* Move memory heavy tests from `test_pytorch_onnx_onnxruntime.py` to
`test_models_onnxruntime.py`. The former is run in parallel in CI,
while the latter is not. A change is that the moved tests are now
only covered in default opset export.
* Refactor and create base class for tests that export model to ONNX
and verify with ONNX Runtime. The new base class are parameterized
with `opset_version` and `is_script`. Further work can be done to
refactor existing test classes in `test_pytorch_onnx_onnxruntime.py`.
See #75630
* Reduce unnecessarily large tensor size in
`test_pytorch_onnx_onnxruntime.py` to further reduce memory usage
and test time.
After this PR, the running time for `test_pytorch_onnx_onnxruntime.py`
is reduced from `1338.82s (0:22:18)` to `225.07s (0:03:45)`,
benchmarked on 10900x with `-n 10`.
Fixes#79179
Pull Request resolved: https://github.com/pytorch/pytorch/pull/79640
Approved by: https://github.com/justinchuby, https://github.com/garymm
Should fix#78844
Custom op related tests utilize inline cpp extension to build custom
operator from c++ source snippet. Only two test cases become flaky after
parallel run, and both use inline cpp extension. Reverting to run these
tests in single process to try resolve the flakiness.
Reverts test skip added previously #78936.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/78944
Approved by: https://github.com/janeyx99, https://github.com/garymm
Currently `torch.onnx.export(.., operator_export_type=OperatorExportTypes.ONNX_ATEN_FALLBACK)` only issues ATen ops through explicit requests (e.g. `g.at()`) calls inside each op symbolic function. This is done based on specific conditions such as `operator_export_type==OperatorExportTypes.ONNX_ATEN_FALLBACK)` or `is_caffe2_aten_fallback()`
This PR extends the ATen fallback mechanism for scenarios when the symbolic function raises `RuntimeError` during export. The idea is that partial implementation of existing ONNX ops can fallback to ATen as a last resort. That is valuable because each operator can have many input combinations and not all are always implemented.
A minor fix was done to make sure the `overload_name` attribute is added to explicit ATen op fallback requests when a symbolic is not registered to a particular op.
ps: The behavior for builds with BUILD_CAFFE2=1 is not changed to ensure BC.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/74759
Approved by: https://github.com/garymm, https://github.com/msaroufim
`torch.cuda.synchronize()` is a heavy hammer and distorts benchmarking results a lot. Timer provides results that are closer to kernel times observed in profiler.
If you want, instead of `blocked_autorange` you can use `timeit` that repeats the stmt fixed number of times.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/75393
Approved by: https://github.com/davidberard98
Summary:
And add a new tool to update it in the future, which follows the policy
of using "latest as of 18 months ago". This policy is meant to balance:
* recent enough to increase the odds of being able to successfully
export
* old enough to increase the odds of exported model being runnable by
different ONNX implementations
Related changes:
* test_models.py: explicitly fix opset_version to 9 rather than relying on default. Caffe2 doesn't support newer versions.
* symbolic_helper.py:
* Remove a misleading comment
* Remove unnecessary check in `_set_opset_version`
* Use a range to define `_onnx_stable_opsets`
* test_pytorch_common.py:
* Rename a variable from min -> max. I think it was a copy-paste error.
* Make skip test messages more informative.
* Remove unused `skipIfONNXShapeInference`. More on that below.
* test_pytorch_onnx_onnxruntime.py:
* Make all the `TestCase` classes explicitly specify opset version.
* Make `test_unsupported_pad` respect `opset_version` by using `run_test`
* Unrelated simplification: make it obvious that all tests run with `onnx_shape_inference=True`. AFAICT this was already the case.
* There was one test that was entirely disabled (test_tolist) because it was asking to be skipped whenever `onnx_shape_inference=True`, but it was always True. I changed the model being tested so as to preserve the intended test coverage but still have the test actually pass.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/73898
Reviewed By: msaroufim
Differential Revision: D35264615
Pulled By: malfet
fbshipit-source-id: cda8fbdffe4cc8210d8d96e659e3a9adf1b5f1d2
(cherry picked from commit b5e639e88828d34442282d0b50c977e610a2ba3a)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/75108
- Add option to only run some graphs
- Add NNC Static vs Dynamic
- Update make_tensor bc it wasnt using strides
Test Plan: Imported from OSS
Reviewed By: ejguan
Differential Revision: D35374000
Pulled By: eellison
fbshipit-source-id: df16b8647f2309a8837207cacba55d30f46845ce
(cherry picked from commit 19feb54db049186972b47548cf3d83e76512adfd)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/74076
Extends the repro script to cpu and NNC. As in file:
Usage:
```
1. Run your script and pipe into a log file
PYTORCH_JIT_LOG_LEVEL=">>tensorexpr_fuser" python3 my_test.py &> log.txt
2. Run log_extract:
log_extract.py log.txt --baseline --nnc
```
Test Plan: Imported from OSS
Reviewed By: gchanan
Differential Revision: D34946883
Pulled By: eellison
fbshipit-source-id: 644012dbbca0b490820ef83e761c06b0dd009e52
(cherry picked from commit 5256c8f3ff8545033d1335cc96d34194abda1370)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/73881
NVFuser fusion groups can contain nvfuser-only ops, e.g. `prim::reshape_copy`. Previously, we couldn't get a baseline performance measurement because the nvfuser-only ops would error out on nnc- and no-fusion- runs. Instead, dump the fallback graphs, after the fallbacks are corrected into runnable fallbacks.
Test Plan: Imported from OSS
Reviewed By: eellison
Differential Revision: D34698307
Pulled By: davidberard98
fbshipit-source-id: c357b2736b789bfd347afe9c83a1b610b64881e0
(cherry picked from commit 5918d826502ff75fbc22d242844ae6435dd7d22a)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/72889
The script along with the GRAPH_EXPORT macro will allow for an easy way to extract IR from logs. One use case in this diff is to extract the fusion groups from nvfuser, so that the fusions can be tested individually.
Usage (e.g. for nvfuser test)
1. Write some test.py file that uses nvfuser
2. `PYTORCH_JIT_LOG_LEVEL=">>graph_fuser" python3 test.py 2>&1 | tee output.txt`
3. `python3 pytorch/scripts/jit/log_extract.py output.txt --nvfuser`
This will run with and without nvfuser to compare the output.
Alternatively, use `--output` to dump the IR so that it can be used in other applications.
Currently, only `--output` works (since generating input tensors is not supported)
Test Plan: Imported from OSS
Reviewed By: ngimel
Differential Revision: D34440189
Pulled By: davidberard98
fbshipit-source-id: fca0f619200ee37aba34bb39b69e6c640c263e26
(cherry picked from commit eb319166075db160f1628f0de545641fbecde8be)
Summary:
RFC: https://github.com/pytorch/rfcs/pull/40
This PR (re)introduces python codegen for unboxing wrappers. Given an entry of `native_functions.yaml` the codegen should be able to generate the corresponding C++ code to convert ivalues from the stack to their proper types. To trigger the codegen, run
```
tools/jit/gen_unboxing.py -d cg/torch/share/ATen
```
Merged changes on CI test. In https://github.com/pytorch/pytorch/issues/71782 I added an e2e test for static dispatch + codegen unboxing. The test exports a mobile model of mobilenetv2, load and run it on a new binary for lite interpreter: `test/mobile/custom_build/lite_predictor.cpp`.
## Lite predictor build specifics
1. Codegen: `gen.py` generates `RegisterCPU.cpp` and `RegisterSchema.cpp`. Now with this PR, once `static_dispatch` mode is enabled, `gen.py` will not generate `TORCH_LIBRARY` API calls in those cpp files, hence avoids interaction with the dispatcher. Once `USE_LIGHTWEIGHT_DISPATCH` is turned on, `cmake/Codegen.cmake` calls `gen_unboxing.py` which generates `UnboxingFunctions.h`, `UnboxingFunctions_[0-4].cpp` and `RegisterCodegenUnboxedKernels_[0-4].cpp`.
2. Build: `USE_LIGHTWEIGHT_DISPATCH` adds generated sources into `all_cpu_cpp` in `aten/src/ATen/CMakeLists.txt`. All other files remain unchanged. In reality all the `Operators_[0-4].cpp` are not necessary but we can rely on linker to strip them off.
## Current CI job test coverage update
Created a new CI job `linux-xenial-py3-clang5-mobile-lightweight-dispatch-build` that enables the following build options:
* `USE_LIGHTWEIGHT_DISPATCH=1`
* `BUILD_LITE_INTERPRETER=1`
* `STATIC_DISPATCH_BACKEND=CPU`
This job triggers `test/mobile/lightweight_dispatch/build.sh` and builds `libtorch`. Then the script runs C++ tests written in `test_lightweight_dispatch.cpp` and `test_codegen_unboxing.cpp`. Recent commits added tests to cover as many C++ argument type as possible: in `build.sh` we installed PyTorch Python API so that we can export test models in `tests_setup.py`. Then we run C++ test binary to run these models on lightweight dispatch enabled runtime.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/69881
Reviewed By: iseeyuan
Differential Revision: D33692299
Pulled By: larryliu0820
fbshipit-source-id: 211e59f2364100703359b4a3d2ab48ca5155a023
(cherry picked from commit 58e1c9a25e3d1b5b656282cf3ac2f548d98d530b)
These were left out of the intial migration for some reason so this just
transfers over those tests
Signed-off-by: Eli Uriegas <eliuriegasfb.com>
Pull Request resolved: https://github.com/pytorch/pytorch/pull/71644
Signed-off-by: Eli Uriegas <eliuriegas@fb.com>
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/64929
Auto categorized 63% of the commits for PyTorch 1.10 release (2.2k out of 3.4k commits)
Test Plan: Imported from OSS
Reviewed By: malfet
Differential Revision: D33768760
Pulled By: anjali411
fbshipit-source-id: 0655090af83e923f8c26fa1ce9f190edc542b97e
(cherry picked from commit 2fe30f77b8)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/69332
---
## Context
The `build_android.sh` script currently does not forward Vulkan configuration options, which makes it impossible to control them when running `build_pytorch_android.sh`.
## Changes
Slightly change the script to allow Vulkan configuration options to propagate from `build_pytorch_android.sh` to `build_android.sh`
Test Plan: Imported from OSS
Reviewed By: beback4u
Differential Revision: D32840908
Pulled By: SS-JIA
fbshipit-source-id: e55d89c93c996b92b743cf047f5a285bb516bbc4
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/67805
Also fix Reduce ops on binary_cross_entropy_with_logits
The graph says the output is a scalar but with `keepdims=1`
(the default), the output should be a tensor of rank 1. We set keep
`keepdims=0` to make it clear that we want a scalar output.
This previously went unnoticed because ONNX Runtime does not strictly
enforce shape inference mismatches if the model is not using the latest
opset version.
Test Plan: Imported from OSS
Reviewed By: msaroufim
Differential Revision: D32181304
Pulled By: malfet
fbshipit-source-id: 1462d8a313daae782013097ebf6341a4d1632e2c
Co-authored-by: Bowen Bao <bowbao@microsoft.com>
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/66513
These were missed in the migration of onnx to github actions.
Adds ort tests with 2 shards for the onnx workflow
Signed-off-by: Eli Uriegas <eliuriegas@fb.com>
Test Plan: Imported from OSS
Reviewed By: malfet
Differential Revision: D31599433
Pulled By: seemethere
fbshipit-source-id: 73dce0d3017c4280e64f0c8578e2be7ef6a168d6
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/66513
These were missed in the migration of onnx to github actions.
Adds ort tests with 2 shards for the onnx workflow
Signed-off-by: Eli Uriegas <eliuriegas@fb.com>
Test Plan: Imported from OSS
Reviewed By: malfet
Differential Revision: D31591512
Pulled By: seemethere
fbshipit-source-id: 4a8bb3f0e62ff98ee77d3d8afc905f4e02db6f24
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/62419
This diff adds support for cpu only kineto profiler on mobile. Thus
enabling chrome trace generation on mobile. This bring cpp API for
mobile profiling on part with Torchscript.
This is done via:
1. Utilizating debug handle annotations in KinetoEvent.
2. Adding post processing capability, via callbacks, to
KinetoThreadLocalState
3. Creating new RAII stype profiler, KinetoEdgeCPUProfiler, which can be
used in surrounding scope of model execution. This will write chrome
trace to the location specified in profiler constructor.
Test Plan:
MobileProfiler.ModuleHierarchy
Imported from OSS
Reviewed By: raziel
Differential Revision: D29993660
fbshipit-source-id: 0b44f52f9e9c5f5aff81ebbd9273c254c3c03299
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/62855
Test Plan: Test on Private Pod with the [HelloWorld](https://fburl.com/3hiwkkhm) demo
Reviewed By: xta0
Differential Revision: D30174151
Pulled By: hanton
fbshipit-source-id: 22cd8663ac239811bf8ed1c3b6301460d798dbfa
Summary:
Two changes:
1. Build lite interpreter as default for iOS
2. Switch the previous lite interpreter test to full jit build test
Test Plan: Imported from OSS
Differential Revision: D27698039
Reviewed By: xta0
Pulled By: cccclai
fbshipit-source-id: 022b554f4997ae577681f2b79a9ebe9236ca4f7d
Summary:
Build lite interpreter as default for android, should wait until https://github.com/pytorch/pytorch/pull/56002 lands
Mainly two changes:
1. Use lite interpreter as default for Android
2. Switch the lite interpreter build test to full jit build test
Test Plan: Imported from OSS
Differential Revision: D27695530
Reviewed By: IvanKobzarev
Pulled By: cccclai
fbshipit-source-id: e1b2c70fee6590accc22c7404b9dd52c7d7c36e2
Summary:
Some machines don't have a versionless `python` on their PATH, which breaks these existing shebangs.
I'm assuming that all the existing versionless `python` shebangs are meant to be `python3` and not `python2`; please let me know if my assumption was incorrect for any of these.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/58275
Test Plan: CI.
Reviewed By: zhouzhuojie
Differential Revision: D28428143
Pulled By: samestep
fbshipit-source-id: 6562be3d12924db72a92a0207b060ef740f61ebf
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/57597
* Special post process for onnx::Cast and onnx::ConstantOfShape
* Update `test_pytorch_onnx_shape_inference.py` to be unit test over shape inference patterns.
Test Plan: Imported from OSS
Reviewed By: malfet
Differential Revision: D28393529
Pulled By: SplitInfinity
fbshipit-source-id: fc26032ddb842d4e299447da39564b28049752ed
Co-authored-by: BowenBao <bowbao@microsoft.com>
Summary:
Expanding support to all builds
Pull Request resolved: https://github.com/pytorch/pytorch/pull/56323
Test Plan: CI
Reviewed By: malfet
Differential Revision: D28171478
Pulled By: ilia-cher
fbshipit-source-id: 16bc752d1be3cbaeda5316f5d8a687ae05a83d22
Summary:
[distutils](https://docs.python.org/3/library/distutils.html) is on its way out and will be deprecated-on-import for Python 3.10+ and removed in Python 3.12 (see [PEP 632](https://www.python.org/dev/peps/pep-0632/)). There's no reason for us to keep it around since all the functionality we want from it can be found in `setuptools` / `sysconfig`. `setuptools` includes a copy of most of `distutils` (which is fine to use according to the PEP), that it uses under the hood, so this PR also uses that in some places.
Fixes#56527
Pull Request resolved: https://github.com/pytorch/pytorch/pull/57040
Pulled By: driazati
Reviewed By: nikithamalgifb
Differential Revision: D28051356
fbshipit-source-id: 1ca312219032540e755593e50da0c9e23c62d720
Summary:
This PR is step 2 (after https://github.com/pytorch/pytorch/issues/56708) to having JIT coverage--it actually uses the plug-in in CI!
Disclaimer: note that this will mark the entire JIT'd function/method as covered without seeking proof that the
compiled code has been executed. This means that even if the code chunk is merely compiled and not run, it will get
marked as covered.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/56310
Test Plan:
We should see coverage improvements in CI after. A file to look out for would be `torch/jit/quantized.py`, which should have more coverage after this PR, which it does!
d3283ccd8c/torch/jit/quantized.py vs https://codecov.io/gh/pytorch/pytorch/src/master/torch/jit/quantized.py
More generally, the whole jit folder got ~3% increase in coverage, I believe.
Reviewed By: walterddr
Differential Revision: D28000672
Pulled By: janeyx99
fbshipit-source-id: 6712979d63a5e1224a92ee9bd9679ec62cf1cbba
Summary:
This PR is step 2 (after https://github.com/pytorch/pytorch/issues/56708) to having JIT coverage--it actually uses the plug-in in CI!
Disclaimer: note that this will mark the entire JIT'd function/method as covered without seeking proof that the
compiled code has been executed. This means that even if the code chunk is merely compiled and not run, it will get
marked as covered.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/56310
Test Plan:
We should see coverage improvements in CI after. A file to look out for would be `torch/jit/quantized.py`, which should have more coverage after this PR, which it does!
d3283ccd8c/torch/jit/quantized.py vs https://codecov.io/gh/pytorch/pytorch/src/master/torch/jit/quantized.py
More generally, the whole jit folder got ~3% increase in coverage, I believe.
Reviewed By: ezyang
Differential Revision: D27967517
Pulled By: janeyx99
fbshipit-source-id: 53fd8431d772c2447191135c29d1b166ecd42f50
Summary:
This adds:
- new categories
- global commit counter
- support for new "Reverted" label on PRs
- new export system to multiple files
Pull Request resolved: https://github.com/pytorch/pytorch/pull/54594
Reviewed By: H-Huang
Differential Revision: D27396011
Pulled By: albanD
fbshipit-source-id: ca1ec3a1b90221ba26fd8b053dfb10f614f05909
Summary:
*Context:* https://github.com/pytorch/pytorch/issues/53406 added a lint for trailing whitespace at the ends of lines. However, in order to pass FB-internal lints, that PR also had to normalize the trailing newlines in four of the files it touched. This PR adds an OSS lint to normalize trailing newlines.
The changes to the following files (made in 54847d0adb9be71be4979cead3d9d4c02160e4cd) are the only manually-written parts of this PR:
- `.github/workflows/lint.yml`
- `mypy-strict.ini`
- `tools/README.md`
- `tools/test/test_trailing_newlines.py`
- `tools/trailing_newlines.py`
I would have liked to make this just a shell one-liner like the other three similar lints, but nothing I could find quite fit the bill. Specifically, all the answers I tried from the following Stack Overflow questions were far too slow (at least a minute and a half to run on this entire repository):
- [How to detect file ends in newline?](https://stackoverflow.com/q/38746)
- [How do I find files that do not end with a newline/linefeed?](https://stackoverflow.com/q/4631068)
- [How to list all files in the Git index without newline at end of file](https://stackoverflow.com/q/27624800)
- [Linux - check if there is an empty line at the end of a file [duplicate]](https://stackoverflow.com/q/34943632)
- [git ensure newline at end of each file](https://stackoverflow.com/q/57770972)
To avoid giving false positives during the few days after this PR is merged, we should probably only merge it after https://github.com/pytorch/pytorch/issues/54967.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/54737
Test Plan:
Running the shell script from the "Ensure correct trailing newlines" step in the `quick-checks` job of `.github/workflows/lint.yml` should print no output and exit in a fraction of a second with a status of 0. That was not the case prior to this PR, as shown by this failing GHA workflow run on an earlier draft of this PR:
- https://github.com/pytorch/pytorch/runs/2197446987?check_suite_focus=true
In contrast, this run (after correcting the trailing newlines in this PR) succeeded:
- https://github.com/pytorch/pytorch/pull/54737/checks?check_run_id=2197553241
To unit-test `tools/trailing_newlines.py` itself (this is run as part of our "Test tools" GitHub Actions workflow):
```
python tools/test/test_trailing_newlines.py
```
Reviewed By: malfet
Differential Revision: D27409736
Pulled By: samestep
fbshipit-source-id: 46f565227046b39f68349bbd5633105b2d2e9b19
Summary:
Promotion to PyPI should be more flexible to allow any package to be
promoted to PyPI.
After we re-added a version suffix to cuda 10.2 it means that this
script needs to have the flexibility to designate which platform and
which version suffix will actually be uploaded to PyPI
Should coincide with https://github.com/pytorch/builder/pull/678
Signed-off-by: Eli Uriegas <eliuriegas@fb.com>
Pull Request resolved: https://github.com/pytorch/pytorch/pull/53774
Reviewed By: jbschlosser
Differential Revision: D27052347
Pulled By: seemethere
fbshipit-source-id: 71129cc5afbd7de448c970ef721bc979c3420586
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/53306
* [ONNX] Fix for sequence of mutations in blocks (#51577)
Fixes consecutive mutations in a tensor inside blocks.
Also, support append and pop in blocks.
* Support inplace operations + indexing
* Clean up old pass for remove mutations
* Add loop test
* Fixes for set attr in loops
* Removing the new jit API flag
* [ONNX] Redesign onnx pass to enable shape type dependent pattern conversion - cont (#51795)
With the introduction of ONNX shape inference, shape and type are inferred on the fly as operators get converted from ATen to ONNX when running symbolic function. This resolves the shape/type requirement for the symbolic functions. The pre-onnx passes however, can not be supported by shape inference, since at that stage the operators in the graph are still ATen operators.
This PR is to update the design of ONNX pass, to enable a mechanism of capturing subgraphs of ATen operators of certain patterns, and convert them later, when shape/type information of upstream operators are available.
The new design will require pre-onnx passes that need shape/type to be written in two parts, encapsulation and conversion.
The encapsulation part will find the nodes of patterns, like how pre-onnx passes were written previously. But instead of converting the nodes, it will encapsulate them into a sub-block of a new placeholder node. This part is called before onnx pass, so it runs before calling symbolic functions.
The conversion part will be called inside the onnx pass. In onnx pass, run_symbolic_func will be called for each node in topological order. When it reaches the placeholder node, the conversion part will be invoked. It will convert the nodes inside the sub-block based on pattern. By that time, it will have shape/type of upstream operators available. After the conversion is complete, the placeholder node will be removed, and nodes inside its sub-block converted. Run_symbolic_func will be called for these nodes, and they will be converted from ATen operator to ONNX operator.
This PR includes several other fixes, listed below.
* ~~replace helper.cpp with onnx_utils.cpp for holding utility functions.~~
* fix EraseNumberTypes on Bool type, the code was outdated that back then Bool type doesn't exist.
* ~~enable onnx shape inference in export with parameter/initializer data.~~
* other code clean ups.
* fix insertion of identity nodes for loop opset 13 sequence output.
~~PR depends on #51603~~
* Fix after merge
* clang
* Fix clang
* Fix clang
* Fix warning message.
* Fixes for non-model param attributes
* Fix for caffe2
* Additional test
* clang
* Skip test for lower opsets
* fix clang-tidy
* Update init.cpp
* Update remove_inplace_ops_for_onnx.cpp
* Update remove_inplace_ops_for_onnx.cpp
* Update remove_inplace_ops_for_onnx.cpp
* Fix for clang formatting
Test Plan: Imported from OSS
Reviewed By: pbelevich, malfet
Differential Revision: D26922416
Pulled By: SplitInfinity
fbshipit-source-id: e7108620b39b6404c594910786c4d275fee59d84
Co-authored-by: Bowen Bao <bowbao@microsoft.com>
Summary:
Context: https://github.com/pytorch/pytorch/pull/53299#discussion_r587882857
These are the only hand-written parts of this diff:
- the addition to `.github/workflows/lint.yml`
- the file endings changed in these four files (to appease FB-internal land-blocking lints):
- `GLOSSARY.md`
- `aten/src/ATen/core/op_registration/README.md`
- `scripts/README.md`
- `torch/csrc/jit/codegen/fuser/README.md`
The rest was generated by running this command (on macOS):
```
git grep -I -l ' $' -- . ':(exclude)**/contrib/**' ':(exclude)third_party' | xargs gsed -i 's/ *$//'
```
I looked over the auto-generated changes and didn't see anything that looked problematic.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/53406
Test Plan:
This run (after adding the lint but before removing existing trailing spaces) failed:
- https://github.com/pytorch/pytorch/runs/2043032377
This run (on the tip of this PR) succeeded:
- https://github.com/pytorch/pytorch/runs/2043296348
Reviewed By: walterddr, seemethere
Differential Revision: D26856620
Pulled By: samestep
fbshipit-source-id: 3f0de7f7c2e4b0f1c089eac9b5085a58dd7e0d97
Summary:
Adds a script so that we can take wheels directly from
download.pytorch.org and publish them to pypi
This is currently mainly used to prep windows binaries for publication to PyPI
Signed-off-by: Eli Uriegas <eliuriegas@fb.com>
Pull Request resolved: https://github.com/pytorch/pytorch/pull/53056
Reviewed By: H-Huang
Differential Revision: D26738642
Pulled By: seemethere
fbshipit-source-id: 96777ed6c3f3454bddb4bc13121f727074312816
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/51419
## Summary
1. Add an option `BUILD_LITE_INTERPRETER` in `caffe2/CMakeLists.txt` and set `OFF` as default.
2. Update 'build_android.sh' with an argument to swtich `BUILD_LITE_INTERPRETER`, 'OFF' as default.
3. Add a mini demo app `lite_interpreter_demo` linked with `libtorch` library, which can be used for quick test.
## Test Plan
Built lite interpreter version of libtorch and test with Image Segmentation demo app ([android version](https://github.com/pytorch/android-demo-app/tree/master/ImageSegmentation)/[ios version](https://github.com/pytorch/ios-demo-app/tree/master/ImageSegmentation))
### Android
1. **Prepare model**: Prepare the lite interpreter version of model by run the script below to generate the scripted model `deeplabv3_scripted.pt` and `deeplabv3_scripted.ptl`
```
import torch
model = torch.hub.load('pytorch/vision:v0.7.0', 'deeplabv3_resnet50', pretrained=True)
model.eval()
scripted_module = torch.jit.script(model)
# Export full jit version model (not compatible lite interpreter), leave it here for comparison
scripted_module.save("deeplabv3_scripted.pt")
# Export lite interpreter version model (compatible with lite interpreter)
scripted_module._save_for_lite_interpreter("deeplabv3_scripted.ptl")
```
2. **Build libtorch lite for android**: Build libtorch for android for all 4 android abis (armeabi-v7a, arm64-v8a, x86, x86_64) `BUILD_LITE_INTERPRETER=1 ./scripts/build_pytorch_android.sh`. This pr is tested on Pixel 4 emulator with x86, so use cmd `BUILD_LITE_INTERPRETER=1 ./scripts/build_pytorch_android.sh x86` to specify abi to save built time. After the build finish, it will show the library path:
```
...
BUILD SUCCESSFUL in 55s
134 actionable tasks: 22 executed, 112 up-to-date
+ find /Users/chenlai/pytorch/android -type f -name '*aar'
+ xargs ls -lah
-rw-r--r-- 1 chenlai staff 13M Feb 11 11:48 /Users/chenlai/pytorch/android/pytorch_android/build/outputs/aar/pytorch_android-release.aar
-rw-r--r-- 1 chenlai staff 36K Feb 9 16:45 /Users/chenlai/pytorch/android/pytorch_android_torchvision/build/outputs/aar/pytorch_android_torchvision-release.aar
```
3. **Use the PyTorch Android libraries built from source in the ImageSegmentation app**: Create a folder 'libs' in the path, the path from repository root will be `ImageSegmentation/app/libs`. Copy `pytorch_android-release` to the path `ImageSegmentation/app/libs/pytorch_android-release.aar`. Copy 'pytorch_android_torchvision` (downloaded from [here](https://oss.sonatype.org/#nexus-search;quick~torchvision_android)) to the path `ImageSegmentation/app/libs/pytorch_android_torchvision.aar` Update the `dependencies` part of `ImageSegmentation/app/build.gradle` to
```
dependencies {
implementation 'androidx.appcompat:appcompat:1.2.0'
implementation 'androidx.constraintlayout:constraintlayout:2.0.2'
testImplementation 'junit:junit:4.12'
androidTestImplementation 'androidx.test.ext:junit:1.1.2'
androidTestImplementation 'androidx.test.espresso:espresso-core:3.3.0'
implementation(name:'pytorch_android-release', ext:'aar')
implementation(name:'pytorch_android_torchvision', ext:'aar')
implementation 'com.android.support:appcompat-v7:28.0.0'
implementation 'com.facebook.fbjni:fbjni-java-only:0.0.3'
}
```
Update `allprojects` part in `ImageSegmentation/build.gradle` to
```
allprojects {
repositories {
google()
jcenter()
flatDir {
dirs 'libs'
}
}
}
```
4. **Update model loader api**: Update `ImageSegmentation/app/src/main/java/org/pytorch/imagesegmentation/MainActivity.java` by
4.1 Add new import: `import org.pytorch.LiteModuleLoader;`
4.2 Replace the way to load pytorch lite model
```
// mModule = Module.load(MainActivity.assetFilePath(getApplicationContext(), "deeplabv3_scripted.pt"));
mModule = LiteModuleLoader.load(MainActivity.assetFilePath(getApplicationContext(), "deeplabv3_scripted.ptl"));
```
5. **Test app**: Build and run the ImageSegmentation app in Android Studio,
### iOS
1. **Prepare model**: Same as Android.
2. **Build libtorch lite for ios** `BUILD_PYTORCH_MOBILE=1 IOS_PLATFORM=SIMULATOR BUILD_LITE_INTERPRETER=1 ./scripts/build_ios.sh`
3. **Remove Cocoapods from the project**: run `pod deintegrate`
4. **Link ImageSegmentation demo app with the custom built library**:
Open your project in XCode, go to your project Target’s **Build Phases - Link Binaries With Libraries**, click the **+** sign and add all the library files located in `build_ios/install/lib`. Navigate to the project **Build Settings**, set the value **Header Search Paths** to `build_ios/install/include` and **Library Search Paths** to `build_ios/install/lib`.
In the build settings, search for **other linker flags**. Add a custom linker flag below
```
-all_load
```
Finally, disable bitcode for your target by selecting the Build Settings, searching for Enable Bitcode, and set the value to No.
**
5. Update library and api**
5.1 Update `TorchModule.mm``
To use the custom built libraries the project, replace `#import <LibTorch/LibTorch.h>` (in `TorchModule.mm`) which is needed when using LibTorch via Cocoapods with the code below:
```
//#import <LibTorch/LibTorch.h>
#include "ATen/ATen.h"
#include "caffe2/core/timer.h"
#include "caffe2/utils/string_utils.h"
#include "torch/csrc/autograd/grad_mode.h"
#include "torch/script.h"
#include <torch/csrc/jit/mobile/function.h>
#include <torch/csrc/jit/mobile/import.h>
#include <torch/csrc/jit/mobile/interpreter.h>
#include <torch/csrc/jit/mobile/module.h>
#include <torch/csrc/jit/mobile/observer.h>
```
5.2 Update `ViewController.swift`
```
// if let filePath = Bundle.main.path(forResource:
// "deeplabv3_scripted", ofType: "pt"),
// let module = TorchModule(fileAtPath: filePath) {
// return module
// } else {
// fatalError("Can't find the model file!")
// }
if let filePath = Bundle.main.path(forResource:
"deeplabv3_scripted", ofType: "ptl"),
let module = TorchModule(fileAtPath: filePath) {
return module
} else {
fatalError("Can't find the model file!")
}
```
### Unit test
Add `test/cpp/lite_interpreter`, with one unit test `test_cores.cpp` and a light model `sequence.ptl` to test `_load_for_mobile()`, `bc.find_method()` and `bc.forward()` functions.
### Size:
**With the change:**
Android:
x86: `pytorch_android-release.aar` (**13.8 MB**)
IOS:
`pytorch/build_ios/install/lib` (lib: **66 MB**):
```
(base) chenlai@chenlai-mp lib % ls -lh
total 135016
-rw-r--r-- 1 chenlai staff 3.3M Feb 15 20:45 libXNNPACK.a
-rw-r--r-- 1 chenlai staff 965K Feb 15 20:45 libc10.a
-rw-r--r-- 1 chenlai staff 4.6K Feb 15 20:45 libclog.a
-rw-r--r-- 1 chenlai staff 42K Feb 15 20:45 libcpuinfo.a
-rw-r--r-- 1 chenlai staff 39K Feb 15 20:45 libcpuinfo_internals.a
-rw-r--r-- 1 chenlai staff 1.5M Feb 15 20:45 libeigen_blas.a
-rw-r--r-- 1 chenlai staff 148K Feb 15 20:45 libfmt.a
-rw-r--r-- 1 chenlai staff 44K Feb 15 20:45 libpthreadpool.a
-rw-r--r-- 1 chenlai staff 166K Feb 15 20:45 libpytorch_qnnpack.a
-rw-r--r-- 1 chenlai staff 384B Feb 15 21:19 libtorch.a
-rw-r--r-- 1 chenlai staff **60M** Feb 15 20:47 libtorch_cpu.a
```
`pytorch/build_ios/install`:
```
(base) chenlai@chenlai-mp install % du -sh *
14M include
66M lib
2.8M share
```
**Master (baseline):**
Android:
x86: `pytorch_android-release.aar` (**16.2 MB**)
IOS:
`pytorch/build_ios/install/lib` (lib: **84 MB**):
```
(base) chenlai@chenlai-mp lib % ls -lh
total 172032
-rw-r--r-- 1 chenlai staff 3.3M Feb 17 22:18 libXNNPACK.a
-rw-r--r-- 1 chenlai staff 969K Feb 17 22:18 libc10.a
-rw-r--r-- 1 chenlai staff 4.6K Feb 17 22:18 libclog.a
-rw-r--r-- 1 chenlai staff 42K Feb 17 22:18 libcpuinfo.a
-rw-r--r-- 1 chenlai staff 1.5M Feb 17 22:18 libeigen_blas.a
-rw-r--r-- 1 chenlai staff 44K Feb 17 22:18 libpthreadpool.a
-rw-r--r-- 1 chenlai staff 166K Feb 17 22:18 libpytorch_qnnpack.a
-rw-r--r-- 1 chenlai staff 384B Feb 17 22:19 libtorch.a
-rw-r--r-- 1 chenlai staff 78M Feb 17 22:19 libtorch_cpu.a
```
`pytorch/build_ios/install`:
```
(base) chenlai@chenlai-mp install % du -sh *
14M include
84M lib
2.8M share
```
Test Plan: Imported from OSS
Reviewed By: iseeyuan
Differential Revision: D26518778
Pulled By: cccclai
fbshipit-source-id: 4503ffa1f150ecc309ed39fb0549e8bd046a3f9c
Summary:
Usage explanation will be in the release note runbook.
This allows to generate diffs like:
```
Processing torch.nn
Things that were added:
{'quantizable', 'ChannelShuffle', 'LazyConvTranspose2d', 'LazyConv2d', 'LazyConvTranspose3d', 'LazyConv1d', 'GaussianNLLLoss', 'LazyConv3d', 'PixelUnshuffle', 'UninitializedParameter', 'LazyLinear', 'LazyConvTranspose1d'}
Things that were removed:
set()
```
This can then be shared with module owners along with the commits to help them validate that the namespace changes for their submodule is as expected.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/51685
Reviewed By: zhangguanheng66
Differential Revision: D26260258
Pulled By: albanD
fbshipit-source-id: 40e40f86314e17246899d01ffa4b2631e93b52f7
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/51521
* Add loop & if node to the list of nodes that could produce sequence type output.
* Switch from `[]` to `at()` to avoid segfault of out of range access.
Test Plan: Imported from OSS
Reviewed By: pbelevich
Differential Revision: D26203112
Pulled By: SplitInfinity
fbshipit-source-id: e990eeed933124b195be0be159271e33fb485063
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/51517
Fix get/set attributes when getting/setting a model parameter.
This PR also fixes inplace ops in If blocks.
Test Plan: Imported from OSS
Reviewed By: pbelevich
Differential Revision: D26203116
Pulled By: SplitInfinity
fbshipit-source-id: bed6ee6dd92b5b43febc8c584a6872290f8fe33f
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/50911
Need to replace dtype of export created scalars from float to double. (In torch implicit conversion logic, python numbers are double)
Test case skipped in CI due to that current CI job env does not have CUDA support.
Test Plan: Imported from OSS
Reviewed By: pbelevich
Differential Revision: D26050889
Pulled By: SplitInfinity
fbshipit-source-id: 1fdde23a68d4793e6b9a82840acc213e5c3aa760
Summary:
Handle sequence output shape and type inference.
This PR fixes value type of sequence outputs. Prior to this, all model sequence type outputs were unfolded for ONNX models.
This PR also enable shape inference for sequence outputs to represent the dynamic shape of these values.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/46542
Reviewed By: ezyang
Differential Revision: D24924236
Pulled By: bzinodev
fbshipit-source-id: 506e70a38cfe31069191d7f40fc6375239c6aafe
Summary:
Update pass that handles prim::ListUnpack in peephole file, so that it also covers the case when input to the node is of ListType.
Fixes https://github.com/pytorch/pytorch/issues/45816
Pull Request resolved: https://github.com/pytorch/pytorch/pull/46264
Reviewed By: mrshenli
Differential Revision: D24566070
Pulled By: bzinodev
fbshipit-source-id: 32555487054f6a7fe02cc17c66bcbe81ddf9623e
Summary:
First commit contains the initial code from Richard's branch.
Second commit are the changes that I made during the writing process
Third commit is the update to support category/topic pair for each commit
Pull Request resolved: https://github.com/pytorch/pytorch/pull/47360
Reviewed By: ejguan
Differential Revision: D24741003
Pulled By: albanD
fbshipit-source-id: d0fcc6765968dc1732d8a515688d11372c7e653d
Summary:
Currently, no test reports are uploaded to CI because the paths for the `onnx` runs are incorrect. This PR attempts to change that.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/47315
Reviewed By: malfet
Differential Revision: D24727607
Pulled By: janeyx99
fbshipit-source-id: f6d91698fdb15a39e01ef812032d4cd30621f864
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/46383
The old `USE_METAL` is actually being used by Caffe2. Here we introduce a new macro to enable metal in pytorch.
ghstack-source-id: 114499392
Test Plan:
- Circle CI
- The Person Segmentation model works
Reviewed By: linbinyu
Differential Revision: D24322018
fbshipit-source-id: 4e5548afba426b49f314366d89b18ba0c7e745ca
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/46112
### Summary
This PR adds the support of running torchscript models on iOS GPU via Metal (Inference only). The feature is currently in prototype state, API changes are expected. The tutorial and the documents will be added once it goes to beta.
allow-large-files
- Users API
```
auto module = torch::jit::load(model);
module.eval();
at::Tensor input = at::ones({1,3,224,224}, at::ScalarType::Float).metal();
auto output = module.forward({input}).toTensor().cpu();
```
- Supported Models
- Person Segmentation v106 (FB Internal)
- Mobilenetv2
- Supported Operators
- aten::conv2d
- aten::addmm
- aten::add.Tensor
- aten::sub.Tensor
- aten::mul.Tensor
- aten::relu
- aten::hardtanh
- aten::hardtanh_
- aten::sigmoid
- aten::max_pool2d
- aten::adaptive_avg_pool2d
- aten::reshape
- aten::t
- aten::view
- aten::log_softmax.int
- aten::upsample_nearest2d.vec
- Supported Devices
- Apple A9 and above
- iOS 10.2 and above
- CMake scripts
- `IOS_ARCH=arm64 ./scripts/build_ios.sh -DUSE_METAL=ON`
### Test Plan
- Circle CI
ghstack-source-id: 114155638
Test Plan:
1. Sandcastle CI
2. Circle CI
Reviewed By: dreiss
Differential Revision: D23236555
fbshipit-source-id: 98ffc48b837e308bc678c37a9a5fd8ae72d11625
Summary:
* Support propagating `dim_param` in ONNX by encoding as `ShapeSymbol` in `SymbolicShape` of outputs. If export is called with `dynamic_axes` provided, shape inference will start with these axes set as dynamic.
* Add new test file `test_pytorch_onnx_shape_inference.py`, reusing all test cases from `test_pytorch_onnx_onnxruntime.py`, but focus on validating shape for all nodes in graph. Currently this is not enabled in the CI, since there are still quite some existing issues and corner cases to fix. The test is default to run only at opset 12.
* Bug fixes, such as div, _len, and peephole.cpp passes for PackPadded, and LogSoftmaxCrossEntropy.
* This PR depends on existing PR such as 44332.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/44920
Reviewed By: eellison
Differential Revision: D23958398
Pulled By: bzinodev
fbshipit-source-id: 00479d9bd19c867d526769a15ba97ec16d56e51d
Summary:
There is a module called `2to3` which you can target for future specifically to remove these, the directory of `caffe2` has the most redundant imports:
```2to3 -f future -w caffe2```
Pull Request resolved: https://github.com/pytorch/pytorch/pull/45033
Reviewed By: seemethere
Differential Revision: D23808648
Pulled By: bugra
fbshipit-source-id: 38971900f0fe43ab44a9168e57f2307580d36a38
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/44651
Adds pruning for our anaconda channels (pytorch-nightly, pytorch-test)
into our CI pipeline so that it gets run on a more consistent basis.
Signed-off-by: Eli Uriegas <eliuriegas@fb.com>
Test Plan: Imported from OSS
Reviewed By: walterddr
Differential Revision: D23692851
Pulled By: seemethere
fbshipit-source-id: fa69b506b73805bf2ffbde75d221aef1ee3f753e
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/43564
Static dispatch was originally introduced for mobile selective build.
Since we have added selective build support for dynamic dispatch and
tested it in FB production for months, we can deprecate static dispatch
to reduce the complexity of the codebase.
Test Plan: Imported from OSS
Reviewed By: ezyang
Differential Revision: D23324452
Pulled By: ljk53
fbshipit-source-id: d2970257616a8c6337f90249076fca1ae93090c7
Summary:
build_android.sh should check PYTHON environment variable before trying to use default python executable.
Even in that case, try to pick python3 over python2 when available.
Closes https://github.com/pytorch/pytorch/issues/41795
Pull Request resolved: https://github.com/pytorch/pytorch/pull/41927
Reviewed By: seemethere
Differential Revision: D22696850
Pulled By: malfet
fbshipit-source-id: be236c2baf54a1cd111e55ee7743cdc93cb6b9d7
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/39341
This PR introduces neon backend for vec256 class for float datatype.
For now only aarch64 is enabled due to few issues with enabling in
aarch32 bit.
Test Plan:
vec256_test
Imported from OSS
Differential Revision: D21822399
fbshipit-source-id: 3851c4336d93d1c359c85b38cf19904f82bc7b8d
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/40059
This benchmark is added specifically for mobile to see if compiler is
autovectorizing and thus we have no advantage of neon backend for vec256
for add op.
Test Plan:
CI
Imported from OSS
Differential Revision: D22055146
fbshipit-source-id: 43ba6c4ae57c6f05d84887c2750ce21ae1b0f0b5
Summary:
This re-applies D21232894 (b9d3869df3) and D22162524, plus updates jni_deps in a few places
to avoid breaking host JNI tests.
Test Plan: `buck test @//fbandroid/mode/server //fbandroid/instrumentation_tests/com/facebook/caffe2:host-test`
Reviewed By: xcheng16
Differential Revision: D22199952
fbshipit-source-id: df13eef39c01738637ae8cf7f581d6ccc88d37d5
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/37243
*** Why ***
As it stands, we have two thread pool solutions concurrently in use in PyTorch mobile: (1) the open source pthreadpool library under third_party, and (2) Caffe2's implementation of pthreadpool under caffe2/utils/threadpool. Since the primary use-case of the latter has been to act as a drop-in replacement for the third party version so as to enable integration and usage from within NNPACK and QNNPACK, Caffe2's implementation is intentionally written to the exact same interface as the third party version.
The original argument in favor of C2's implementation has been improved performance as a result of using spin locks, as opposed to relinquishing the thread's time slot and putting it to sleep - a less expensive operation up to a point. That seems to have given C2's implementation the upper hand in performance, hence justifying the added maintenance complexity, until the third party version improved in parallel surpassing the efficiency of C2's implementation as I have verified in benchmarks. With that advantage gone, there is no reason to continue using C2's implementation in PyTorch mobile either from the perspective of performance or code hygiene. As a matter of fact, there is considerable performance benefit to be had as a result of using the third party version as it currently stands.
This is a tricky change though, mainly because in order to avoid potential performance regressions, of which I have witnessed none but just in abundance of caution, we have decided to continue using the internal C2's implementation whenever building for Caffe2. Again, this is mainly to avoid potential performance regressions in production C2 use cases even if doing so results in reduced performance as far as I can tell.
So to summarize, today, and as it currently stands, we are using C2's implementation for (1) NNPACK, (2) PyTorch QNNPACK, and (3) ATen parallel_for on mobile builds, while using the third party version of pthreadpool for XNNPACK as XNNPACK does not provide any build options to link against an external implementation unlike NNPACK and QNNPACK do.
The goal of this PR then, is to unify all usage on mobile to the third party implementation both for improved performance and better code hygiene. This applies to PyTorch's use of NNPACK, QNNPACK, XNNPACK, and mobile's implementation of ATen parallel_for, all getting routed to the
exact same third party implementation in this PR.
Considering that NNPACK, QNNPACK, and XNNPACK are not mobile specific, these benefits carry over to non-mobile builds of PyTorch (but not Caffe2) as well. The implementation of ATen parallel_for on non-mobile builds remains unchanged.
*** How ***
This is where things get tricky.
A good deal of the build system complexity in this PR arises from our desire to maintain C2's implementation intact for C2's use.
pthreadpool is a C library with no concept of namespaces, which means two copies of the library cannot exist in the same binary or symbol collision will occur violating ODR. This means that somehow, and based on some condition, we must decide on the choice of a pthreadpool implementation. In practice, this has become more complicated as a result of all the possible combinations that USE_NNPACK, USE_QNNPACK, USE_PYTORCH_QNNPACK, USE_XNNPACK, USE_SYSTEM_XNNPACK, USE_SYSTEM_PTHREADPOOL and other variables can result in. Having said that, I have done my best in this PR to surgically cut through this complexity in a way that minimizes the side effects, considering the significance of the performance we are leaving on the table, yet, as a result of this combinatorial explosion explained above I cannot guarantee that every single combination will work as expected on the first try. I am heavily relying on CI to find any issues as local testing can only go that far.
Having said that, this PR provides a simple non mobile-specific C++ thread pool implementation on top of pthreadpool, namely caffe2::PThreadPool that automatically routes to C2's implementation or the third party version depending on the build configuration. This simplifies the logic at the cost of pushing the complexity to the build scripts. From there on, this thread pool is used in aten parallel_for, and NNPACK and family, again, routing all usage of threading to C2 or third party pthreadpool depending on the build configuration.
When it is all said or done, the layering will look like this:
a) aten::parallel_for, uses
b) caffe2::PThreadPool, which uses
c) pthreadpool C API, which delegates to
c-1) third_party implementation of pthreadpool if that's what the build has requested, and the rabbit hole ends here.
c-2) C2's implementation of pthreadpool if that's what the build has requested, which itself delegates to
c-2-1) caffe2::ThreadPool, and the rabbit hole ends here.
NNPACK, and (PyTorch) QNNPACK directly hook into (c). They never go through (b).
Differential Revision: D21232894
Test Plan: Imported from OSS
Reviewed By: dreiss
Pulled By: AshkanAliabadi
fbshipit-source-id: 8b3de86247fbc3a327e811983e082f9d40081354
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/39587
Example of using direct linking to pytorch_jni library from aar and updating android/README.md with the tutorial how to do it.
Adding `nativeBuild` dimension to `test_app`, using direct aar dependencies, as headers packaging is not landed yet, excluding `nativeBuild` from building by default for CI.
Additional change to `scripts/build_pytorch_android.sh`:
Skipping clean task here as android gradle plugin 3.3.2 exteralNativeBuild has problems with it when abiFilters are specified.
Will be returned back in the following diffs with upgrading of gradle and android gradle plugin versions.
Test Plan: Imported from OSS
Differential Revision: D22118945
Pulled By: IvanKobzarev
fbshipit-source-id: 31c54b49b1f262cbe5f540461d3406f74851db6c
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/39588
Before this diff we used c++_static linking.
Users will dynamically link to libpytorch_jni.so and have at least one more their own shared library that probably uses stl library.
We must have not more than one stl per app. ( https://developer.android.com/ndk/guides/cpp-support#one_stl_per_app )
To have only one stl per app changing ANDROID_STL way to c++_shared, that will add libc++_shared.so to packaging.
Test Plan: Imported from OSS
Differential Revision: D22118031
Pulled By: IvanKobzarev
fbshipit-source-id: ea1e5085ae207a2f42d1fa9f6ab8ed0a21768e96
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/39868
### Summary
why disable NNPACK on iOS
- To stay consistency with our internal version
- It's currently blocking some external users due to its lack support of x86 architecture
- https://github.com/pytorch/pytorch/issues/32040
- https://discuss.pytorch.org/t/undefined-symbols-for-architecture-x86-64-for-libtorch-in-swift-unit-test/84552/6
- NNPACK uses fast convolution algorithms (FFT, winograd) to reduce the computational complexity of convolutions with large kernel size. The algorithmic speedup is limited to specific conv params which are unlikely to appear in mobile networks.
- Since XNNPACK has been enabled, it performs much better than NNPACK on depthwise-separable convolutions which is the algorithm being used by most of mobile computer vision networks.
### Test Plan
- CI Checks
Test Plan: Imported from OSS
Differential Revision: D22087365
Pulled By: xta0
fbshipit-source-id: 89a959b0736c1f8703eff10723a8fbd02357fd4a
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/39999
Cleaned up the android build scripts. Consolidated common functions into
common.sh. Also made a few minor fixes:
- We should trust build_android.sh doing right about reusing existing
`build_android_$abi` directory;
- We should clean up `pytorch_android/src/main/jniLibs/` to remove
broken symbolic links in case custom abi list changes since last build;
Test Plan: Imported from OSS
Differential Revision: D22036926
Pulled By: ljk53
fbshipit-source-id: e93915ee4f195111b6171cdabc667fa0135d5195
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/39188
Extracting Vulkan_LIBS and Vulkan_INCLUDES setup from `cmake/Dependencies.cmake` to `cmake/VulkanDependencies.cmake` and reuse it in android/pytorch_android/CMakeLists.txt
Adding control to build with Vulkan setting env variable `USE_VULKAN` for `scripts/build_android.sh` `scripts/build_pytorch_android.sh`
We do not use Vulkan backend in pytorch_android, but with this build option we can track android aar change with `USE_VULKAN` added.
Currently it is 88Kb.
Test Plan: Imported from OSS
Differential Revision: D21770892
Pulled By: IvanKobzarev
fbshipit-source-id: a39433505fdcf43d3b524e0fe08062d5ebe0d872
Summary:
* Does a basic upload of release candidates to an extra folder within our
S3 bucket.
* Refactors AWS promotion to allow for easier development of restoration
of backups
Backup restoration usage:
```
RESTORE_FROM=v1.6.0-rc3 restore-backup.sh
```
Requires:
* AWS credentials to upload / download stuff
* Anaconda credentials to upload
Pull Request resolved: https://github.com/pytorch/pytorch/pull/38690
Differential Revision: D21691033
Pulled By: seemethere
fbshipit-source-id: 31118814db1ca701c55a3cb0bc32caa1e77a833d
Summary:
Files that were named the same within the anaconda repository, i.e.
pytorch_1.5.0-cpu.bz2, were found to be clobbering each other,
especially amongst different platforms.
This lead to similarly named packages for different platforms to not get
promoted.
This also adds "--skip" to our anaconda upload so that we don't end up
overwriting our releases just in case this script gets run twice.
Also, conda search ends up erroring out if it doesn't find anything for
the current platform being searched for so we should just continue
forward if we don't find anything since we want to be able to use this
script for all of the packages we support which also do not release
packages for all of the same platforms. (torchtext for example only has
"noarch")
This should also probably be back-ported to the `release/1.5` branch since this changeset was used to release `v1.5.0`
Signed-off-by: Eli Uriegas <eliuriegas@fb.com>
Pull Request resolved: https://github.com/pytorch/pytorch/pull/37089
Differential Revision: D21184768
Pulled By: seemethere
fbshipit-source-id: dbe12d74df593b57405b178ddb2375691e128a49
Summary:
Adds a new promotion pipeline for both our wheel packages hosted on S3
as well as our conda packages hosted on anaconda.
Promotion is only run on tags that that match the following regex:
/v[0-9]+(\.[0-9]+)*/
Example:
v1.5.0
The promotion pipeline is also only run after a manual approval from
someone within the CircleCI security context "org-member"
> NOTE: This promotion pipeline does not cover promotion of packages that
> are published to PyPI, this is an intentional choice as those
> packages cannot be reverted after they have been published.
TODO: Write a proper testing pipeline for this
Signed-off-by: Eli Uriegas <eliuriegas@fb.com>
Pull Request resolved: https://github.com/pytorch/pytorch/pull/34993
Differential Revision: D20539497
Pulled By: seemethere
fbshipit-source-id: 104772d3c3898d77a24ef9bf25f7dbd2496613df
Summary:
How this actually works:
1. Get's a list of URLs from anaconda for pkgs to download, most
likely from pytorch-test
2. Download all of those packages locally in a temp directory
3. Upload all of those packages, with a dry run upload by default
This, along with https://github.com/pytorch/pytorch/issues/34500 basically completes the scripting work for the eventual promotion pipeline.
Currently testing with:
```
TEST_WITHOUT_GIT_TAG=1 TEST_PYTORCH_PROMOTE_VERSION=1.4.0 PYTORCH_CONDA_FROM=pytorch scripts/release/promote/conda_to_conda.sh
```
Signed-off-by: Eli Uriegas <eliuriegas@fb.com>
Pull Request resolved: https://github.com/pytorch/pytorch/pull/34659
Differential Revision: D20432687
Pulled By: seemethere
fbshipit-source-id: c2a99f6cbc6a7448e83e666cde11d6875aeb878e
Summary:
Is reliant on scripts for promotion from s3 to s3 to have already run.
A continuation of the work done in https://github.com/pytorch/pytorch/issues/34274
Signed-off-by: Eli Uriegas <eliuriegas@fb.com>
Pull Request resolved: https://github.com/pytorch/pytorch/pull/34500
Test Plan: yeah_sandcastle
Differential Revision: D20389101
Pulled By: seemethere
fbshipit-source-id: 5e5b554cff964630c5414d48be35f14ba6894021
Summary:
**Summary**
This commit adds `tools/clang_format_new.py`, which downloads a platform-appropriate
clang-format binary to a `.gitignored` location, verifies the binary by comparing its
SHA1 hash to a reference hash (also included in this commit), and runs it on all files
matched a specific regex in a list of whitelisted subdirectories of pytorch.
This script will eventually replace `tools/clang_format.py`.
**Testing**
Ran the script.
*No Args*
```
pytorch > ./tools/clang_format.py
Downloading clang-format to /Users/<user>/Desktop/pytorch/.clang-format-bin
0% |################################################################| 100%
Using clang-format located at /Users/<user>/Desktop/pytorch/.clang-format-bin/clang-format
> echo $?
0
> git status
<bunch of files>
```
`--diff` *mode*
```
> ./tools/clang_format.py --diff
Using clang-format located at /Users/<user>/Desktop/pytorch/.clang-format-bin/clang-format
Some files are not formatted correctly
> echo $?
1
<format files using the script>
> ./tools/clang_format.py --diff
Using clang-format located at /Users/<user>/Desktop/pytorch/.clang-format-bin/clang-format
All files are formatted correctly
> echo $?
0
```
Pull Request resolved: https://github.com/pytorch/pytorch/pull/34566
Differential Revision: D20431290
Pulled By: SplitInfinity
fbshipit-source-id: 3966f769cfb923e58ead9376d85e97127415bdc6
Summary:
If SELECTED_OP_LIST is specified as a relative path in command line, CMake build will fail.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/33942
Differential Revision: D20392797
Pulled By: ljk53
fbshipit-source-id: dffeebc48050970e286cf263bdde8b26d8fe4bce
Summary:
When a system has ROCm dev tools installed, `scripts/build_mobile.sh` tried to use it.
This PR fixes looking up unused ROCm library when building libtorch mobile.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/34478
Differential Revision: D20388147
Pulled By: ljk53
fbshipit-source-id: b512c38fa2d3cda9ac20fe47bcd67ad87c848857
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/34410
### Summary
Currently, the iOS jobs are not being run on PRs anymore. This is because all iOS jobs have specified the `org-member` as a context which used to include all pytorch members. But seems like recently this rule has changed. It turns out that only users from the admin group or builder group can have access right to the context values. https://circleci.com/gh/organizations/pytorch/settings#contexts/2b885fc9-ef3a-4b86-8f5a-2e6e22bd0cfe
This PR will remove `org-member` from the iOS simulator build which doesn't require code signing. For the arm64 builds, they'll only be run on master, not on PRs anymore.
### Test plan
- The iOS simulator job should be able to appear in the PR workflow
Test Plan: Imported from OSS
Differential Revision: D20347270
Pulled By: xta0
fbshipit-source-id: 23f37d40160c237dc280e0e82f879c1d601f72ac
Summary:
Currently testing against the older release `1.4.0` with:
```
PYTORCH_S3_FROM=nightly TEST_WITHOUT_GIT_TAG=1 TEST_PYTORCH_PROMOTE_VERSION=1.4.0 scripts/release/promote/libtorch_to_s3.sh
PYTORCH_S3_FROM=nightly TEST_WITHOUT_GIT_TAG=1 TEST_PYTORCH_PROMOTE_VERSION=1.4.0 scripts/release/promote/wheel_to_s3.sh
```
These scripts can also be used for `torchvision` as well which may make the release process better there as well.
Later on this should be made into a re-usable module that can be downloaded from anywhere and used amongst all pytorch repositories.
Signed-off-by: Eli Uriegas <eliuriegas@fb.com>
Pull Request resolved: https://github.com/pytorch/pytorch/pull/34274
Test Plan: sandcastle_will_deliver
Differential Revision: D20294419
Pulled By: seemethere
fbshipit-source-id: c8c31b5c42af5096f09275166ac43d45a459d25c
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/34203
Currently cmake and mobile build scripts still build libcaffe2 by
default. To build pytorch mobile users have to set environment variable
BUILD_PYTORCH_MOBILE=1 or set cmake option BUILD_CAFFE2_MOBILE=OFF.
PyTorch mobile has been released for a while. It's about time to change
CMake and build scripts to build libtorch by default.
Changed caffe2 CI job to build libcaffe2 by setting BUILD_CAFFE2_MOBILE=1
environment variable. Only found android CI for libcaffe2 - do we ever
have iOS CI for libcaffe2?
Test Plan: Imported from OSS
Differential Revision: D20267274
Pulled By: ljk53
fbshipit-source-id: 9d997032a599c874d62fbcfc4f5d4fbf8323a12e
Summary:
Among all ONNX tests, ONNXRuntime tests are taking the most time on CI (almost 60%).
This is because we are testing larger models (mainly torchvision RCNNs) for multiple onnx opsets.
I decided to divide tests between two jobs for older/newer opsets. This is now reducing the test time from 2h to around 1h10mins.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/33242
Reviewed By: hl475
Differential Revision: D19866498
Pulled By: houseroad
fbshipit-source-id: 446c1fe659e85f5aef30efc5c4549144fcb5778c
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/34187
Noticed that a recent PR broke Android/iOS CI but didn't break mobile
build with host toolchain. Turns out one mobile related flag was not
set on PYTORCH_BUILD_MOBILE code path:
```
"set(INTERN_DISABLE_MOBILE_INTERP ON)"
```
First, move the INTERN_DISABLE_MOBILE_INTERP macro below, to stay with
other "mobile + pytorch" options - it's not relevant to "mobile + caffe2"
so doesn't need to be set as common "mobile" option;
Second, rename PYTORCH_BUILD_MOBILE env-variable to
BUILD_PYTORCH_MOBILE_WITH_HOST_TOOLCHAIN - it's a bit verbose but
becomes more clear what it does - there is another env-variable
"BUILD_PYTORCH_MOBILE" used in scripts/build_android.sh, build_ios.sh,
which toggles between "mobile + pytorch" v.s. "mobile + caffe2";
Third, combine BUILD_PYTORCH_MOBILE_WITH_HOST_TOOLCHAIN with ANDROID/IOS
to avoid missing common mobile options again in future.
Test Plan: Imported from OSS
Differential Revision: D20251864
Pulled By: ljk53
fbshipit-source-id: dc90cc87ffd4d0bf8a78ae960c4ce33a8bb9e912
Summary:
**Summary**
This commit adds a script that fetches a platform-appropriate `clang-format` binary
from S3 for use during PyTorch development. The goal is for everyone to use the exact
same `clang-format` binary so that there are no formatting conflicts.
**Testing**
Ran the script.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/33644
Differential Revision: D20076598
Pulled By: SplitInfinity
fbshipit-source-id: cd837076fd30e9c7a8280665c0d652a33b559047
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/33722
In order to improve CPU performance on floating-point models on mobile, this PR introduces a new CPU backend for mobile that implements the most common mobile operators with NHWC memory layout support through integration with XNNPACK.
XNNPACK itself, and this codepath, are currently only included in the build, but the actual integration is gated with USE_XNNPACK preprocessor guards. This preprocessor symbol is intentionally not passed on to the compiler, so as to enable this rollout in multiple stages in follow up PRs. This changeset will build XNNPACK as part of the build if the identically named USE_XNNPACK CMAKE variable, defaulted to ON, is enabled, but will not actually expose or enable this code path in any other way.
Furthermore, it is worth pointing out that in order to efficiently map models to these operators, some front-end method of exposing this backend to the user is needed. The less efficient implementation would be to hook these operators into their corresponding native implementations, granted that a series of XNNPACK-specific conditions are met, much like how NNPACK is integrated with PyTorch today for instance.
Having said that, while the above implementation is still expected to outperform NNPACK based on the benchmarks I ran, the above integration would be leave a considerable gap between the performance achieved and the maximum performance potential XNNPACK enables, as it does not provide a way to compute and factor out one-time operations out of the inner most forward() loop.
The more optimal solution, and one we will decide on soon, would involve either providing a JIT pass that maps nn operators onto these newly introduced operators, while allowing one-time calculations to be factored out, much like quantized mobile models. Alternatively, new eager-mode modules can also be introduced that would directly call into these implementations either through c10 or some other mechanism, also allowing for decoupling of op creation from op execution.
This PR does not include any of the front end changes mentioned above. Neither does it include the mobile threadpool unification present in the original https://github.com/pytorch/pytorch/issues/30644. Furthermore, this codepath seems to be faster than NNPACK in a good number of use cases, which can potentially allow us to remove NNPACK from aten to make the codebase a little simpler, granted that there is widespread support for such a move.
Regardless, these changes will be introduced gradually and in a more controlled way in subsequent PRs.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/32509
Test Plan:
Build: CI
Functionality: Not exposed
Reviewed By: dreiss
Differential Revision: D20069796
Pulled By: AshkanAliabadi
fbshipit-source-id: d46c1c91d4bea91979ea5bd46971ced5417d309c
Summary:
In order to improve CPU performance on floating-point models on mobile, this PR introduces a new CPU backend for mobile that implements the most common mobile operators with NHWC memory layout support through integration with XNNPACK.
XNNPACK itself, and this codepath, are currently only included in the build, but the actual integration is gated with USE_XNNPACK preprocessor guards. This preprocessor symbol is intentionally not passed on to the compiler, so as to enable this rollout in multiple stages in follow up PRs. This changeset will build XNNPACK as part of the build if the identically named USE_XNNPACK CMAKE variable, defaulted to ON, is enabled, but will not actually expose or enable this code path in any other way.
Furthermore, it is worth pointing out that in order to efficiently map models to these operators, some front-end method of exposing this backend to the user is needed. The less efficient implementation would be to hook these operators into their corresponding **native** implementations, granted that a series of XNNPACK-specific conditions are met, much like how NNPACK is integrated with PyTorch today for instance.
Having said that, while the above implementation is still expected to outperform NNPACK based on the benchmarks I ran, the above integration would be leave a considerable gap between the performance achieved and the maximum performance potential XNNPACK enables, as it does not provide a way to compute and factor out one-time operations out of the inner most forward() loop.
The more optimal solution, and one we will decide on soon, would involve either providing a JIT pass that maps nn operators onto these newly introduced operators, while allowing one-time calculations to be factored out, much like quantized mobile models. Alternatively, new eager-mode modules can also be introduced that would directly call into these implementations either through c10 or some other mechanism, also allowing for decoupling of op creation from op execution.
This PR does not include any of the front end changes mentioned above. Neither does it include the mobile threadpool unification present in the original https://github.com/pytorch/pytorch/issues/30644. Furthermore, this codepath seems to be faster than NNPACK in a good number of use cases, which can potentially allow us to remove NNPACK from aten to make the codebase a little simpler, granted that there is widespread support for such a move.
Regardless, these changes will be introduced gradually and in a more controlled way in subsequent PRs.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/32509
Reviewed By: dreiss
Differential Revision: D19521853
Pulled By: AshkanAliabadi
fbshipit-source-id: 99a1fab31d0ece64961df074003bb852c36acaaa
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/33318
### Summary
Recently, we have a [discussion](https://discuss.pytorch.org/t/libtorch-on-watchos/69073/14) in the forum about watchOS. This PR adds the support for building watchOS libraries.
### Test Plan
- `BUILD_PYTORCH_MOBILE=1 IOS_PLATFORM=WATCHOS ./scripts/build_ios.sh`
Test Plan: Imported from OSS
Differential Revision: D19896534
Pulled By: xta0
fbshipit-source-id: 7b9286475e895d9fefd998246e7090ac92c4c9b6
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/30315
The new structure is that libtorch_cpu contains the bulk of our
code, and libtorch depends on libtorch_cpu and libtorch_cuda.
This is a reland of https://github.com/pytorch/pytorch/pull/29731 but
I've extracted all of the prep work into separate PRs which can be
landed before this one.
Some things of note:
* torch/csrc/cuda/nccl.cpp was added to the wrong list of SRCS, now fixed (this didn't matter before because previously they were all in the same library)
* The dummy file for libtorch was brought back from the dead; it was previously deleted in #20774
In an initial version of the patch, I forgot to make torch_cuda explicitly depend on torch_cpu. This lead to some very odd errors, most notably "bin/blob_test: hidden symbol `_ZNK6google8protobuf5Arena17OnArenaAllocationEPKSt9type_infom' in lib/libprotobuf.a(arena.cc.o) is referenced by DSO"
* A number of places in Android/iOS builds have to add torch_cuda explicitly as a library, as they do not have transitive dependency calculation working correctly
* I had to torch_cpu/torch_cuda caffe2_interface_library so that they get whole-archived linked into torch when you statically link. And I had to do this in an *exported* fashion because torch needs to depend on torch_cpu_library. In the end I exported everything and removed the redefinition in the Caffe2Config.cmake. However, I am not too sure why the old code did it in this way in the first place; however, it doesn't seem to have broken anything to switch it this way.
* There's some uses of `__HIP_PLATFORM_HCC__` still in `torch_cpu` code, so I had to apply it to that library too (UGH). This manifests as a failer when trying to run the CUDA fuser. This doesn't really matter substantively right now because we still in-place HIPify, but it would be good to fix eventually. This was a bit difficult to debug because of an unrelated HIP bug, see https://github.com/ROCm-Developer-Tools/HIP/issues/1706Fixes#27215 (as our libraries are smaller), and executes on
part of the plan in #29235.
Signed-off-by: Edward Z. Yang <ezyang@fb.com>
Test Plan: Imported from OSS
Differential Revision: D18790941
Pulled By: ezyang
fbshipit-source-id: 01296f6089d3de5e8365251b490c51e694f2d6c7
Summary:
Move the shell script into this separate PR to make the original PR
smaller and less scary.
Test Plan:
- With stacked PRs:
1. analyze test project and compare with expected results:
```
ANALYZE_TEST=1 CHECK_RESULT=1 tools/code_analyzer/build.sh
```
2. analyze LibTorch:
```
ANALYZE_TORCH=1 tools/code_analyzer/build.sh
```
Differential Revision: D18474749
Pulled By: ljk53
fbshipit-source-id: 55c5cae3636cf2b1c4928fd2dc615d01f287076a
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/29731
The new structure is that libtorch_cpu contains the bulk of our
code, and libtorch depends on libtorch_cpu and libtorch_cuda.
Some subtleties about the patch:
- There were a few functions that crossed CPU-CUDA boundary without API macros. I just added them, easy enough. An inverse situation was aten/src/THC/THCTensorRandom.cu where we weren't supposed to put API macros directly in a cpp file.
- DispatchStub wasn't getting all of its symbols related to static members on DispatchStub exported properly. I tried a few fixes but in the end I just moved everyone off using DispatchStub to dispatch CUDA/HIP (so they just use normal dispatch for those cases.) Additionally, there were some mistakes where people incorrectly were failing to actually import the declaration of the dispatch stub, so added includes for those cases.
- torch/csrc/cuda/nccl.cpp was added to the wrong list of SRCS, now fixed (this didn't matter before because previously they were all in the same library)
- The dummy file for libtorch was brought back from the dead; it was previously deleted in #20774
- In an initial version of the patch, I forgot to make torch_cuda explicitly depend on torch_cpu. This lead to some very odd errors, most notably "bin/blob_test: hidden symbol `_ZNK6google8protobuf5Arena17OnArenaAllocationEPKSt9type_infom' in lib/l
ibprotobuf.a(arena.cc.o) is referenced by DSO"
- A number of places in Android/iOS builds have to add torch_cuda explicitly as a library, as they do not have transitive dependency calculation working correctly. This situation also happens with custom C++ extensions.
- There's a ROCm compiler bug where extern "C" on functions is not respected. There's a little workaround to handle this.
- Because I was too lazy to check if HIPify was converting TORCH_CUDA_API into TORCH_HIP_API, I just made it so HIP build also triggers the TORCH_CUDA_API macro. Eventually, we should translate and keep the nature of TORCH_CUDA_API constant in all cases.
Fixes#27215 (as our libraries are smaller), and executes on
part of the plan in #29235.
Signed-off-by: Edward Z. Yang <ezyang@fb.com>
Test Plan: Imported from OSS
Differential Revision: D18632773
Pulled By: ezyang
fbshipit-source-id: ea717c81e0d7554ede1dc404108603455a81da82
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/30144
Create script to produce libtorch that only contains ops needed by specific
models. Developers can use this workflow to further optimize mobile build size.
Need keep a dummy stub for unused (stripped) ops because some JIT side
logic requires certain function schemas to be existed in the JIT op
registry.
Test Steps:
1. Build "dump_operator_names" binary and use it to dump root ops needed
by a specific model:
```
build/bin/dump_operator_names --model=mobilenetv2.pk --output=mobilenetv2.yaml
```
2. The MobileNetV2 model should use the following ops:
```
- aten::t
- aten::dropout
- aten::mean.dim
- aten::add.Tensor
- prim::ListConstruct
- aten::addmm
- aten::_convolution
- aten::batch_norm
- aten::hardtanh_
- aten::mm
```
NOTE that for some reason it outputs "aten::addmm" but actually uses "aten::mm".
You need fix it manually for now.
3. Run custom build script locally (use Android as an example):
```
SELECTED_OP_LIST=mobilenetv2.yaml scripts/build_pytorch_android.sh armeabi-v7a
```
4. Checkout demo app that uses locally built library instead of
downloading from jcenter repo:
```
git clone --single-branch --branch custom_build git@github.com:ljk53/android-demo-app.git
```
5. Copy locally built libraries to demo app folder:
```
find ${HOME}/src/pytorch/android -name '*.aar' -exec cp {} ${HOME}/src/android-demo-app/HelloWorldApp/app/libs/ \;
```
6. Build demo app with locally built libtorch:
```
cd ${HOME}/src/android-demo-app/HelloWorldApp
./gradlew clean && ./gradlew assembleDebug
```
7. Install and run the demo app.
In-APK arm-v7 libpytorch_jni.so build size reduced from 5.5M to 2.9M.
Test Plan: Imported from OSS
Differential Revision: D18612127
Pulled By: ljk53
fbshipit-source-id: fa8d5e1d3259143c7346abd1c862773be8c7e29a
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/29715
Previous we hard code it to enable static dispatch when building mobile
library. Since we are exploring approaches to deprecate static dispatch
we should make it optional. This PR moved the setting from cmake to bash
build scripts which can be overridden.
Test Plan: - verified it's still using static dispatch when building with these scripts.
Differential Revision: D18474640
Pulled By: ljk53
fbshipit-source-id: 7591acc22009bfba36302e3b2a330b1428d8e3f1
Summary:
Reason:
To have one-step build for test android application based on the current code state that is ready for profiling with simpleperf, systrace etc. to profile performance inside the application.
## Parameters to control debug symbols stripping
Introducing /CMakeLists parameter `ANDROID_DEBUG_SYMBOLS` to be able not to strip symbols for pytorch (not add linker flag `-s`)
which is checked in `scripts/build_android.sh`
On gradle side stripping happens by default, and to prevent it we have to specify
```
android {
packagingOptions {
doNotStrip "**/*.so"
}
}
```
which is now controlled by new gradle property `nativeLibsDoNotStrip `
## Test_App
`android/test_app` - android app with one MainActivity that does inference in cycle
`android/build_test_app.sh` - script to build libtorch with debug symbols for specified android abis and adds `NDK_DEBUG=1` and `-PnativeLibsDoNotStrip=true` to keep all debug symbols for profiling.
Script assembles all debug flavors:
```
└─ $ find . -type f -name *apk
./test_app/app/build/outputs/apk/mobilenetQuant/debug/test_app-mobilenetQuant-debug.apk
./test_app/app/build/outputs/apk/resnet/debug/test_app-resnet-debug.apk
```
## Different build configurations
Module for inference can be set in `android/test_app/app/build.gradle` as a BuildConfig parameters:
```
productFlavors {
mobilenetQuant {
dimension "model"
applicationIdSuffix ".mobilenetQuant"
buildConfigField ("String", "MODULE_ASSET_NAME", buildConfigProps('MODULE_ASSET_NAME_MOBILENET_QUANT'))
addManifestPlaceholders([APP_NAME: "PyMobileNetQuant"])
buildConfigField ("String", "LOGCAT_TAG", "\"pytorch-mobilenet\"")
}
resnet {
dimension "model"
applicationIdSuffix ".resnet"
buildConfigField ("String", "MODULE_ASSET_NAME", buildConfigProps('MODULE_ASSET_NAME_RESNET18'))
addManifestPlaceholders([APP_NAME: "PyResnet"])
buildConfigField ("String", "LOGCAT_TAG", "\"pytorch-resnet\"")
}
```
In that case we can setup several apps on the same device for comparison, to separate packages `applicationIdSuffix`: 'org.pytorch.testapp.mobilenetQuant' and different application names and logcat tags as `manifestPlaceholder` and another BuildConfig parameter:
```
─ $ adb shell pm list packages | grep pytorch
package:org.pytorch.testapp.mobilenetQuant
package:org.pytorch.testapp.resnet
```
In future we can add another BuildConfig params e.g. single/multi threads and other configuration for profiling.
At the moment 2 flavors - for resnet18 and for mobilenetQuantized
which can be installed on connected device:
```
cd android
```
```
gradle test_app:installMobilenetQuantDebug
```
```
gradle test_app:installResnetDebug
```
## Testing:
```
cd android
sh build_test_app.sh
adb install -r test_app/app/build/outputs/apk/mobilenetQuant/debug/test_app-mobilenetQuant-debug.apk
```
```
cd $ANDROID_NDK
python simpleperf/run_simpleperf_on_device.py record --app org.pytorch.testapp.mobilenetQuant -g --duration 10 -o /data/local/tmp/perf.data
adb pull /data/local/tmp/perf.data
python simpleperf/report_html.py
```
Simpleperf report has all symbols:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/28406
Differential Revision: D18386622
Pulled By: IvanKobzarev
fbshipit-source-id: 3a751192bbc4bc3c6d7f126b0b55086b4d586e7a
