diff options
| author | Adam Siemieniuk <adam.siemieniuk@intel.com> | 2025-01-29 13:07:41 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-01-29 13:07:41 +0100 |
| commit | 87782b216fd3e7a8f8b2de04d4af467b390e9a34 (patch) | |
| tree | 975bcdf7a659987d384a4f8fa52ad61cac6b2fc6 /clang/lib/Frontend/CompilerInvocation.cpp | |
| parent | 9534d27e3321a3b9e6e79fe6328445575bf26b7b (diff) | |
| download | llvm-87782b216fd3e7a8f8b2de04d4af467b390e9a34.zip llvm-87782b216fd3e7a8f8b2de04d4af467b390e9a34.tar.gz llvm-87782b216fd3e7a8f8b2de04d4af467b390e9a34.tar.bz2 | |
[mlir][x86vector] AVX512-BF16 Dot op (#124800)
Adds AVX512 bf16 dot-product operation and defines lowering to LLVM
intrinsics.
AVX512 intrinsic operation definition is extended with an optional
extension field that allows specifying necessary LLVM mnemonic suffix
e.g., `"bf16"` for `x86_avx512bf16_` intrinsics.
Diffstat (limited to 'clang/lib/Frontend/CompilerInvocation.cpp')
0 files changed, 0 insertions, 0 deletions