (workload key: ["69115f188984ae34ede37c3b8ca40b43", 1, 7, 7, 2048, 1, 1, 1, 2048]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 2048]
tensor(ax0, ax1, ax2, ax3) += placeholder[ax0, ((ax1*7) + rv0), ((ax2*7) + rv1), ax3]
tensor(ax0, ax1, ax2, ax3) = (tensor[ax0, ax1, ax2, ax3]/(float32((select((bool)1, ((ax1 + 1)*7), (((ax1 + 1)*7) + 1)) - (ax1*7)))*float32((select((bool)1, ((ax2 + 1)*7), (((ax2 + 1)*7) + 1)) - (ax2*7)))))
-========== Task 16 (workload key: ["1cc666833c122282e3fcf3595901b12b", [1, 56, 56, 64], [1, 1, 64, 256], [1, 56, 56, 256], [1, 56, 56, 256]]) ==========
+========== Task 16 (workload key: ["1cc666833c122282e3fcf3595901b12b", 1, 56, 56, 64, 1, 1, 64, 256, 1, 56, 56, 256, 1, 56, 56, 256]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 64, 256]
@@ -629,7 +629,7 @@ Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*place
placeholder = PLACEHOLDER [1, 56, 56, 256]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
-========== Task 17 (workload key: ["de7d1695278cf52778b038e6573d7626", [1, 56, 56, 256], [1, 1, 256, 128], [1, 1, 1, 128], [1, 28, 28, 128]]) ==========
+========== Task 17 (workload key: ["de7d1695278cf52778b038e6573d7626", 1, 56, 56, 256, 1, 1, 256, 128, 1, 1, 1, 128, 1, 28, 28, 128]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 128]
@@ -638,7 +638,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 128]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 18 (workload key: ["de7d1695278cf52778b038e6573d7626", [1, 14, 14, 1024], [1, 1, 1024, 512], [1, 1, 1, 512], [1, 7, 7, 512]]) ==========
+========== Task 18 (workload key: ["de7d1695278cf52778b038e6573d7626", 1, 14, 14, 1024, 1, 1, 1024, 512, 1, 1, 1, 512, 1, 7, 7, 512]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 1024]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 1024, 512]
@@ -647,7 +647,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 512]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 19 (workload key: ["ecec634b4882c5731f86cce3109db636", [1, 28, 28, 128], [6, 6, 128, 128], [1, 1, 1, 128], [1, 28, 28, 128]]) ==========
+========== Task 19 (workload key: ["ecec634b4882c5731f86cce3109db636", 1, 28, 28, 128, 6, 6, 128, 128, 1, 1, 1, 128, 1, 28, 28, 128]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 29)) && (i2 >= 1)) && (i2 < 29)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 49), ((floormod(floordiv(p, 7), 7)*4) + eps), ((floormod(p, 7)*4) + nu), ci]
@@ -662,7 +662,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 128]
T_add(ax0, ax1, ax2, ax3) = (conv2d_winograd[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 20 (workload key: ["1cc666833c122282e3fcf3595901b12b", [1, 7, 7, 512], [1, 1, 512, 2048], [1, 7, 7, 2048], [1, 7, 7, 2048]]) ==========
+========== Task 20 (workload key: ["1cc666833c122282e3fcf3595901b12b", 1, 7, 7, 512, 1, 1, 512, 2048, 1, 7, 7, 2048, 1, 7, 7, 2048]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 2048]
@@ -670,7 +670,7 @@ Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*place
placeholder = PLACEHOLDER [1, 7, 7, 2048]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
-========== Task 21 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", [1, 7, 7, 2048], [1, 1, 2048, 512], [1, 1, 1, 512], [1, 7, 7, 512]]) ==========
+========== Task 21 (workload key: ["6b7583cf23c7c37d3212cad9d06e58c1", 1, 7, 7, 2048, 1, 1, 2048, 512, 1, 1, 1, 512, 1, 7, 7, 512]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 2048]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 2048, 512]
@@ -679,7 +679,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 512]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 22 (workload key: ["875556d12d0be2269206a7775d5296a6", [1, 7, 7, 512], [1, 1, 512, 2048], [1, 7, 7, 2048], [1, 1, 1, 2048], [1, 1, 1, 2048], [1, 7, 7, 2048]]) ==========
+========== Task 22 (workload key: ["875556d12d0be2269206a7775d5296a6", 1, 7, 7, 512, 1, 1, 512, 2048, 1, 7, 7, 2048, 1, 1, 1, 2048, 1, 1, 1, 2048, 1, 7, 7, 2048]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 2048]
@@ -692,7 +692,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 2048]
T_add(ax0, ax1, ax2, ax3) = (T_multiply[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 23 (workload key: ["c68f92478eb18145106184c587d212b6", [1, 14, 14, 256], [6, 6, 256, 256], [1, 1, 1, 256], [1, 14, 14, 256]]) ==========
+========== Task 23 (workload key: ["c68f92478eb18145106184c587d212b6", 1, 14, 14, 256, 6, 6, 256, 256, 1, 1, 1, 256, 1, 14, 14, 256]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
data_pad(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 15)) && (i2 >= 1)) && (i2 < 15)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
input_tile(eps, nu, p, ci) = data_pad[floordiv(p, 16), ((floormod(floordiv(p, 4), 4)*4) + eps), ((floormod(p, 4)*4) + nu), ci]
@@ -707,21 +707,21 @@ placeholder = PLACEHOLDER [1, 1, 1, 256]
T_add(ax0, ax1, ax2, ax3) = (conv2d_winograd[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 24 (workload key: ["7d44c6e3c81cd80f61ff2265b2bae89a", [1, 2048], [1000, 2048], [1, 1000], [1, 1000]]) ==========
+========== Task 24 (workload key: ["7d44c6e3c81cd80f61ff2265b2bae89a", 1, 2048, 1000, 2048, 1, 1000, 1, 1000]) ==========
placeholder = PLACEHOLDER [1, 2048]
placeholder = PLACEHOLDER [1000, 2048]
T_matmul_NT(i, j) += (placeholder[i, k]*placeholder[j, k])
placeholder = PLACEHOLDER [1, 1000]
T_add(ax0, ax1) = (T_matmul_NT[ax0, ax1] + placeholder[ax0, ax1])
-========== Task 25 (workload key: ["d7b65649a4dd54becea0a52aabbc5af5", [1, 1000], [1, 1000]]) ==========
+========== Task 25 (workload key: ["d7b65649a4dd54becea0a52aabbc5af5", 1, 1000, 1, 1000]) ==========
placeholder = PLACEHOLDER [1, 1000]
T_softmax_maxelem(i0) max= placeholder[i0, k]
T_softmax_exp(i0, i1) = tir.exp((placeholder[i0, i1] - T_softmax_maxelem[i0]))
T_softmax_expsum(i0) += T_softmax_exp[i0, k]
T_softmax_norm(i0, i1) = (T_softmax_exp[i0, i1]/T_softmax_expsum[i0])
-========== Task 26 (workload key: ["64b98c71af70a904fdbb81d7d4188d84", [1, 112, 112, 64], [1, 1, 1, 64], [1, 56, 56, 64]]) ==========
+========== Task 26 (workload key: ["64b98c71af70a904fdbb81d7d4188d84", 1, 112, 112, 64, 1, 1, 1, 64, 1, 56, 56, 64]) ==========
placeholder = PLACEHOLDER [1, 112, 112, 64]
pad_temp(ax0, ax1, ax2, ax3) = tir.if_then_else(((((ax1 >= 1) && (ax1 < 113)) && (ax2 >= 1)) && (ax2 < 113)), placeholder[ax0, (ax1 - 1), (ax2 - 1), ax3], -3.40282e+38f)
tensor(ax0, ax1, ax2, ax3) max= pad_temp[ax0, ((ax1*2) + rv0), ((ax2*2) + rv1), ax3]
@@ -729,7 +729,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 64]
T_add(ax0, ax1, ax2, ax3) = (tensor[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 27 (workload key: ["1b524af89dd867d26059e1f621cf987c", [1, 14, 14, 256], [1, 1, 256, 1024], [1, 14, 14, 1024], [1, 1, 1, 1024], [1, 14, 14, 1024]]) ==========
+========== Task 27 (workload key: ["1b524af89dd867d26059e1f621cf987c", 1, 14, 14, 256, 1, 1, 256, 1024, 1, 14, 14, 1024, 1, 1, 1, 1024, 1, 14, 14, 1024]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 1024]
@@ -740,7 +740,7 @@ placeholder = PLACEHOLDER [1, 1, 1, 1024]
T_add(ax0, ax1, ax2, ax3) = (T_add[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
-========== Task 28 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", [1, 14, 14, 1024], [1, 1, 1024, 2048], [1, 7, 7, 2048]]) ==========
+========== Task 28 (workload key: ["f4380bb1dc62422a69ad4a1a9771f927", 1, 14, 14, 1024, 1, 1, 1024, 2048, 1, 7, 7, 2048]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 1024]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 1024, 2048]
@@ -887,7 +887,7 @@ 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)
- 561.6463 561.3978 563.6430 559.8980 1.5390
+ 552.8841 552.2991 554.2759 552.0773 0.9883
</pre></div>
</div>
</div>
diff --git a/docs/tutorials/auto_scheduler/tune_sparse_x86.html b/docs/tutorials/auto_scheduler/tune_sparse_x86.html
index 1462151..0509a01 100644
--- a/docs/tutorials/auto_scheduler/tune_sparse_x86.html
+++ b/docs/tutorials/auto_scheduler/tune_sparse_x86.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -586,26 +586,32 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
primfn(placeholder_5: handle, placeholder_6: handle, placeholder_7: handle, placeholder_8: handle, placeholder_9: handle, compute_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], []),
- placeholder_4: Buffer(placeholder_10: Pointer(float32), float32, [128, 256], []),
- placeholder_3: Buffer(placeholder_11: Pointer(float32), float32, [128, 512], []),
- placeholder_2: Buffer(placeholder_12: Pointer(int32), int32, [33], []),
- placeholder: Buffer(placeholder_13: Pointer(float32), float32, [4916, 16, 1], []),
- placeholder_1: Buffer(placeholder_14: Pointer(int32), int32, [4916], [])}
- buffer_map = {placeholder_6: placeholder, placeholder_7: placeholder_1, placeholder_8: placeholder_2, placeholder_9: placeholder_3, placeholder_5: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 128) {
- for (j.init: int32, 0, 16) {
- compute_3[((i.outer.inner*16) + j.init)] = 0f32
+ placeholder_2: Buffer(placeholder_10: Pointer(int32), int32, [4916], []),
+ placeholder: Buffer(placeholder_11: Pointer(float32), float32, [128, 512], []),
+ placeholder_4: Buffer(placeholder_12: Pointer(float32), float32, [4916, 16, 1], []),
+ placeholder_3: Buffer(placeholder_13: Pointer(int32), int32, [33], []),
+ placeholder_1: Buffer(placeholder_14: Pointer(float32), float32, [128, 256], [])}
+ buffer_map = {placeholder_9: placeholder, placeholder_5: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, compute_1: compute, placeholder_6: placeholder_4} {
+ for (i0.outer.i1.outer.fused: int32, 0, 512) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [128]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 4) {
+ for (j.init: int32, 0, 16) {
+ compute_3[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
+ }
}
- for (elem_idx: int32, 0, ((int32*)placeholder_12[(i0.outer.i1.outer.fused + 1)] - (int32*)placeholder_12[i0.outer.i1.outer.fused])) {
- for (j: int32, 0, 16) {
- compute_3[((i.outer.inner*16) + j)] = ((float32*)compute_3[((i.outer.inner*16) + j)] + ((float32*)placeholder_13[((((int32*)placeholder_12[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + j)]*max((float32*)placeholder_10[((i.outer.inner*256) + (int32*)placeholder_14[((int32*)placeholder_12[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, ((int32*)placeholder_13[(floormod(i0.outer.i1.outer.fused, 32) + 1)] - (int32*)placeholder_13[floormod(i0.outer.i1.outer.fused, 32)])) {
+ for (i.inner: int32, 0, 4) {
+ for (j: int32, 0, 16) {
+ compute_3[(((i.outer.inner*64) + (i.inner*16)) + j)] = ((float32*)compute_3[(((i.outer.inner*64) + (i.inner*16)) + j)] + ((float32*)placeholder_12[((((int32*)placeholder_13[floormod(i0.outer.i1.outer.fused, 32)]*16) + (elem_idx*16)) + j)]*max((float32*)placeholder_14[((((floordiv(i0.outer.i1.outer.fused, 32)*2048) + (i.outer.inner*1024)) + (i.inner*256)) + (int32*)placeholder_10[((int32*)placeholder_13[floormod(i0.outer.i1.outer.fused, 32)] + elem_idx)])], 0f32)))
+ }
}
}
}
- for (i0.inner: int32, 0, 128) {
- compute_2[ramp(((i0.inner*512) + (i0.outer.i1.outer.fused*16)), 1, 16)] = max(((float32x16*)compute_3[ramp((i0.inner*16), 1, 16)] + (float32x16*)placeholder_11[ramp(((i0.inner*512) + (i0.outer.i1.outer.fused*16)), 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 8) {
+ for (i1.inner: int32, 0, 16) {
+ compute_2[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16)) + i1.inner)] = max(((float32*)compute_3[((i0.inner*16) + i1.inner)] + (float32*)placeholder_11[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16)) + i1.inner)]), 0f32)
+ }
}
}
}
@@ -644,7 +650,7 @@ primfn(placeholder_5: handle, placeholder_6: handle, placeholder_7: handle, plac
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.277 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.368 ms
</pre></div>
</div>
<div class="admonition note">
diff --git a/docs/tutorials/autotvm/sg_execution_times.html b/docs/tutorials/autotvm/sg_execution_times.html
index 98243f8..0083102 100644
--- a/docs/tutorials/autotvm/sg_execution_times.html
+++ b/docs/tutorials/autotvm/sg_execution_times.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Computation times — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Computation times — tvm 0.8.dev0 documentation</title>
@@ -167,7 +167,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -308,13 +308,13 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:39.245</strong> total execution time for <strong>tutorials_autotvm</strong> files:</p>
+<p><strong>00:39.734</strong> total execution time for <strong>tutorials_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:38.648</strong>: <a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-tutorials-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></li>
-<li><p><strong>00:00.156</strong>: <a class="reference internal" href="tune_relay_x86.html#sphx-glr-tutorials-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></li>
-<li><p><strong>00:00.148</strong>: <a class="reference internal" href="tune_relay_arm.html#sphx-glr-tutorials-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></li>
-<li><p><strong>00:00.146</strong>: <a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-tutorials-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></li>
-<li><p><strong>00:00.146</strong>: <a class="reference internal" href="tune_relay_cuda.html#sphx-glr-tutorials-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></li>
+<li><p><strong>00:39.040</strong>: <a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-tutorials-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></li>
+<li><p><strong>00:00.181</strong>: <a class="reference internal" href="tune_relay_x86.html#sphx-glr-tutorials-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></li>
+<li><p><strong>00:00.172</strong>: <a class="reference internal" href="tune_relay_cuda.html#sphx-glr-tutorials-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></li>
+<li><p><strong>00:00.171</strong>: <a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-tutorials-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></li>
+<li><p><strong>00:00.170</strong>: <a class="reference internal" href="tune_relay_arm.html#sphx-glr-tutorials-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/tutorials/autotvm/tune_conv2d_cuda.html b/docs/tutorials/autotvm/tune_conv2d_cuda.html
index b0f9f5a..b8f5bf5 100644
--- a/docs/tutorials/autotvm/tune_conv2d_cuda.html
+++ b/docs/tutorials/autotvm/tune_conv2d_cuda.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Tuning High Performance Convolution on NVIDIA GPUs — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Tuning High Performance Convolution on NVIDIA GPUs — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -517,26 +517,26 @@ for this template</p>
7 unroll_explicit: OtherOption([0, 1]) len=2
)
Get devices for measurement successfully!
-No: 1 GFLOPS: 0.00/0.00 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::T [...]
-No: 2 GFLOPS: 0.00/0.00 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::T [...]
-No: 3 GFLOPS: 0.00/0.00 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::T [...]
-No: 4 GFLOPS: 0.00/0.00 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::T [...]
-No: 5 GFLOPS: 0.00/0.00 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::T [...]
-No: 6 GFLOPS: 201.58/201.58 result: MeasureResult(costs=(0.001148416731958763,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6018972396850586, timestamp=1631673064.161226) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
-No: 7 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::T [...]
-No: 8 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::T [...]
-No: 9 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::T [...]
-No: 10 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(TimeoutError(),), error_no=MeasureErrorNo.BUILD_TIMEOUT, all_cost=10, timestamp=1631673060.8658895) [('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
-No: 11 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::T [...]
-No: 12 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::T [...]
-No: 13 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::T [...]
-No: 14 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::T [...]
-No: 15 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::T [...]
-No: 16 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::T [...]
-No: 17 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::T [...]
-No: 18 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::T [...]
-No: 19 GFLOPS: 0.00/201.58 result: MeasureResult(costs=(RuntimeError('Traceback (most recent call last):\n 11: TVMFuncCall\n at /home/areusch/ws/tvm4/src/runtime/c_runtime_api.cc:474\n 10: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /home/areusch/ws/tvm4/include/tvm/runtime/packed_func.h:1151\n 9: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, [...]
-No: 20 GFLOPS: 280.06/280.06 result: MeasureResult(costs=(0.0008266168206896552,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2443122863769531, timestamp=1631673072.5713875) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+No: 1 GFLOPS: 0.00/0.00 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime:: [...]
+No: 2 GFLOPS: 0.00/0.00 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime:: [...]
+No: 3 GFLOPS: 0.00/0.00 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime:: [...]
+No: 4 GFLOPS: 0.00/0.00 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime:: [...]
+No: 5 GFLOPS: 0.00/0.00 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime:: [...]
+No: 6 GFLOPS: 89.05/89.05 result: MeasureResult(costs=(0.0025997949565217393,), error_no=0, all_cost=2.115823268890381, timestamp=1630092140.2873092) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+No: 7 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime:: [...]
+No: 8 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime:: [...]
+No: 9 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime:: [...]
+No: 10 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(TimeoutError(),), error_no=6, all_cost=10, timestamp=1630092151.3702137) [('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
+No: 11 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime:: [...]
+No: 12 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime:: [...]
+No: 13 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime:: [...]
+No: 14 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime:: [...]
+No: 15 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime:: [...]
+No: 16 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime:: [...]
+No: 17 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime:: [...]
+No: 18 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(InstantiationError('Traceback (most recent call last):\n 24: TVMFuncCall\n at /workspace/src/runtime/c_runtime_api.cc:474\n 23: tvm::runtime::PackedFunc::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const\n at /workspace/include/tvm/runtime/packed_func.h:1151\n 22: std::function<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)>::operator()(tvm::runtime::TVMArgs, tvm::runtime:: [...]
+No: 19 GFLOPS: 0.00/89.05 result: MeasureResult(costs=(RuntimeError('Traceback (most recent call last):\n 99: 0x00000000005099ff\n 98: 0x0000000000507cd3\n 97: _PyEval_EvalFrameDefault\n 96: 0x000000000050a3fc\n 95: 0x00000000005096c7\n 94: _PyEval_EvalFrameDefault\n 93: 0x000000000050a3fc\n 92: 0x00000000005096c7\n 91: _PyEval_EvalFrameDefault\n 90: 0x000000000050a3fc\n 89: 0x00000000005096c7\n 88: _PyEval_EvalFrameDefault\n 87: 0x000000000050a532\n 86: _PyObject [...]
+No: 20 GFLOPS: 144.01/144.01 result: MeasureResult(costs=(0.0016075873015873017,), error_no=0, all_cost=1.4732651710510254, timestamp=1630092163.9221466) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -575,7 +575,7 @@ and measure running time.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
-Time cost of this operator: 0.000934
+Time cost of this operator: 0.002075
</pre></div>
</div>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorials-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/tutorials/autotvm/tune_relay_arm.html b/docs/tutorials/autotvm/tune_relay_arm.html
index ed4a307..1b7996d 100644
--- a/docs/tutorials/autotvm/tune_relay_arm.html
+++ b/docs/tutorials/autotvm/tune_relay_arm.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Auto-tuning a Convolutional Network for ARM CPU — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Auto-tuning a Convolutional Network for ARM CPU — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/tutorials/autotvm/tune_relay_cuda.html b/docs/tutorials/autotvm/tune_relay_cuda.html
index e9e9fb9..6a7a9e5 100644
--- a/docs/tutorials/autotvm/tune_relay_cuda.html
+++ b/docs/tutorials/autotvm/tune_relay_cuda.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Auto-tuning a Convolutional Network for NVIDIA GPU — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Auto-tuning a Convolutional Network for NVIDIA GPU — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/tutorials/autotvm/tune_relay_mobile_gpu.html b/docs/tutorials/autotvm/tune_relay_mobile_gpu.html
index 0694d77..dee7bb6 100644
--- a/docs/tutorials/autotvm/tune_relay_mobile_gpu.html
+++ b/docs/tutorials/autotvm/tune_relay_mobile_gpu.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Auto-tuning a Convolutional Network for Mobile GPU — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Auto-tuning a Convolutional Network for Mobile GPU — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/tutorials/autotvm/tune_relay_x86.html b/docs/tutorials/autotvm/tune_relay_x86.html
index fd6b5de..5ee5849 100644
--- a/docs/tutorials/autotvm/tune_relay_x86.html
+++ b/docs/tutorials/autotvm/tune_relay_x86.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Auto-tuning a Convolutional Network for x86 CPU — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Auto-tuning a Convolutional Network for x86 CPU — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/tutorials/dev/bring_your_own_datatypes.html b/docs/tutorials/dev/bring_your_own_datatypes.html
index cc58bee..8e3af68 100644
--- a/docs/tutorials/dev/bring_your_own_datatypes.html
+++ b/docs/tutorials/dev/bring_your_own_datatypes.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Bring Your Own Datatypes to TVM — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Bring Your Own Datatypes to TVM — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/tutorials/dev/low_level_custom_pass.html b/docs/tutorials/dev/low_level_custom_pass.html
index b3de7b3..ff0d744 100644
--- a/docs/tutorials/dev/low_level_custom_pass.html
+++ b/docs/tutorials/dev/low_level_custom_pass.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Writing a Customized Pass — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Writing a Customized Pass — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -480,8 +480,8 @@ called after each phase is done.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>primfn(a_1: handle, b_1: handle, c_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {c: Buffer(c_2: Pointer(float32), float32, [128], []),
- a: Buffer(a_2: Pointer(float32), float32, [128], []),
+ buffers = {a: Buffer(a_2: Pointer(float32), float32, [128], []),
+ c: Buffer(c_2: Pointer(float32), float32, [128], []),
b: Buffer(b_2: Pointer(float32), float32, [128], [])}
buffer_map = {a_1: a, b_1: b, c_1: c} {
for (i.outer: int32, 0, 16) {
diff --git a/docs/tutorials/dev/sg_execution_times.html b/docs/tutorials/dev/sg_execution_times.html
index 2f05c3a..dd42c2a 100644
--- a/docs/tutorials/dev/sg_execution_times.html
+++ b/docs/tutorials/dev/sg_execution_times.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Computation times — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Computation times — tvm 0.8.dev0 documentation</title>
@@ -167,7 +167,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -308,12 +308,12 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorials-dev-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.311</strong> total execution time for <strong>tutorials_dev</strong> files:</p>
+<p><strong>00:49.008</strong> total execution time for <strong>tutorials_dev</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:31.575</strong>: <a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-tutorials-dev-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></li>
-<li><p><strong>00:02.244</strong>: <a class="reference internal" href="use_pass_instrument.html#sphx-glr-tutorials-dev-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></li>
-<li><p><strong>00:01.344</strong>: <a class="reference internal" href="use_pass_infra.html#sphx-glr-tutorials-dev-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></li>
-<li><p><strong>00:00.148</strong>: <a class="reference internal" href="low_level_custom_pass.html#sphx-glr-tutorials-dev-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></li>
+<li><p><strong>00:49.008</strong>: <a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-tutorials-dev-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></li>
+<li><p><strong>00:00.000</strong>: <a class="reference internal" href="low_level_custom_pass.html#sphx-glr-tutorials-dev-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></li>
+<li><p><strong>00:00.000</strong>: <a class="reference internal" href="use_pass_infra.html#sphx-glr-tutorials-dev-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></li>
+<li><p><strong>00:00.000</strong>: <a class="reference internal" href="use_pass_instrument.html#sphx-glr-tutorials-dev-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/tutorials/dev/use_pass_infra.html b/docs/tutorials/dev/use_pass_infra.html
index 9c1f9ca..5cdcbe8 100644
--- a/docs/tutorials/dev/use_pass_infra.html
+++ b/docs/tutorials/dev/use_pass_infra.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>How to Use TVM Pass Infra — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>How to Use TVM Pass Infra — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/tutorials/dev/use_pass_instrument.html b/docs/tutorials/dev/use_pass_instrument.html
index 527d85e..bb446f2 100644
--- a/docs/tutorials/dev/use_pass_instrument.html
+++ b/docs/tutorials/dev/use_pass_instrument.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>How to Use TVM Pass Instrument — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>How to Use TVM Pass Instrument — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -478,10 +478,10 @@ profile the execution time of each passes.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 3752us [3752us] (45.67%; 45.67%)
-FoldScaleAxis: 4464us [2us] (54.33%; 54.33%)
- FoldConstant: 4463us [920us] (54.31%; 99.96%)
- InferType: 3542us [3542us] (43.12%; 79.38%)
+InferType: 5181us [5181us] (45.61%; 45.61%)
+FoldScaleAxis: 6179us [2us] (54.39%; 54.39%)
+ FoldConstant: 6177us [1335us] (54.38%; 99.97%)
+ InferType: 4842us [4842us] (42.62%; 78.39%)
</pre></div>
</div>
</div>
@@ -504,10 +504,10 @@ Refer to following sections and <a class="reference internal" href="../../api/py
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 3532us [3532us] (44.22%; 44.22%)
-FoldScaleAxis: 4455us [2us] (55.78%; 55.78%)
- FoldConstant: 4454us [969us] (55.76%; 99.97%)
- InferType: 3485us [3485us] (43.63%; 78.24%)
+InferType: 4919us [4919us] (44.75%; 44.75%)
+FoldScaleAxis: 6074us [2us] (55.25%; 55.25%)
+ FoldConstant: 6072us [1337us] (55.23%; 99.97%)
+ InferType: 4734us [4734us] (43.07%; 77.97%)
</pre></div>
</div>
<p>Register empty list to clear existing instruments.</p>
diff --git a/docs/tutorials/frontend/build_gcn.html b/docs/tutorials/frontend/build_gcn.html
index 9b50082..e485aca 100644
--- a/docs/tutorials/frontend/build_gcn.html
+++ b/docs/tutorials/frontend/build_gcn.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Building a Graph Convolutional Network — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Building a Graph Convolutional Network — tvm 0.8.dev0 documentation</title>
@@ -170,7 +170,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -393,7 +393,9 @@ This part reuses the code from the above example.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Using backend: pytorch
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>DGL backend not selected or invalid. Assuming PyTorch for now.
+Setting the default backend to "pytorch". You can change it in the ~/.dgl/config.json file or export the DGLBACKEND environment variable. Valid options are: pytorch, mxnet, tensorflow (all lowercase)
+Using backend: pytorch
</pre></div>
</div>
</div>
@@ -457,14 +459,17 @@ This part reuses the code from the above example.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> NumNodes: 2708
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.dgl/cora_v2.zip from https://data.dgl.ai/dataset/cora_v2.zip...
+Extracting file to /workspace/.dgl/cora_v2
+Finished data loading and preprocessing.
+ NumNodes: 2708
NumEdges: 10556
NumFeats: 1433
NumClasses: 7
NumTrainingSamples: 140
NumValidationSamples: 500
NumTestSamples: 1000
-Done loading data from cached files.
+Done saving data into cached files.
/usr/local/lib/python3.6/dist-packages/dgl/data/utils.py:285: UserWarning: Property dataset.graph will be deprecated, please use dataset[0] instead.
warnings.warn('Property {} will be deprecated, please use {} instead.'.format(old, new))
/usr/local/lib/python3.6/dist-packages/dgl/data/utils.py:285: UserWarning: Property dataset.feat will be deprecated, please use g.ndata['feat'] instead.
diff --git a/docs/tutorials/frontend/deploy_model_on_android.html b/docs/tutorials/frontend/deploy_model_on_android.html
index 7a7ed67..59effc1 100644
--- a/docs/tutorials/frontend/deploy_model_on_android.html
+++ b/docs/tutorials/frontend/deploy_model_on_android.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Deploy the Pretrained Model on Android — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Deploy the Pretrained Model on Android — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -633,7 +633,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.3173 7.2984 7.3807 7.2587 0.0423
+ 11.0604 10.7861 12.7899 10.6342 0.6586
</pre></div>
</div>
</div>
diff --git a/docs/tutorials/frontend/deploy_model_on_rasp.html b/docs/tutorials/frontend/deploy_model_on_rasp.html
index 8a4194b..7e5d146 100644
--- a/docs/tutorials/frontend/deploy_model_on_rasp.html
+++ b/docs/tutorials/frontend/deploy_model_on_rasp.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Deploy the Pretrained Model on Raspberry Pi — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Deploy the Pretrained Model on Raspberry Pi — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/tutorials/frontend/deploy_object_detection_pytorch.html b/docs/tutorials/frontend/deploy_object_detection_pytorch.html
index 37f3bf4..81b3c7c 100644
--- a/docs/tutorials/frontend/deploy_object_detection_pytorch.html
+++ b/docs/tutorials/frontend/deploy_object_detection_pytorch.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Compile PyTorch Object Detection Models — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Compile PyTorch Object Detection Models — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -415,7 +415,51 @@ be unstable.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/usr/local/lib/python3.6/dist-packages/torch/tensor.py:593: RuntimeWarning: Iterating over a tensor might cause the trace to be incorrect. Passing a tensor of different shape won't change the number of iterations executed (and might lead to errors or silently give incorrect results).
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
+
+ 0%| | 0.00/170M [00:00<?, ?B/s]
+ 0%| | 8.00k/170M [00:00<1:36:57, 30.6kB/s]
+ 1%|1 | 2.31M/170M [00:00<00:20, 8.39MB/s]
+ 4%|4 | 7.31M/170M [00:00<00:07, 22.9MB/s]
+ 7%|7 | 12.0M/170M [00:00<00:05, 31.3MB/s]
+ 9%|9 | 15.7M/170M [00:00<00:05, 30.0MB/s]
+ 11%|#1 | 19.4M/170M [00:00<00:04, 32.4MB/s]
+ 13%|#3 | 22.8M/170M [00:00<00:04, 31.7MB/s]
+ 15%|#5 | 26.1M/170M [00:01<00:04, 30.5MB/s]
+ 17%|#7 | 29.1M/170M [00:01<00:04, 30.3MB/s]
+ 20%|## | 34.5M/170M [00:01<00:03, 37.5MB/s]
+ 24%|##3 | 40.2M/170M [00:01<00:03, 43.9MB/s]
+ 26%|##6 | 44.6M/170M [00:01<00:03, 43.0MB/s]
+ 29%|##8 | 49.1M/170M [00:01<00:02, 44.3MB/s]
+ 31%|###1 | 53.4M/170M [00:01<00:02, 44.5MB/s]
+ 34%|###4 | 58.2M/170M [00:01<00:02, 46.1MB/s]
+ 37%|###6 | 62.7M/170M [00:01<00:02, 42.7MB/s]
+ 39%|###9 | 66.8M/170M [00:02<00:02, 42.1MB/s]
+ 42%|####1 | 70.9M/170M [00:02<00:02, 40.7MB/s]
+ 44%|####4 | 75.5M/170M [00:02<00:02, 42.9MB/s]
+ 47%|####6 | 79.6M/170M [00:02<00:02, 36.4MB/s]
+ 50%|####9 | 84.3M/170M [00:02<00:02, 39.6MB/s]
+ 53%|#####2 | 89.9M/170M [00:02<00:01, 44.8MB/s]
+ 56%|#####5 | 94.4M/170M [00:02<00:01, 44.8MB/s]
+ 58%|#####8 | 98.8M/170M [00:02<00:01, 44.0MB/s]
+ 61%|###### | 103M/170M [00:02<00:01, 41.7MB/s]
+ 63%|######3 | 107M/170M [00:03<00:01, 33.8MB/s]
+ 66%|######5 | 111M/170M [00:03<00:01, 36.0MB/s]
+ 68%|######8 | 116M/170M [00:03<00:01, 39.7MB/s]
+ 71%|#######1 | 121M/170M [00:03<00:01, 42.3MB/s]
+ 74%|#######3 | 125M/170M [00:03<00:01, 43.8MB/s]
+ 76%|#######6 | 130M/170M [00:03<00:01, 31.9MB/s]
+ 79%|#######8 | 133M/170M [00:03<00:01, 33.3MB/s]
+ 81%|######## | 137M/170M [00:03<00:00, 35.0MB/s]
+ 83%|########3 | 141M/170M [00:04<00:00, 37.2MB/s]
+ 86%|########5 | 146M/170M [00:04<00:00, 38.9MB/s]
+ 88%|########8 | 150M/170M [00:04<00:00, 41.6MB/s]
+ 91%|######### | 154M/170M [00:04<00:00, 38.4MB/s]
+ 94%|#########4| 160M/170M [00:04<00:00, 43.7MB/s]
+ 97%|#########6| 164M/170M [00:04<00:00, 42.7MB/s]
+ 99%|#########9| 169M/170M [00:04<00:00, 42.2MB/s]
+100%|##########| 170M/170M [00:04<00:00, 37.6MB/s]
+/usr/local/lib/python3.6/dist-packages/torch/tensor.py:593: RuntimeWarning: Iterating over a tensor might cause the trace to be incorrect. Passing a tensor of different shape won't change the number of iterations executed (and might lead to errors or silently give incorrect results).
'incorrect results).', category=RuntimeWarning)
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py:3123: 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).
dtype=torch.float32)).float())) for i in range(dim)]
@@ -498,7 +542,7 @@ 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> ( 1 minutes 42.237 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 34.821 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorials-frontend-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/ec94e7a109437cf90cddcc60a7b5aaea/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/tutorials/frontend/deploy_prequantized.html b/docs/tutorials/frontend/deploy_prequantized.html
index fa88770..32f67de 100644
--- a/docs/tutorials/frontend/deploy_prequantized.html
+++ b/docs/tutorials/frontend/deploy_prequantized.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Deploy a Framework-prequantized Model with TVM — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Deploy a Framework-prequantized Model with TVM — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -458,6 +458,15 @@ training. Other models require a full post training calibration.</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">qmodel</span> <span class="o">=</span> <span class="n">qmobilenet</span><span class="o">.</span><span class="n">mobilenet_v2</span><span class="p">(</span><span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span><span class="o">.</span><span class="n">eval</span><span class="p">()</span>
</pre></div>
</div>
+<p class="sphx-glr-script-out">Out:</p>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "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]
+ 29%|##9 | 3.98M/13.6M [00:00<00:00, 41.7MB/s]
+ 62%|######1 | 8.36M/13.6M [00:00<00:00, 44.2MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 63.1MB/s]
+</pre></div>
+</div>
</div>
<div class="section" id="quantize-trace-and-run-the-pytorch-mobilenet-v2-model">
<h2>Quantize, trace and run the PyTorch Mobilenet v2 model<a class="headerlink" href="#quantize-trace-and-run-the-pytorch-mobilenet-v2-model" title="Permalink to this headline">¶</a></h2>
@@ -517,7 +526,7 @@ standard Relay operators before compilation.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>PyTorch top3 labels: ['tiger cat', 'Egyptian cat', 'tabby, tabby cat']
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>PyTorch top3 labels: ['tiger cat', 'Egyptian cat', 'lynx, catamount']
TVM top3 labels: ['tiger cat', 'Egyptian cat', 'tabby, tabby cat']
</pre></div>
</div>
@@ -528,7 +537,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>140 in 1000 raw floating outputs identical.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>132 in 1000 raw floating outputs identical.
</pre></div>
</div>
</div>
@@ -543,7 +552,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 18.4986 18.4725 19.6626 18.3014 0.1583
+ 39.4568 38.9747 58.8311 38.6383 2.0381
</pre></div>
</div>
<div class="admonition note">
@@ -582,6 +591,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 37.273 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorials-frontend-deploy-prequantized-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/8a7f17665207908e373e8146da09443a/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/tutorials/frontend/deploy_prequantized_tflite.html b/docs/tutorials/frontend/deploy_prequantized_tflite.html
index 7db0b07..0a6fc57 100644
--- a/docs/tutorials/frontend/deploy_prequantized_tflite.html
+++ b/docs/tutorials/frontend/deploy_prequantized_tflite.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite) — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite) — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -553,7 +553,7 @@ TFLite Top-5 labels: [387 102 386 341 880]
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 34.6676 34.3071 55.0247 33.8788 2.1488
+ 72.0695 71.4769 89.6603 69.9658 2.3134
</pre></div>
</div>
<div class="admonition note">
@@ -580,7 +580,7 @@ device and follow <a class="reference external" href="https://tvm.apache.org/doc
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 9.880 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 19.036 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorials-frontend-deploy-prequantized-tflite-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/5c443f88ea44ce77c5ccade429af6e74/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/tutorials/frontend/deploy_quantized.html b/docs/tutorials/frontend/deploy_quantized.html
index 453489a..3dd1ded 100644
--- a/docs/tutorials/frontend/deploy_quantized.html
+++ b/docs/tutorials/frontend/deploy_quantized.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Deploy a Quantized Model on Cuda — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Deploy a Quantized Model on Cuda — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -482,6 +482,7 @@ for calibration. But the accuracy might be impacted.</p>
<span class="n">main</span><span class="p">()</span>
</pre></div>
</div>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 24.981 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorials-frontend-deploy-quantized-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/5b32f1dc3e9e2fc5ac5be0918758b967/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/tutorials/frontend/deploy_sparse.html b/docs/tutorials/frontend/deploy_sparse.html
index 74e3686..9d51718 100644
--- a/docs/tutorials/frontend/deploy_sparse.html
+++ b/docs/tutorials/frontend/deploy_sparse.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Deploy a Hugging Face Pruned Model on CPU — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Deploy a Hugging Face Pruned Model on CPU — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/tutorials/frontend/deploy_ssd_gluoncv.html b/docs/tutorials/frontend/deploy_ssd_gluoncv.html
index 5e2d65a..bb9429c 100644
--- a/docs/tutorials/frontend/deploy_ssd_gluoncv.html
+++ b/docs/tutorials/frontend/deploy_ssd_gluoncv.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Deploy Single Shot Multibox Detector(SSD) model — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Deploy Single Shot Multibox Detector(SSD) model — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -416,6 +416,31 @@ to your device.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/usr/local/lib/python3.6/dist-packages/mxnet/gluon/block.py:1389: UserWarning: Cannot decide type for the following arguments. Consider providing them as input:
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]
+ 2%|1 | 2136/132723 [00:00<00:14, 9070.09KB/s]
+ 4%|3 | 4955/132723 [00:00<00:07, 16289.03KB/s]
+ 8%|7 | 10343/132723 [00:00<00:04, 29460.18KB/s]
+ 10%|# | 13908/132723 [00:00<00:04, 29404.22KB/s]
+ 13%|#2 | 17223/132723 [00:00<00:04, 28235.72KB/s]
+ 17%|#6 | 21954/132723 [00:00<00:03, 33744.53KB/s]
+ 19%|#9 | 25584/132723 [00:00<00:03, 33127.69KB/s]
+ 25%|##4 | 32757/132723 [00:01<00:02, 37422.81KB/s]
+ 28%|##7 | 37099/132723 [00:01<00:02, 35875.46KB/s]
+ 31%|### | 40711/132723 [00:01<00:02, 35048.87KB/s]
+ 37%|###6 | 48894/132723 [00:01<00:01, 47232.76KB/s]
+ 41%|#### | 53835/132723 [00:01<00:02, 38447.61KB/s]
+ 48%|####8 | 64078/132723 [00:01<00:01, 53641.55KB/s]
+ 53%|#####2 | 70129/132723 [00:01<00:01, 49190.34KB/s]
+ 59%|#####9 | 78360/132723 [00:01<00:00, 57245.79KB/s]
+ 64%|######3 | 84644/132723 [00:02<00:00, 51620.82KB/s]
+ 71%|#######1 | 94737/132723 [00:02<00:00, 63687.46KB/s]
+ 77%|#######6 | 101708/132723 [00:02<00:00, 39024.85KB/s]
+ 84%|########4 | 111833/132723 [00:02<00:00, 50300.89KB/s]
+ 89%|########9 | 118693/132723 [00:02<00:00, 46824.58KB/s]
+ 97%|#########7| 128849/132723 [00:02<00:00, 57925.56KB/s]
+100%|##########| 132723/132723 [00:03<00:00, 43823.76KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -455,7 +480,7 @@ to your device.</p>
</pre></div>
</div>
<img alt="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" />
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 44.102 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 23.389 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorials-frontend-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/ca08de6c440df207921d807474d26f06/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/tutorials/frontend/from_caffe2.html b/docs/tutorials/frontend/from_caffe2.html
index a0f0224..7f46dd7 100644
--- a/docs/tutorials/frontend/from_caffe2.html
+++ b/docs/tutorials/frontend/from_caffe2.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Compile Caffe2 Models — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Compile Caffe2 Models — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -372,6 +372,17 @@ conda install pytorch-nightly cuda80 -c pytorch
<span class="n">resnet50</span> <span class="o">=</span> <span class="n">Model</span><span class="p">(</span><span class="s2">"resnet50"</span><span class="p">)</span>
</pre></div>
</div>
+<p class="sphx-glr-script-out">Out:</p>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading from https://s3.amazonaws.com/download.caffe2.ai/models/resnet50/predict_net.pb
+Writing to /workspace/.caffe2/models/resnet50/predict_net.pb
+
+Downloading from https://s3.amazonaws.com/download.caffe2.ai/models/resnet50/init_net.pb
+Writing to /workspace/.caffe2/models/resnet50/init_net.pb
+
+Downloading from https://s3.amazonaws.com/download.caffe2.ai/models/resnet50/value_info.json
+Writing to /workspace/.caffe2/models/resnet50/value_info.json
+</pre></div>
+</div>
</div>
<div class="section" id="load-a-test-image">
<h2>Load a test image<a class="headerlink" href="#load-a-test-image" title="Permalink to this headline">¶</a></h2>
diff --git a/docs/tutorials/frontend/from_coreml.html b/docs/tutorials/frontend/from_coreml.html
index 39dec1c..a66eabf 100644
--- a/docs/tutorials/frontend/from_coreml.html
+++ b/docs/tutorials/frontend/from_coreml.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Compile CoreML Models — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Compile CoreML Models — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/tutorials/frontend/from_darknet.html b/docs/tutorials/frontend/from_darknet.html
index 78e30b3..7efb3ab 100644
--- a/docs/tutorials/frontend/from_darknet.html
+++ b/docs/tutorials/frontend/from_darknet.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Compile YOLO-V2 and YOLO-V3 in DarkNet Models — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Compile YOLO-V2 and YOLO-V3 in DarkNet Models — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -550,6 +550,7 @@ class:['truck 0.9266'] left:471 right:83 top:689 bottom:169
class:['bicycle 0.9984'] left:111 right:113 top:577 bottom:447
</pre></div>
</div>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.353 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorials-frontend-from-darknet-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/a7ce44923ffcc359fd2e532ac1f62c9e/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/tutorials/frontend/from_keras.html b/docs/tutorials/frontend/from_keras.html
index 5b5e128..58da264 100644
--- a/docs/tutorials/frontend/from_keras.html
+++ b/docs/tutorials/frontend/from_keras.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Compile Keras Models — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Compile Keras Models — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/tutorials/frontend/from_mxnet.html b/docs/tutorials/frontend/from_mxnet.html
index cb426a2..67dc791 100644
--- a/docs/tutorials/frontend/from_mxnet.html
+++ b/docs/tutorials/frontend/from_mxnet.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Compile MXNet Models — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Compile MXNet Models — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -402,7 +402,8 @@
</div>
<img alt="../../_images/sphx_glr_from_mxnet_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_from_mxnet_001.png" />
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>x (1, 3, 224, 224)
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipfaa14738-16e4-4da0-8285-ae245f11b665 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+x (1, 3, 224, 224)
</pre></div>
</div>
</div>
diff --git a/docs/tutorials/frontend/from_onnx.html b/docs/tutorials/frontend/from_onnx.html
index ae85e19..5cad8cd 100644
--- a/docs/tutorials/frontend/from_onnx.html
+++ b/docs/tutorials/frontend/from_onnx.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Compile ONNX Models — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Compile ONNX Models — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -421,7 +421,7 @@ provides a static definition of the input size.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>../../python/tvm/relay/frontend/onnx.py:4206: UserWarning: Mismatched attribute type in ' : kernel_shape'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>../../python/tvm/relay/frontend/onnx.py:4025: UserWarning: Mismatched attribute type in ' : kernel_shape'
==> Context: Bad node spec: input: "1" input: "2" output: "11" op_type: "Conv" attribute { name: "kernel_shape" ints: 5 ints: 5 } attribute { name: "strides" ints: 1 ints: 1 } attribute { name: "pads" ints: 2 ints: 2 ints: 2 ints: 2 } attribute { name: "dilations" ints: 1 ints: 1 } attribute { name: "group" i: 1 }
warnings.warn(str(e))
diff --git a/docs/tutorials/frontend/from_pytorch.html b/docs/tutorials/frontend/from_pytorch.html
index c3d9849..158aafb 100644
--- a/docs/tutorials/frontend/from_pytorch.html
+++ b/docs/tutorials/frontend/from_pytorch.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Compile PyTorch Models — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Compile PyTorch Models — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -384,6 +384,15 @@ be unstable.</p>
<span class="n">scripted_model</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">jit</span><span class="o">.</span><span class="n">trace</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">input_data</span><span class="p">)</span><span class="o">.</span><span class="n">eval</span><span class="p">()</span>
</pre></div>
</div>
+<p class="sphx-glr-script-out">Out:</p>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-5c106cde.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-5c106cde.pth
+
+ 0%| | 0.00/44.7M [00:00<?, ?B/s]
+ 28%|##8 | 12.6M/44.7M [00:00<00:00, 132MB/s]
+ 77%|#######7 | 34.5M/44.7M [00:00<00:00, 189MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 194MB/s]
+</pre></div>
+</div>
</div>
<div class="section" id="load-a-test-image">
<h2>Load a test image<a class="headerlink" href="#load-a-test-image" title="Permalink to this headline">¶</a></h2>
diff --git a/docs/tutorials/frontend/from_tensorflow.html b/docs/tutorials/frontend/from_tensorflow.html
index 85069f1..fcd084d 100644
--- a/docs/tutorials/frontend/from_tensorflow.html
+++ b/docs/tutorials/frontend/from_tensorflow.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Compile Tensorflow Models — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Compile Tensorflow Models — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -504,146 +504,6 @@ lib: target library which can be deployed on target with TVM runtime.</p>
<span class="n">lib</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">mod</span><span class="p">,</span> <span class="n">target</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="n">params</span><span class="p">)</span>
</pre></div>
</div>
-<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-conv2d NHWC layout is not optimized for x86 with autotvm.
-</pre></div>
-</div>
</div>
<div class="section" id="execute-the-portable-graph-on-tvm">
<h2>Execute the portable graph on TVM<a class="headerlink" href="#execute-the-portable-graph-on-tvm" title="Permalink to this headline">¶</a></h2>
@@ -752,6 +612,7 @@ 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 20.985 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorials-frontend-from-tensorflow-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/50b174352ccf0a0defcbd8e6b40145e2/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/tutorials/frontend/from_tflite.html b/docs/tutorials/frontend/from_tflite.html
index 86378f5..addc377 100644
--- a/docs/tutorials/frontend/from_tflite.html
+++ b/docs/tutorials/frontend/from_tflite.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Compile TFLite Models — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Compile TFLite Models — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/tutorials/frontend/sg_execution_times.html b/docs/tutorials/frontend/sg_execution_times.html
index 2e30223..2bdf3fd 100644
--- a/docs/tutorials/frontend/sg_execution_times.html
+++ b/docs/tutorials/frontend/sg_execution_times.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Computation times — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Computation times — tvm 0.8.dev0 documentation</title>
@@ -167,7 +167,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -308,27 +308,27 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>12:48.781</strong> total execution time for <strong>tutorials_frontend</strong> files:</p>
+<p><strong>00:20.583</strong> total execution time for <strong>tutorials_frontend</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:44.102</strong>: <a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-tutorials-frontend-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></li>
-<li><p><strong>02:09.880</strong>: <a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-tutorials-frontend-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></li>
-<li><p><strong>01:42.237</strong>: <a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-tutorials-frontend-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></li>
-<li><p><strong>00:58.362</strong>: <a class="reference internal" href="deploy_prequantized.html#sphx-glr-tutorials-frontend-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></li>
-<li><p><strong>00:51.534</strong>: <a class="reference internal" href="from_tensorflow.html#sphx-glr-tutorials-frontend-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></li>
-<li><p><strong>00:49.915</strong>: <a class="reference internal" href="deploy_quantized.html#sphx-glr-tutorials-frontend-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></li>
-<li><p><strong>00:44.022</strong>: <a class="reference internal" href="from_darknet.html#sphx-glr-tutorials-frontend-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></li>
-<li><p><strong>00:33.724</strong>: <a class="reference internal" href="from_caffe2.html#sphx-glr-tutorials-frontend-from-caffe2-py"><span class="std std-ref">Compile Caffe2 Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_caffe2.py</span></code>)</p></li>
-<li><p><strong>00:25.786</strong>: <a class="reference internal" href="deploy_model_on_android.html#sphx-glr-tutorials-frontend-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></li>
-<li><p><strong>00:22.924</strong>: <a class="reference internal" href="from_tflite.html#sphx-glr-tutorials-frontend-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></li>
-<li><p><strong>00:20.266</strong>: <a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-tutorials-frontend-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></li>
-<li><p><strong>00:18.185</strong>: <a class="reference internal" href="from_coreml.html#sphx-glr-tutorials-frontend-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></li>
-<li><p><strong>00:16.801</strong>: <a class="reference internal" href="from_pytorch.html#sphx-glr-tutorials-frontend-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></li>
-<li><p><strong>00:15.877</strong>: <a class="reference internal" href="from_mxnet.html#sphx-glr-tutorials-frontend-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></li>
-<li><p><strong>00:10.187</strong>: <a class="reference internal" href="from_keras.html#sphx-glr-tutorials-frontend-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></li>
-<li><p><strong>00:02.287</strong>: <a class="reference internal" href="using_external_lib.html#sphx-glr-tutorials-frontend-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></li>
-<li><p><strong>00:01.525</strong>: <a class="reference internal" href="from_onnx.html#sphx-glr-tutorials-frontend-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></li>
-<li><p><strong>00:01.027</strong>: <a class="reference internal" href="build_gcn.html#sphx-glr-tutorials-frontend-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></li>
-<li><p><strong>00:00.141</strong>: <a class="reference internal" href="deploy_sparse.html#sphx-glr-tutorials-frontend-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></li>
+<li><p><strong>00:18.527</strong>: <a class="reference internal" href="from_keras.html#sphx-glr-tutorials-frontend-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></li>
+<li><p><strong>00:02.056</strong>: <a class="reference internal" href="from_onnx.html#sphx-glr-tutorials-frontend-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></li>
+<li><p><strong>00:00.000</strong>: <a class="reference internal" href="build_gcn.html#sphx-glr-tutorials-frontend-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></li>
+<li><p><strong>00:00.000</strong>: <a class="reference internal" href="deploy_model_on_android.html#sphx-glr-tutorials-frontend-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></li>
+<li><p><strong>00:00.000</strong>: <a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-tutorials-frontend-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></li>
+<li><p><strong>00:00.000</strong>: <a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-tutorials-frontend-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></li>
+<li><p><strong>00:00.000</strong>: <a class="reference internal" href="deploy_prequantized.html#sphx-glr-tutorials-frontend-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></li>
+<li><p><strong>00:00.000</strong>: <a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-tutorials-frontend-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></li>
+<li><p><strong>00:00.000</strong>: <a class="reference internal" href="deploy_quantized.html#sphx-glr-tutorials-frontend-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></li>
+<li><p><strong>00:00.000</strong>: <a class="reference internal" href="deploy_sparse.html#sphx-glr-tutorials-frontend-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></li>
+<li><p><strong>00:00.000</strong>: <a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-tutorials-frontend-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></li>
+<li><p><strong>00:00.000</strong>: <a class="reference internal" href="from_caffe2.html#sphx-glr-tutorials-frontend-from-caffe2-py"><span class="std std-ref">Compile Caffe2 Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_caffe2.py</span></code>)</p></li>
+<li><p><strong>00:00.000</strong>: <a class="reference internal" href="from_coreml.html#sphx-glr-tutorials-frontend-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></li>
+<li><p><strong>00:00.000</strong>: <a class="reference internal" href="from_darknet.html#sphx-glr-tutorials-frontend-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></li>
+<li><p><strong>00:00.000</strong>: <a class="reference internal" href="from_mxnet.html#sphx-glr-tutorials-frontend-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></li>
+<li><p><strong>00:00.000</strong>: <a class="reference internal" href="from_pytorch.html#sphx-glr-tutorials-frontend-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></li>
+<li><p><strong>00:00.000</strong>: <a class="reference internal" href="from_tensorflow.html#sphx-glr-tutorials-frontend-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></li>
+<li><p><strong>00:00.000</strong>: <a class="reference internal" href="from_tflite.html#sphx-glr-tutorials-frontend-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></li>
+<li><p><strong>00:00.000</strong>: <a class="reference internal" href="using_external_lib.html#sphx-glr-tutorials-frontend-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/tutorials/frontend/using_external_lib.html b/docs/tutorials/frontend/using_external_lib.html
index f54a7fb..4242b83 100644
--- a/docs/tutorials/frontend/using_external_lib.html
+++ b/docs/tutorials/frontend/using_external_lib.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Using External Libraries in Relay — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Using External Libraries in Relay — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/tutorials/get_started/auto_scheduler_matmul_x86.html b/docs/tutorials/get_started/auto_scheduler_matmul_x86.html
index 36d6e62..5892799 100644
--- a/docs/tutorials/get_started/auto_scheduler_matmul_x86.html
+++ b/docs/tutorials/get_started/auto_scheduler_matmul_x86.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Optimizing Operators with Auto-scheduling — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Optimizing Operators with Auto-scheduling — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -541,7 +541,7 @@ primfn(A_1: handle, B_1: handle, C_1: handle, out_1: handle) -> ()
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 21.160 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 45.432 ms
</pre></div>
</div>
</div>
diff --git a/docs/tutorials/get_started/autotvm_matmul_x86.html b/docs/tutorials/get_started/autotvm_matmul_x86.html
index 167b47b..b484041 100644
--- a/docs/tutorials/get_started/autotvm_matmul_x86.html
+++ b/docs/tutorials/get_started/autotvm_matmul_x86.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Optimizing Operators with Schedule Templates and AutoTVM — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Optimizing Operators with Schedule Templates and AutoTVM — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
diff --git a/docs/tutorials/get_started/autotvm_relay_x86.html b/docs/tutorials/get_started/autotvm_relay_x86.html
index 0babdf5..6836a4d 100644
--- a/docs/tutorials/get_started/autotvm_relay_x86.html
+++ b/docs/tutorials/get_started/autotvm_relay_x86.html
@@ -11,7 +11,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Compiling and Optimizing a Model with the Python Interface (AutoTVM) — tvm 0.8.dev1706+gdc2f70e3c documentation</title>
+ <title>Compiling and Optimizing a Model with the Python Interface (AutoTVM) — tvm 0.8.dev0 documentation</title>
@@ -169,7 +169,7 @@
<div class="version">
- 0.8.dev1706+gdc2f70e3c
+ 0.8.dev0
</div>
@@ -478,10 +478,6 @@ set.</p>
<span class="n">module</span> <span class="o">=</span> <a href="../../api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="View documentation for tvm.contrib.graph_executor.GraphModule"><span class="n">graph_executor</span><span class="o">.</span><span class="n">GraphModule</span></a><span class="p">(</span><span class="n">lib</span><span class="p">[</span><span class="s2">"default"</span><span class="p">](</span><span class="n">dev</span><span class="p [...]
</pre></div>
</div>
-<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>One or more operators have not been tuned. Please tune your model for better performance. Use DEBUG logging level to see more details.
-</pre></div>
-</div>
</div>
<div class="section" id="execute-on-the-tvm-runtime">
<h2>Execute on the TVM Runtime<a class="headerlink" href="#execute-on-the-tvm-runtime" title="Permalink to this headline">¶</a></h2>
@@ -526,7 +522,7 @@ standard deviation.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 100.97112998832017, 'median': 100.64726648852229, 'std': 0.9355632830933527}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 226.42689668997264, 'median': 226.24714619996666, 'std': 0.646916386317958}
</pre></div>
</div>
</div>
@@ -555,8 +551,8 @@ for the model.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.610551
-class='n02123159 tiger cat' with probability=0.367180
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.610552
+class='n02123159 tiger cat' with probability=0.367179
class='n02124075 Egyptian cat' with probability=0.019365
class='n02129604 tiger, Panthera tigris' with probability=0.001273
class='n04040759 radiator' with probability=0.000261
@@ -682,79 +678,129 @@ depending on the specifics of the model and the target platform.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 1/25] Current/Best: 13.44/ 26.27 GFLOPS | Progress: (10/10) | 95.13 s
+[Task 1/25] Current/Best: 12.05/ 14.13 GFLOPS | Progress: (4/10) | 11.61 s
+[Task 1/25] Current/Best: 14.75/ 14.75 GFLOPS | Progress: (8/10) | 22.10 s
+[Task 1/25] Current/Best: 9.32/ 14.75 GFLOPS | Progress: (10/10) | 32.45 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 2/25] Current/Best: 1.81/ 1.81 GFLOPS | Progress: (10/10) | 36.88 s
+[Task 2/25] Current/Best: 6.24/ 12.89 GFLOPS | Progress: (4/10) | 3.57 s
+[Task 2/25] Current/Best: 19.53/ 19.53 GFLOPS | Progress: (8/10) | 12.75 s
+[Task 2/25] Current/Best: 19.58/ 19.58 GFLOPS | Progress: (10/10) | 13.84 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 3/25] Current/Best: 42.58/ 74.66 GFLOPS | Progress: (10/10) | 37.79 s
+[Task 3/25] Current/Best: 27.76/ 39.82 GFLOPS | Progress: (4/10) | 3.83 s
+[Task 3/25] Current/Best: 23.57/ 46.16 GFLOPS | Progress: (8/10) | 6.40 s
+[Task 3/25] Current/Best: 15.99/ 46.16 GFLOPS | Progress: (10/10) | 8.16 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 4/25] Current/Best: 53.23/ 96.78 GFLOPS | Progress: (10/10) | 9.82 s Done.
+[Task 4/25] Current/Best: 33.28/ 45.79 GFLOPS | Progress: (4/10) | 3.06 s
+[Task 4/25] Current/Best: 28.97/ 45.79 GFLOPS | Progress: (8/10) | 5.45 s
+[Task 4/25] Current/Best: 45.86/ 45.86 GFLOPS | Progress: (10/10) | 6.87 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 5/25] Current/Best: 6.82/ 60.22 GFLOPS | Progress: (10/10) | 16.41 s Done.
+[Task 5/25] Current/Best: 20.78/ 38.54 GFLOPS | Progress: (4/10) | 2.22 s
+[Task 5/25] Current/Best: 47.72/ 47.72 GFLOPS | Progress: (8/10) | 3.87 s
+[Task 5/25] Current/Best: 19.84/ 47.72 GFLOPS | Progress: (10/10) | 4.61 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 6/25] Current/Best: 69.75/ 69.75 GFLOPS | Progress: (10/10) | 14.71 s Done.
+[Task 6/25] Current/Best: 24.75/ 24.75 GFLOPS | Progress: (4/10) | 3.88 s
+[Task 6/25] Current/Best: 36.38/ 46.07 GFLOPS | Progress: (8/10) | 6.43 s
+[Task 6/25] Current/Best: 23.05/ 46.65 GFLOPS | Progress: (10/10) | 7.39 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 7/25] Current/Best: 64.33/ 90.56 GFLOPS | Progress: (10/10) | 15.68 s Done.
+[Task 7/25] Current/Best: 47.84/ 47.84 GFLOPS | Progress: (4/10) | 2.21 s
+[Task 7/25] Current/Best: 34.60/ 47.84 GFLOPS | Progress: (8/10) | 3.98 s
+[Task 7/25] Current/Best: 10.16/ 47.84 GFLOPS | Progress: (10/10) | 4.97 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 8/25] Current/Best: 41.50/ 65.29 GFLOPS | Progress: (10/10) | 33.51 s
-[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
+[Task 8/25] Current/Best: 30.68/ 30.68 GFLOPS | Progress: (4/10) | 2.32 s
+[Task 8/25] Current/Best: 37.35/ 45.33 GFLOPS | Progress: (8/10) | 5.31 s
+[Task 8/25] Current/Best: 46.41/ 46.41 GFLOPS | Progress: (10/10) | 5.93 s Done.
-[Task 9/25] Current/Best: 60.73/ 82.22 GFLOPS | Progress: (10/10) | 11.42 s Done.
+[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
+[Task 9/25] Current/Best: 8.46/ 42.93 GFLOPS | Progress: (4/10) | 3.18 s
+[Task 9/25] Current/Best: 41.72/ 42.93 GFLOPS | Progress: (8/10) | 4.84 s
+[Task 9/25] Current/Best: 43.40/ 43.40 GFLOPS | Progress: (10/10) | 6.23 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 10/25] Current/Best: 27.21/ 55.24 GFLOPS | Progress: (10/10) | 11.12 s Done.
+[Task 10/25] Current/Best: 33.50/ 36.81 GFLOPS | Progress: (4/10) | 2.17 s
+[Task 10/25] Current/Best: 15.28/ 36.81 GFLOPS | Progress: (8/10) | 3.77 s
+[Task 10/25] Current/Best: 16.60/ 36.81 GFLOPS | Progress: (10/10) | 5.26 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 11/25] Current/Best: 85.07/ 85.07 GFLOPS | Progress: (10/10) | 10.00 s Done.
+[Task 11/25] Current/Best: 46.46/ 46.46 GFLOPS | Progress: (4/10) | 3.53 s
+[Task 11/25] Current/Best: 38.92/ 46.46 GFLOPS | Progress: (8/10) | 5.45 s
+[Task 11/25] Current/Best: 27.07/ 46.46 GFLOPS | Progress: (10/10) | 6.57 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 12/25] Current/Best: 50.72/ 68.54 GFLOPS | Progress: (10/10) | 11.57 s Done.
+[Task 12/25] Current/Best: 34.53/ 39.45 GFLOPS | Progress: (4/10) | 2.36 s
+[Task 12/25] Current/Best: 31.65/ 44.32 GFLOPS | Progress: (8/10) | 3.91 s
+[Task 12/25] Current/Best: 17.73/ 44.32 GFLOPS | Progress: (10/10) | 7.64 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 13/25] Current/Best: 22.31/ 65.46 GFLOPS | Progress: (10/10) | 19.41 s Done.
+[Task 13/25] Current/Best: 25.99/ 35.90 GFLOPS | Progress: (4/10) | 2.10 s
+[Task 13/25] Current/Best: 28.48/ 35.90 GFLOPS | Progress: (8/10) | 7.06 s
+[Task 13/25] Current/Best: 35.65/ 38.45 GFLOPS | Progress: (10/10) | 7.77 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 14/25] Current/Best: 87.35/ 87.71 GFLOPS | Progress: (10/10) | 5.70 s Done.
+[Task 14/25] Current/Best: 29.02/ 47.75 GFLOPS | Progress: (4/10) | 2.58 s
+[Task 14/25] Current/Best: 38.29/ 47.75 GFLOPS | Progress: (8/10) | 4.64 s
+[Task 14/25] Current/Best: 30.86/ 47.75 GFLOPS | Progress: (10/10) | 5.71 s Done.
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 15/25] Current/Best: 38.18/ 51.59 GFLOPS | Progress: (10/10) | 5.07 s Done.
+[Task 15/25] Current/Best: 41.66/ 43.09 GFLOPS | Progress: (4/10) | 2.09 s
+[Task 15/25] Current/Best: 22.98/ 43.09 GFLOPS | Progress: (8/10) | 5.28 s
+[Task 15/25] Current/Best: 12.10/ 43.09 GFLOPS | Progress: (10/10) | 6.04 s Done.
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 16/25] Current/Best: 30.83/ 61.08 GFLOPS | Progress: (10/10) | 5.07 s Done.
+[Task 16/25] Current/Best: 14.11/ 47.00 GFLOPS | Progress: (4/10) | 4.16 s
+[Task 16/25] Current/Best: 40.78/ 47.00 GFLOPS | Progress: (8/10) | 5.93 s
+[Task 16/25] Current/Best: 13.65/ 47.00 GFLOPS | Progress: (10/10) | 6.82 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 17/25] Current/Best: 54.49/ 68.61 GFLOPS | Progress: (10/10) | 6.46 s Done.
+[Task 17/25] Current/Best: 25.74/ 27.83 GFLOPS | Progress: (4/10) | 4.52 s
+[Task 17/25] Current/Best: 46.56/ 46.56 GFLOPS | Progress: (8/10) | 5.98 s
+[Task 17/25] Current/Best: 12.30/ 46.56 GFLOPS | Progress: (10/10) | 6.94 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 18/25] Current/Best: 45.63/ 61.39 GFLOPS | Progress: (10/10) | 10.53 s Done.
+[Task 18/25] Current/Best: 20.07/ 34.05 GFLOPS | Progress: (4/10) | 2.56 s
+[Task 18/25] Current/Best: 26.35/ 42.79 GFLOPS | Progress: (8/10) | 5.79 s
+[Task 18/25] Current/Best: 33.49/ 42.79 GFLOPS | Progress: (10/10) | 6.79 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 19/25] Current/Best: 99.57/ 99.57 GFLOPS | Progress: (10/10) | 5.14 s Done.
+[Task 19/25] Current/Best: 44.44/ 44.44 GFLOPS | Progress: (4/10) | 2.58 s
+[Task 19/25] Current/Best: 45.86/ 45.86 GFLOPS | Progress: (8/10) | 4.22 s
+[Task 19/25] Current/Best: 32.42/ 45.86 GFLOPS | Progress: (10/10) | 5.20 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 20/25] Current/Best: 34.33/ 46.20 GFLOPS | Progress: (10/10) | 5.47 s Done.
+[Task 20/25] Current/Best: 35.55/ 38.18 GFLOPS | Progress: (4/10) | 2.58 s
+[Task 20/25] Current/Best: 38.55/ 38.55 GFLOPS | Progress: (8/10) | 4.25 s
+[Task 20/25] Current/Best: 8.66/ 38.55 GFLOPS | Progress: (10/10) | 5.12 s Done.
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 21/25] Current/Best: 29.78/ 40.29 GFLOPS | Progress: (10/10) | 4.88 s Done.
+[Task 21/25] Current/Best: 22.51/ 35.86 GFLOPS | Progress: (4/10) | 2.60 s
+[Task 21/25] Current/Best: 11.92/ 37.32 GFLOPS | Progress: (8/10) | 3.97 s
+[Task 21/25] Current/Best: 13.60/ 37.32 GFLOPS | Progress: (10/10) | 4.85 s Done.
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 22/25] Current/Best: 59.79/ 102.15 GFLOPS | Progress: (10/10) | 6.66 s Done.
+[Task 22/25] Current/Best: 40.97/ 48.00 GFLOPS | Progress: (4/10) | 2.28 s
+[Task 22/25] Current/Best: 28.80/ 48.86 GFLOPS | Progress: (8/10) | 4.65 s
+[Task 22/25] Current/Best: 30.62/ 48.86 GFLOPS | Progress: (10/10) | 5.65 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 23/25] Current/Best: 60.67/ 60.67 GFLOPS | Progress: (10/10) | 19.24 s
+[Task 23/25] Current/Best: 26.07/ 27.08 GFLOPS | Progress: (4/10) | 10.41 s
+[Task 23/25] Current/Best: 9.40/ 29.51 GFLOPS | Progress: (8/10) | 12.53 s
+[Task 23/25] Current/Best: 17.33/ 31.99 GFLOPS | Progress: (10/10) | 13.42 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 24/25] Current/Best: 62.59/ 76.12 GFLOPS | Progress: (10/10) | 13.95 s Done.
- Done.
- Done.
- Done.
- Done.
+[Task 24/25] Current/Best: 32.87/ 34.13 GFLOPS | Progress: (4/10) | 4.51 s
+[Task 24/25] Current/Best: 14.52/ 34.13 GFLOPS | Progress: (8/10) | 11.00 s
... 1691 lines suppressed ...