[mathcore] Work around libstdc++ <experimental/simd> AVX-512 bug#22437
Open
guitargeek wants to merge 1 commit into
Open
[mathcore] Work around libstdc++ <experimental/simd> AVX-512 bug#22437guitargeek wants to merge 1 commit into
<experimental/simd> AVX-512 bug#22437guitargeek wants to merge 1 commit into
Conversation
The `libstdc++`'s `_VecBltnBtmsk` (AVX-512 mask) ABI fails to compile with non-GCC front ends (Clang, Intel icpx) due to a static_assert requiring `long long` and `long` to be the same type, reproducible at least with GCC 15 and 16. Detect this in CMake and, when the AVX-512 path is broken but the 256-bit AVX path compiles, pin ROOT's SIMD alias in `Math/Types.h` to `simd_abi::__avx` (which corresponds to AVX-256). ABI stays consistent across all translation units and interpreted contexts, no `-mno-avx512f` is needed, and the rest of ROOT keeps native AVX-512 codegen. Closes root-project#22370.
1 task
Test Results 22 files 22 suites 3d 7h 48m 37s ⏱️ For more details on these failures, see this check. Results for commit 51dd384. ♻️ This comment has been updated with latest results. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The
libstdc++'s_VecBltnBtmsk(AVX-512 mask) ABI fails to compile with non-GCC front ends (Clang, Intel icpx) due to a static_assert requiringlong longandlongto be the same type, reproducible at least with GCC 15 and 16.Detect this in CMake and, when the AVX-512 path is broken but the 256-bit AVX path compiles, pin ROOT's SIMD alias in
Math/Types.htosimd_abi::__avx(which corresponds to AVX-256). ABI stays consistent across all translation units and interpreted contexts, no-mno-avx512fis needed, and the rest of ROOT keeps native AVX-512 codegen.Closes #22370.