================ @@ -0,0 +1,381 @@ +/*===--------------------- amxavx512intrin.h - AMXAVX512 --------------------=== + * + * 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 <amxavx512intrin.h> directly; include <immintrin.h> instead." +#endif // __IMMINTRIN_H + +#ifndef __AMX_AVX512INTRIN_H +#define __AMX_AVX512INTRIN_H +#ifdef __x86_64__ + +#define __DEFAULT_FN_ATTRS_AVX512 \ + __attribute__((__always_inline__, __nodebug__, __target__("amx-avx512"))) + +/// Moves a row from a tile register to a zmm destination register, converting +/// the int32 source elements to fp32. The row of the tile is selected by an +/// 32b GPR. +/// +/// \headerfile <x86intrin.h> +/// +/// \code +/// __m512i _tile_cvtrowd2ps(__tile tsrc, unsigned int row); +/// \endcode +/// +/// \code{.operation} +/// VL := 512 +/// VL_bytes := VL >> 3 +/// row_index := row & 0xffff +/// row_chunk := ((row >> 16) & 0xffff) * VL_bytes +/// FOR i := 0 TO (VL_bytes / 4) - 1 +/// IF i + row_chunk / 4 >= tsrc.colsb / 4 +/// dst.dword[i] := 0 +/// ELSE +/// dst.f32[i] := CONVERT_INT32_TO_FP32(tsrc.row[row_index].dword[row_chunk/4+i], RNE) +/// FI +/// ENDFOR +/// dst[MAX_VL-1:VL] := 0 +/// zero_tileconfig_start() +/// \endcode +/// +/// This intrinsic corresponds to the \c TCVTROWD2PS instruction. +/// +/// \param tsrc +/// The 1st source tile. Max size is 1024 Bytes. +/// \param row +/// The row of the source tile +#define _tile_cvtrowd2ps(tsrc, row) __builtin_ia32_tcvtrowd2ps(tsrc, row) + +/// Moves a row from a tile register to a zmm destination register, converting +/// the fp32 source elements to bf16. It places the resulting bf16 elements +/// in the high 16 bits within each dword. The row of the tile is selected +/// by an 32b GPR. ---------------- phoebewang wrote:
Done. https://github.com/llvm/llvm-project/pull/114070 _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
