================ @@ -0,0 +1,83 @@ +/*===------------- amxfp8intrin.h - AMX intrinsics -*- C++ -*----------------=== + * + * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. + * See https://llvm.org/LICENSE.txt for license information. + * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception + * + *===------------------------------------------------------------------------=== + */ + +#ifndef __IMMINTRIN_H +#error "Never use <amxfp8intrin.h> directly; include <immintrin.h> instead." +#endif /* __IMMINTRIN_H */ + +#ifndef __AMXFP8INTRIN_H +#define __AMXFP8INTRIN_H +#ifdef __x86_64__ + + +/// Compute dot-product of brain-float8 (BF8) or hybrid-float8 (HF8) +/// floating-point pairs in tiles \a a and \a b, accumulating the +/// intermediate single-precision (32-bit) floating-point elements with +/// elements in \a dst, and store the 32-bit result back to tile \a dst. +/// +/// \headerfile <immintrin.h> +/// +/// \code +/// void _tile_dpbf8ps (__tile dst, __tile a, __tile b) +/// \endcode +/// +/// This intrinsic corresponds to the \c TDPBF8PS instruction. +/// +/// \param dst +/// The destination tile. Max size is 1024 Bytes. +/// \param a +/// The 1st source tile. Max size is 1024 Bytes. +/// \param b +/// The 2nd source tile. Max size is 1024 Bytes. +#define _tile_dpbf8ps __builtin_ia32_tdpbf8ps ---------------- phoebewang wrote:
`#define _tile_dpbf8ps(dst, a, b) __builtin_ia32_tdpbf8ps((dst), (a), (b))` The same below. https://github.com/llvm/llvm-project/pull/113850 _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
