Skip to content

[ET][Windows] Fix ExecuTorch Windows host build portability defects#20948

Merged
meta-codesync[bot] merged 1 commit into
gh/SS-JIA/573/basefrom
gh/SS-JIA/573/head
Jul 16, 2026
Merged

[ET][Windows] Fix ExecuTorch Windows host build portability defects#20948
meta-codesync[bot] merged 1 commit into
gh/SS-JIA/573/basefrom
gh/SS-JIA/573/head

Conversation

@SS-JIA

@SS-JIA SS-JIA commented Jul 14, 2026

Copy link
Copy Markdown
Contributor

Stack from ghstack (oldest at bottom):

Building ExecuTorch (Vulkan backend plus core runtime) for a Windows x86_64 host with the arvr clang toolchain surfaced three genuine portability defects that fail under its strict -Werror set and generated-header wiring. These are correct fixes independent of any warning-suppression workaround.

In runtime/core/portable_type/c10/c10/targets.bzl, the arvr-mode select that supplies the generated ATen/Config.h routed every non-Android OS to ovrsource_aten_Config.h, an OVR-native-only oxx_static_library that produces no output on the Windows host. The result was fatal error: 'ATen/Config.h' file not found in every CPU kernel that includes ATen vec headers. This adds an ovr_config//os:windows branch pointing at the working generated_aten_config_header, mirroring the existing Android fallback.

In backends/vulkan/runtime/api/containers/Tensor.h, size() and dim() returned const int64_t by value; the meaningless top-level const on a scalar return trips -Werror,-Wignored-qualifiers. This header is included throughout the Vulkan backend, so it blocked vulkan_graph_runtime. The const qualifier is dropped.

In extension/data_loader/mman.h and mman_windows.cpp, #define NOMINMAX was unconditional while the toolchain already predefines it, tripping -Werror,-Wmacro-redefined when compiling mmap_data_loader (pulled in by Module). Both sites are now guarded with #ifndef NOMINMAX.

Differential Revision: D112012051

[ghstack-poisoned]
@SS-JIA
SS-JIA requested a review from JacobSzwejbka as a code owner July 14, 2026 22:35
@pytorch-bot

pytorch-bot Bot commented Jul 14, 2026

Copy link
Copy Markdown

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20948

Note: Links to docs will display an error until the docs builds have been completed.

❌ 34 New Failures

As of commit c061549 with merge base ceecc9e (image):

NEW FAILURES - The following jobs have failed:

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@github-actions

Copy link
Copy Markdown

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

@meta-cla meta-cla Bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Jul 14, 2026
@meta-codesync
meta-codesync Bot merged commit 66f08a3 into gh/SS-JIA/573/base Jul 16, 2026
169 of 215 checks passed
@meta-codesync
meta-codesync Bot deleted the gh/SS-JIA/573/head branch July 16, 2026 01:47
@meta-codesync
meta-codesync Bot temporarily deployed to cherry-pick-bot July 16, 2026 01:47 Inactive
SS-JIA added a commit that referenced this pull request Jul 16, 2026
Pull Request resolved: #20948

Building ExecuTorch (Vulkan backend plus core runtime) for a Windows x86_64 host with the arvr clang toolchain surfaced three genuine portability defects that fail under its strict `-Werror` set and generated-header wiring. These are correct fixes independent of any warning-suppression workaround.

In `runtime/core/portable_type/c10/c10/targets.bzl`, the arvr-mode `select` that supplies the generated `ATen/Config.h` routed every non-Android OS to `ovrsource_aten_Config.h`, an OVR-native-only `oxx_static_library` that produces no output on the Windows host. The result was `fatal error: 'ATen/Config.h' file not found` in every CPU kernel that includes ATen vec headers. This adds an `ovr_config//os:windows` branch pointing at the working `generated_aten_config_header`, mirroring the existing Android fallback.

In `backends/vulkan/runtime/api/containers/Tensor.h`, `size()` and `dim()` returned `const int64_t` by value; the meaningless top-level `const` on a scalar return trips `-Werror,-Wignored-qualifiers`. This header is included throughout the Vulkan backend, so it blocked `vulkan_graph_runtime`. The `const` qualifier is dropped.

In `extension/data_loader/mman.h` and `mman_windows.cpp`, `#define NOMINMAX` was unconditional while the toolchain already predefines it, tripping `-Werror,-Wmacro-redefined` when compiling `mmap_data_loader` (pulled in by `Module`). Both sites are now guarded with `#ifndef NOMINMAX`.
ghstack-source-id: 402995448
@exported-using-ghexport

Differential Revision: [D112012051](https://our.internmc.facebook.com/intern/diff/D112012051/)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. meta-exported

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants