Adam Siemieniuk 87782b216f [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.

2025-01-29 13:07:41 +01:00

..

IR

…

Transforms

[mlir][x86vector] AVX512-BF16 Dot op (#124800)

2025-01-29 13:07:41 +01:00

CMakeLists.txt

…