Summary:
- HIP_VERSION semantic versioning will change in ROCm4.3. The changes essentially remove the dependency on HIP_VERSION provided in the hip header to keep code compatible with older and newer versions of ROCm.
- TORCH_HIP_VERSION is derived from HIP_VERSION_MAJOR and HIP_VERSION_MINOR
Pull Request resolved: https://github.com/pytorch/pytorch/pull/62786
Reviewed By: bdhirsh
Differential Revision: D30281682
Pulled By: seemethere
fbshipit-source-id: e41e69fb9e13de5ddd1af99ba5bbdcbb7b64b673
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:
This PR contains the following updates:
1. MIOpen 3D pooling enabled in Caffe2.
2. Refactored the MIOpen pooling code in caffe2.
3. Enabled unit test cases for 3D pooling.
CC: ezyang jeffdaily ashishfarmer
Pull Request resolved: https://github.com/pytorch/pytorch/pull/38260
Differential Revision: D21524754
Pulled By: xw285cornell
fbshipit-source-id: ddfe09dc585cd61e42eee22eff8348d326fd0c3b
Summary:
This directory is opted-in to clang-format but is not format-clean. This blocks continuous formatting from being enabled on fbcode, and causes hassle for other codemods that leave inconsistent formatting. This diff runs clang-format, which is widely used and considered safe.
If you are unhappy with the formatting of a particular block, please *accept this diff* and then in a stacked commit undo the change and wrap that code in `// clang-format off` and `// clang-format on`, or `/* clang-format off */` and `/* clang-format on */`.
drop-conflicts
Test Plan: sandcastleit
Reviewed By: jerryzh168
Differential Revision: D22311706
fbshipit-source-id: 1ca59a82e96156a4a5dfad70ba3e64d44c5e762a
Summary:
For both the Caffe2 and PyTorch backends, enable 3D convolutions through MIOpen.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/33067
Reviewed By: BIT-silence
Differential Revision: D19880495
Pulled By: bddppq
fbshipit-source-id: 8f6f970910654c1c5aa871b48a04c1054875691c
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/17764
Original commit changeset: f1923fdca4a1
reverted int8 ops fixes the original runtime regression.
We'll ignore the memory regression since it is flaky, see D14228484
Reviewed By: dzhulgakov
Differential Revision: D13885233
fbshipit-source-id: ccbe4b94acb44b7b4cb3ae4d73e3f6091e1e1195
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/16273
Previously we have SetOutputSize which accept a partially initialized Output Tensor and set it to the correct size,
the diff change this to GetOutputSize that returns the correct size instead.
e.g.
```
auto* Y = Output(0);
ConvPoolOp<Context>::SetOutputSize(X, Y, channels);
...
Y->mutable_data<T>...
```
-->
```
auto sizes = ConvPoolOp<Context>::GetOutputSize(X, channels);
auto* Y = Output(0, sizes, at::dtype<T>());
```
Reviewed By: dzhulgakov
Differential Revision: D13736281
fbshipit-source-id: 64abce3dbaed0b375098463333dfd0ea5a3b1945
Summary:
This PR contains changes for:
1. Using memory alloc from HIPContext while allocating workspace for MIOpen conv and transpose_conv operators rather than direct HIP mem alloc
2. Minor cleanup and removing an unnecessary sync call from MIOpen conv op
Differential Revision: D13598894
Pulled By: bddppq
fbshipit-source-id: 44886161abdf91cd29c7c93b3e23620e1b09c7c9
Summary:
xw285cornell
- To make hip files to have unique filename extension we change hip files from _hip.cc to .hip (it's the only blessing option other than .cu in hipcc 3d51a1fb01/bin/hipcc (L552)).
- Change to use host compiler to compile .cc|.cpp files. Previously we use hcc to compile them which is unnecessary
- Change the hipify script to not replace "gpu" with "hip" in the filename of the generated hipified files. Previously we do this because hcc has a bug when linking files that have same filename. We have now changed to use host linker to do linking so this is unnecessary anymore.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/14036
Reviewed By: xw285cornell
Differential Revision: D13091813
Pulled By: bddppq
fbshipit-source-id: ea3d887751d8abb39d75f5d5104aa66ce66b9ee0
Summary:
xw285cornell
Unfortunately it's not easy to add -Werror=reorder flag since there are out of order initializations in thrust headers as well, and the rocm cmake macro hip_include_directories doesn't offer a way to include headers as external headers.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/14015
Reviewed By: soumith
Differential Revision: D13081104
Pulled By: bddppq
fbshipit-source-id: 2540421cb29cf556c79f2d86c460bde6ea5a182e
Summary:
This pull request contains changes for:
1. Removing ConvTranspose related changes from caffe2/operators/hip/conv_op_miopen.cc
2. Adding the file caffe2/operators/hip/conv_transpose_op_miopen.cc
3. Modifying the tests to run convTranspose op using MIOpen engine
Differential Revision: D13055099
Pulled By: bddppq
fbshipit-source-id: ca284f8f9a073005b22013c375cc958257815865
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/13264
Simply change the initialization order to make hcc happy. Otherwise will have to add -Wno-error=reorder.
Reviewed By: bddppq
Differential Revision: D12827635
fbshipit-source-id: 6f4cd67209f2aa8ae85cfbdc53df0efb3b3cc473
Summary:
This pull request contains changes for:
1. Adding a generalized MIOpen activation class to be used by activation operators
2. Refactoring MIOpen ReLU op to use the new class
3. Adding ELU, Tanh and Sigmoid MIOpen ops
Differential Revision: D12810112
Pulled By: bddppq
fbshipit-source-id: 9519b3a0cd733b906bcba5d8948be089029c43ac
Summary:
This is mostly for reusing all the cudnn test cases in our python operator_tests.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/12278
Differential Revision: D10842592
Pulled By: bddppq
fbshipit-source-id: 4b3ed91fca64ff02060837b3270393bc2f9a9898
Summary:
This PR contains changes for:
1. Removing MIOpen softmax operator. Will be added later with the required functionality
2. Enabling softmax_ops_test on ROCm target
Differential Revision: D10416079
Pulled By: bddppq
fbshipit-source-id: 288099903aa9e0c3378e068fffe6e7d6a9a84841
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/12180
I had to fix a lot of call sites, because a lot of places assume that
you can actually get a const vector&, and if the internal representation
of sizes in a tensor is NOT a vector, it's not possible to fulfill
this API contract.
Framework changes:
- I deleted TensorImpl::dims(); caffe2::Tensor::dims() just forwards to
sizes() now.
- De-templatized SetDims; now it is an explicit list of ArrayRef and
variadic overloads. This makes implicit conversions work again,
so I don't need to explicitly list the std::vector cases too.
- As a knock-on effect, this causes Reset() to accept at::IntList as well as
const std::vector<int64_t>&
- Edited variadic overloads of SetDims to all forward to the underlying
arbitrary-dim implementation, reducing code duplication. (It's probably
marginally less efficient in the new world.)
- Replace Tensor constructor accepting const std::vector<int64_t>& with at::IntList
- Make MKLTensor accept ArrayRef along with vector in constructor and
Reset (unfortunately, no implicit conversions here, since it's templated on
index type.)
- There are a few other places, like cudnn, where I changed functions
that previously took const std::vector<int64_t>& to take at::IntList
instead.
Classification of call site changes:
- 'const std::vector<int64_t>& x_dims = x.dims()' ==>
'at::IntList x_dims = x.dims()'
- 'std::vector<int64_t> x_dims = x.dims()' ==>
'std::vector<int64_t> x_dims = x.dims().vec()' (we need a copy!)
Usually this is because we're about to mutably modify the vector
to compute some new dimension. However, it also very commonly occurs in the
form: 'x_dims_ = x.dims()' because we frequently cache sizes in operators.
- Instead of constructing std::vector<int64_t>{blah, blah}, construct an
at::IntList directly
ArrayRef changes:
- cbegin()/cend() iterators, they operate the same aas begin()/end() because
everything on ArrayRef is const.
- Moved operator<< into ArrayRef.h, so that it's always available when
working with ArrayRef. I also templated it, so it now works on an
ArrayRef of any type.
- Add operator== overload for ArrayRef, and also add variants to permit
comparison of ArrayRef with std::vector, a very common operation.
(The non-templated version of operator== can get these automatically
via implicit conversion, but with templates C++ refuses to do
any explicit conversions.)
I'm planning to audit all dims() call sites to make sure they don't
expect 'auto x = t.dims()' to give you an x whose lifetime can validly
outlive the tensor.
I opted not to do a dims() to sizes() rename, because dims() also matches
the protobufs accessor. Bad news!
Reviewed By: jerryzh168
Differential Revision: D10111759
fbshipit-source-id: a2a81dc4b92c22ad4b3b8ef4077a7e97b6479452
Summary:
This PR contains changes for:
1. Performance enhancements for group conv using MIOpen
2. Performance enhancements by removing unnecessary computations while running pooling through MIOpen
3. Added check for bwdData comptutation while running MIOpen convGradient operator
4. Fix in MIOpen poolingGradient operator to compute window size for global pooling case
5. Minor code cleanup in MIOpen spatial batch norm operator
Differential Revision: D9979050
Pulled By: bddppq
fbshipit-source-id: fabc7a44a2f9ca0307d99564d1ce8fe1de9a6fbb
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/10888
Add cuda version of SpatialBNOp also optimize SpatialBN on CPU
Reviewed By: houseroad
Differential Revision: D9512435
fbshipit-source-id: 6f828c88d56d30dc9a2f98a297a161c35cc511b1
Summary:
The goal of this PR is to update the hip files to reflect relevant changes in cuda source files.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/9826
Differential Revision: D9032840
Pulled By: bddppq
fbshipit-source-id: 504e55c46308eebfee3c9a7beea1f294fe03470f
Summary:
The PR contains:
Fixes for running MIOpen conv operator in a multi worker scenario, along with a performance fix
Fixing a typo in MIOpen pool op and adding some extra checks for MIOpen spatial BN op
bddppq
Pull Request resolved: https://github.com/pytorch/pytorch/pull/9842
Differential Revision: D9012512
Pulled By: bddppq
fbshipit-source-id: 270e1323c20fbfbc4b725f9a4ff34cd073ddaaa8
Summary:
The goal of this PR is to add an infrastructure; to convert(hipify) CUDA ops into [HIP](https://github.com/ROCm-Developer-Tools/HIP) ops , at **compile** time.
Note that HIP ops, which are portable c++ code, can run on AMD and NVIDIA platform.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/9322
Differential Revision: D8884707
Pulled By: bddppq
fbshipit-source-id: dabc6319546002c308c10528238e6684f7aef0f8
* Add hip support for caffe2 core
* Add MIOPEN header/wrapper to caffe2 core
* Add HIP device into caffe2 PB
* top level makefile change for rocm/hip
* makefile scaffolding for AMD/RocM/HIP
* Makefile scafodding for AMD/RocM/HIP; add makefile/utility for HIP files
* caffe2 PB update for AMD/ROCM HIP device
* Add AMD/RocM/Thrust dependency
* HIP threadpool update
* Fix makefile macro
* makefile fix: duplicate test/binary name
* makefile clean-up
* makefile clean-up
* add HIP operator registry
* add utilities for hip device
* Add USE_HIP to config summary
* makefile fix for BUILD_TEST
* merge latest
* Fix indentation
* code clean-up
* Guard builds without HIP and use the same cmake script as PyTorch to find HIP
* Setup rocm environment variables in build.sh (ideally should be done in the docker images)
* setup locale
* set HIP_PLATFORM
* Revert "set HIP_PLATFORM"
This reverts commit 8ec58db2b390c9259220c49fa34cd403568300ad.
* continue the build script environment variables mess
* HCC_AMDGPU_TARGET
* Cleanup the mess, has been fixed in the lastest docker images
* Assign protobuf field hip_gpu_id a new field number for backward compatibility
* change name to avoid conflict
* Fix duplicated thread pool flag
* Refactor cmake files to not add hip includes and libs globally
* Fix the wrong usage of environment variables detection in cmake
* Add MIOPEN CNN operators
* Revert "Add MIOPEN CNN operators"
This reverts commit 6e89ad4385b5b8967a7854c4adda52c012cee42a.
* Add MIOPEN pooling operator
* Add MIOPEN activation operator
* Add MIOPEN softmax operator
* Add MIOPEN spatial batch norm operator
* Add MIOPEN loacl response normalization operator
* Add MIOPEN conv operator
* Clean-up LRN ops
* enable fp16 in MIOPEN pool ops
* Enable fp16 for MIOPEN relu op
* Enable fp16 for MIOPEN spatial batch norm op
* code clean-up
* revert float16 support
* Create Caffe2 python binding for AMD/ROCM/HIP
* Add op fallback for HIP operator
* add hip src/test files in cmake
* exclude hip src/test files
* fix python binding for hip backend
* fix MIOPEN pooling op workspace
* hack to compile miopen operators
* fix include path for MIOPEN ops
* Fix include path
* Add HIP math utilities
* Fix path for HIP math utils
* cmake fix
* Cmake fix / hipcc for hip files
* suppress hipcc warning
* cmake fix /replcae USE_HIP with USE_ROCM
* revert LoadHIP.cmake change
* fix include for thrust/cub-hip
* include path fix for conversion.h
* Updated with latest upstream changes
* clang format fixes
* Context_hip updates
* Fixed typo in rocblas handle get function
* Updated hipified math utils
* Updated math hip test util
* Updated context hip test
* Updated common_hip
* Updated net async dag for HIP
* Added MIOPEN in operator hip test
* fix
* C2 dependencies clean-up
* fix include path for building custom protobuf
* Decouple miopen pool op and conv_pool_op base
* cmake refactor
* fix operator_hip_test
* move all hip/miopen ops files into caffe2/operators/hip
* sanitize cmake
* permission issue
* remove extra parenthesis
* remove artifact from resolving merge conflict
* cont. sanitize cmake files
* fix syntax error
* sanitize conversion.h
* .
* Revert "."
This reverts commit 56020cb0e996a31ae27bf1f8f491955ed0b121b9.
* clang-format
