Skip to content

Remove AVX compilation on aarch64 builds #5045

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Remove AVX compilation on aarch64 builds #5045

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src/TransposeUtils.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,7 +57,7 @@ void transpose_simd(
#else
static const auto iset = fbgemmInstructionSet();
// Run time CPU detection
#if defined(FBGEMM_FBCODE) || !defined(__aarch64__)
#if defined(FBGEMM_FBCODE)
if (isZmm(iset)) {
internal::transpose_avx512<T>(M, N, src, ld_src, dst, ld_dst);
} else if (isYmm(iset)) {
Expand Down
4 changes: 4 additions & 0 deletions src/UtilsAvx2.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,8 @@

namespace fbgemm::internal {

#ifdef __AVX2__

template <>
void transpose_avx2(
int64_t M,
Expand Down Expand Up @@ -336,4 +338,6 @@ void transpose_avx2(
}
}

#endif // __AVX2__

} // namespace fbgemm::internal
4 changes: 4 additions & 0 deletions src/UtilsAvx512.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,8 @@ namespace fbgemm {

namespace {

#ifdef __AVX512F__

// 16 * 6 = 96 instructions
inline void transpose_kernel_16x16_avx512(
const float* src,
Expand Down Expand Up @@ -2441,6 +2443,8 @@ void transpose_avx512(
}
}

#endif // __AVX512F__

} // namespace internal

} // namespace fbgemm
Loading