Skip to content

Don't specialize the executable for the current device#3

Merged
DenisVieriu97 merged 2 commits intoDenisVieriu97:mainfrom
georgepaw:dev/georgep/package
Nov 18, 2023
Merged

Don't specialize the executable for the current device#3
DenisVieriu97 merged 2 commits intoDenisVieriu97:mainfrom
georgepaw:dev/georgep/package

Conversation

@georgepaw
Copy link

No description provided.

@DenisVieriu97 DenisVieriu97 self-requested a review November 17, 2023 22:06
Copy link
Owner

@DenisVieriu97 DenisVieriu97 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks! Looks good

@DenisVieriu97 DenisVieriu97 merged commit df7cb59 into DenisVieriu97:main Nov 18, 2023
@georgepaw georgepaw deleted the dev/georgep/package branch November 20, 2023 11:46
DenisVieriu97 added a commit that referenced this pull request Nov 26, 2023
Co-authored-by: Denis Vieriu <104024078+DenisVieriu97@users.noreply.github.com>
DenisVieriu97 added a commit that referenced this pull request Nov 30, 2023
Co-authored-by: Denis Vieriu <104024078+DenisVieriu97@users.noreply.github.com>
DenisVieriu97 added a commit that referenced this pull request Nov 30, 2023
* Fix mps_executor_runner build when using cmake

* Add CI scripts to run supported executorch networks through MPS (#1)

* Add CI scripts to run supported executorch networks through MPS

* Fix CI

* Fix CI #2

* Don't specialize the executable for the current device (#3)

Co-authored-by: Denis Vieriu <104024078+DenisVieriu97@users.noreply.github.com>

* Update CI script to run test_mps (#4)

* Update CI script to run test_mps

* Update cmdline

* Add lint for mps

* Update lint script

* Update lint script

* Fix lint

* Fix lint

* Fix lint

* Fix lint

* Fix lint

* Fix lint

* Add support for conv1D (fixes w2l)

* Perf imprv - Map conv2D to depthwiseConv3D

* Add support for PyTorch style printing of output tensors

* Fix lint

* Remove unused headers

* Remove unused headers #2

---------

Co-authored-by: Grzegorz George Pawelczak <grzpawelczak@gmail.com>
DenisVieriu97 added a commit that referenced this pull request Dec 1, 2023
Co-authored-by: Denis Vieriu <104024078+DenisVieriu97@users.noreply.github.com>
DenisVieriu97 added a commit that referenced this pull request Dec 1, 2023
* Fix mps_executor_runner build when using cmake

* Add CI scripts to run supported executorch networks through MPS (#1)

* Add CI scripts to run supported executorch networks through MPS

* Fix CI

* Fix CI #2

* Don't specialize the executable for the current device (#3)

Co-authored-by: Denis Vieriu <104024078+DenisVieriu97@users.noreply.github.com>

* Update CI script to run test_mps (#4)

* Update CI script to run test_mps

* Update cmdline

* Add lint for mps

* Update lint script

* Update lint script

* Fix lint

* Fix lint

* Fix lint

* Fix lint

* Fix lint

* Fix lint

* Add support for conv1D (fixes w2l)

* Perf imprv - Map conv2D to depthwiseConv3D

* Add support for PyTorch style printing of output tensors

* Fix lint

* Remove unused headers

* Remove unused headers #2

---------

Co-authored-by: Grzegorz George Pawelczak <grzpawelczak@gmail.com>
DenisVieriu97 added a commit that referenced this pull request Dec 12, 2023
Co-authored-by: Denis Vieriu <104024078+DenisVieriu97@users.noreply.github.com>
DenisVieriu97 added a commit that referenced this pull request Dec 12, 2023
* Fix mps_executor_runner build when using cmake

* Add CI scripts to run supported executorch networks through MPS (#1)

* Add CI scripts to run supported executorch networks through MPS

* Fix CI

* Fix CI #2

* Don't specialize the executable for the current device (#3)

Co-authored-by: Denis Vieriu <104024078+DenisVieriu97@users.noreply.github.com>

* Update CI script to run test_mps (#4)

* Update CI script to run test_mps

* Update cmdline

* Add lint for mps

* Update lint script

* Update lint script

* Fix lint

* Fix lint

* Fix lint

* Fix lint

* Fix lint

* Fix lint

* Add support for conv1D (fixes w2l)

* Perf imprv - Map conv2D to depthwiseConv3D

* Add support for PyTorch style printing of output tensors

* Fix lint

* Remove unused headers

* Remove unused headers #2

---------

Co-authored-by: Grzegorz George Pawelczak <grzpawelczak@gmail.com>
DenisVieriu97 added a commit that referenced this pull request Jan 19, 2024
Co-authored-by: Denis Vieriu <104024078+DenisVieriu97@users.noreply.github.com>
DenisVieriu97 added a commit that referenced this pull request Jan 19, 2024
* Fix mps_executor_runner build when using cmake

* Add CI scripts to run supported executorch networks through MPS (#1)

* Add CI scripts to run supported executorch networks through MPS

* Fix CI

* Fix CI #2

* Don't specialize the executable for the current device (#3)

Co-authored-by: Denis Vieriu <104024078+DenisVieriu97@users.noreply.github.com>

* Update CI script to run test_mps (#4)

* Update CI script to run test_mps

* Update cmdline

* Add lint for mps

* Update lint script

* Update lint script

* Fix lint

* Fix lint

* Fix lint

* Fix lint

* Fix lint

* Fix lint

* Add support for conv1D (fixes w2l)

* Perf imprv - Map conv2D to depthwiseConv3D

* Add support for PyTorch style printing of output tensors

* Fix lint

* Remove unused headers

* Remove unused headers #2

---------

Co-authored-by: Grzegorz George Pawelczak <grzpawelczak@gmail.com>
DenisVieriu97 pushed a commit that referenced this pull request Aug 9, 2024
Summary:
Pull Request resolved: pytorch#4127

The convention in most files is:
1. Related header
2. Headers of the form ".h" (i.e. this project's other headers, further organize into blocks according to directory)
3. Headers of the form <> (i.e. standard libraries' headers)

This change organizes files violating this convention by resolving #3.
ghstack-source-id: 232399398
exported-using-ghexport

bypass-github-export-checks
bypass-github-pytorch-ci-checks
bypass-github-executorch-ci-checks

Reviewed By: SS-JIA

Differential Revision: D59282477

fbshipit-source-id: 29e0ece657c9bae05a3072594e57e57db92be2b3
DenisVieriu97 added a commit that referenced this pull request Aug 14, 2024
manuelcandales pushed a commit that referenced this pull request Aug 27, 2025
BNNS copy crashes the process when the dtypes differ
(pytorch#11714).

With the example in this PR
(pytorch#11714), we crash the
process on main. Here is the stack trace from LLDB:

```
Process 19234 stopped
* thread #1, queue = 'com.apple.main-thread', stop reason = signal SIGABRT
    frame #0: 0x0000000190ac9388 libsystem_kernel.dylib`__pthread_kill + 8
libsystem_kernel.dylib`__pthread_kill:
->  0x190ac9388 <+8>:  b.lo   0x190ac93a8    ; <+40>
    0x190ac938c <+12>: pacibsp 
    0x190ac9390 <+16>: stp    x29, x30, [sp, #-0x10]!
    0x190ac9394 <+20>: mov    x29, sp
(lldb) bt
* thread #1, queue = 'com.apple.main-thread', stop reason = signal SIGABRT
  * frame #0: 0x0000000190ac9388 libsystem_kernel.dylib`__pthread_kill + 8
    frame #1: 0x0000000190b0288c libsystem_pthread.dylib`pthread_kill + 296
    frame #2: 0x0000000190a0bc60 libsystem_c.dylib`abort + 124
    frame #3: 0x0000000190910174 libsystem_malloc.dylib`malloc_vreport + 892
    frame #4: 0x0000000190913c90 libsystem_malloc.dylib`malloc_report + 64
    frame #5: 0x000000019091821c libsystem_malloc.dylib`___BUG_IN_CLIENT_OF_LIBMALLOC_POINTER_BEING_FREED_WAS_NOT_ALLOCATED + 32
    frame #6: 0x000000019d2f4084 libBNNS.dylib`___lldb_unnamed_symbol1620 + 564
    frame #7: 0x000000019d2f5bac libBNNS.dylib`___lldb_unnamed_symbol1628 + 680
    frame #8: 0x000000019d69ce48 libBNNS.dylib`BNNSCopy + 616
    frame #9: 0x000000030c74d950 _portable_lib.cpython-310-darwin.so`(anonymous namespace)::copy_using_bnns(executorchcoreml::MultiArray const&, executorchcoreml::MultiArray&) + 188
    frame #10: 0x000000030c74cfdc _portable_lib.cpython-310-darwin.so`(anonymous namespace)::copy(executorchcoreml::MultiArray const&, executorchcoreml::MultiArray&, executorchcoreml::MultiArray::CopyOptions) + 72
    frame #11: 0x000000030c74ceec _portable_lib.cpython-310-darwin.so`executorchcoreml::MultiArray::copy(executorchcoreml::MultiArray&, executorchcoreml::MultiArray::CopyOptions) const + 148
    frame #12: 0x000000030c7488d4 _portable_lib.cpython-310-darwin.so`invocation function for block in (anonymous namespace)::copy(MLMultiArray*, executorchcoreml::MultiArray&) + 376
    frame #13: 0x000000030c748ac8 _portable_lib.cpython-310-darwin.so`invocation function for block in (anonymous namespace)::copy(MLMultiArray*, executorchcoreml::MultiArray&) + 52
    frame #14: 0x000000019ad33f4c CoreML`CoreML::MultiArrayBuffer::getBytesWithHandler(void (void const*, unsigned long) block_pointer) const + 340
    frame pytorch#15: 0x000000019ad34138 CoreML`-[MLMultiArray(ScopedBufferAccess) getBytesWithHandler:] + 152
    frame pytorch#16: 0x000000030c7485ec _portable_lib.cpython-310-darwin.so`(anonymous namespace)::copy(MLMultiArray*, executorchcoreml::MultiArray&) + 296
    frame pytorch#17: 0x000000030c744f68 _portable_lib.cpython-310-darwin.so`(anonymous namespace)::set_outputs(std::__1::vector<executorchcoreml::MultiArray, std::__1::allocator<executorchcoreml::MultiArray>>&, NSArray<MLMultiArray*>*) + 180
```


With this PR, the process succeeds.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants