Files
TheRock/compiler/amd-llvm/clang/lib/Headers/amxmovrsintrin.h
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

49 lines
2.2 KiB
C++

/*===-------- amxmovrsintrin.h - AMX MOVRS 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 <amxmovrsintrin.h> directly; include <immintrin.h> instead."
#endif /* __IMMINTRIN_H */
#ifndef __AMXMOVRSINTRIN_H
#define __AMXMOVRSINTRIN_H
#ifdef __x86_64__
#define __DEFAULT_FN_ATTRS_MOVRS \
__attribute__((__always_inline__, __nodebug__, __target__("amx-movrs")))
#define _tile_loaddrs(dst, base, stride) \
__builtin_ia32_tileloaddrs64((dst), ((const void *)(base)), \
(__SIZE_TYPE__)(stride))
#define _tile_stream_loaddrs(dst, base, stride) \
__builtin_ia32_tileloaddrst164((dst), ((const void *)(base)), \
(__SIZE_TYPE__)(stride))
static __inline__ _tile1024i __DEFAULT_FN_ATTRS_MOVRS
_tile_loaddrs_internal(unsigned short m, unsigned short n, const void *base,
__SIZE_TYPE__ stride) {
return __builtin_ia32_tileloaddrs64_internal(m, n, base,
(__SIZE_TYPE__)(stride));
}
static __inline__ _tile1024i __DEFAULT_FN_ATTRS_MOVRS
_tile_loaddrst1_internal(unsigned short m, unsigned short n, const void *base,
__SIZE_TYPE__ stride) {
return __builtin_ia32_tileloaddrst164_internal(m, n, base,
(__SIZE_TYPE__)(stride));
}
static __inline__ void __DEFAULT_FN_ATTRS_MOVRS
__tile_loaddrs(__tile1024i *dst, const void *base, __SIZE_TYPE__ stride) {
dst->tile = _tile_loaddrs_internal(dst->row, dst->col, base, stride);
}
static __inline__ void __DEFAULT_FN_ATTRS_MOVRS __tile_stream_loaddrs(
__tile1024i *dst, const void *base, __SIZE_TYPE__ stride) {
dst->tile = _tile_loaddrst1_internal(dst->row, dst->col, base, stride);
}
#undef __DEFAULT_FN_ATTRS_MOVRS
#endif /* __x86_64__ */
#endif /* __AMXMOVRSINTRIN_H */