Files
TheRock/compiler/amd-llvm/clang/lib/Headers/avx512ifmavlintrin.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

139 lines
6.0 KiB
C++

/*===------------- avx512ifmavlintrin.h - IFMA intrinsics ------------------===
*
*
* 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 <avx512ifmavlintrin.h> directly; include <immintrin.h> instead."
#endif
#ifndef __IFMAVLINTRIN_H
#define __IFMAVLINTRIN_H
/* Define the default attributes for the functions in this file. */
#if defined(__cplusplus) && (__cplusplus >= 201103L)
#define __DEFAULT_FN_ATTRS128 \
__attribute__((__always_inline__, __nodebug__, \
__target__("avx512ifma,avx512vl"), \
__min_vector_width__(128))) constexpr
#define __DEFAULT_FN_ATTRS256 \
__attribute__((__always_inline__, __nodebug__, \
__target__("avx512ifma,avx512vl"), \
__min_vector_width__(256))) constexpr
#else
#define __DEFAULT_FN_ATTRS128 \
__attribute__((__always_inline__, __nodebug__, \
__target__("avx512ifma,avx512vl"), \
__min_vector_width__(128)))
#define __DEFAULT_FN_ATTRS256 \
__attribute__((__always_inline__, __nodebug__, \
__target__("avx512ifma,avx512vl"), \
__min_vector_width__(256)))
#endif
#if !(defined(__AVXIFMA__) || defined(__AVX512IFMA__))
#define _mm_madd52hi_epu64(X, Y, Z) \
((__m128i)__builtin_ia32_vpmadd52huq128((__v2di)(X), (__v2di)(Y), \
(__v2di)(Z)))
#define _mm256_madd52hi_epu64(X, Y, Z) \
((__m256i)__builtin_ia32_vpmadd52huq256((__v4di)(X), (__v4di)(Y), \
(__v4di)(Z)))
#define _mm_madd52lo_epu64(X, Y, Z) \
((__m128i)__builtin_ia32_vpmadd52luq128((__v2di)(X), (__v2di)(Y), \
(__v2di)(Z)))
#define _mm256_madd52lo_epu64(X, Y, Z) \
((__m256i)__builtin_ia32_vpmadd52luq256((__v4di)(X), (__v4di)(Y), \
(__v4di)(Z)))
#endif
#if defined(__AVX512IFMA__)
static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_madd52hi_epu64(__m128i __X, __m128i __Y, __m128i __Z) {
return (__m128i)__builtin_ia32_vpmadd52huq128((__v2di)__X, (__v2di)__Y,
(__v2di)__Z);
}
static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_madd52hi_epu64(__m256i __X, __m256i __Y, __m256i __Z) {
return (__m256i)__builtin_ia32_vpmadd52huq256((__v4di)__X, (__v4di)__Y,
(__v4di)__Z);
}
static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_madd52lo_epu64(__m128i __X, __m128i __Y, __m128i __Z) {
return (__m128i)__builtin_ia32_vpmadd52luq128((__v2di)__X, (__v2di)__Y,
(__v2di)__Z);
}
static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_madd52lo_epu64(__m256i __X, __m256i __Y, __m256i __Z) {
return (__m256i)__builtin_ia32_vpmadd52luq256((__v4di)__X, (__v4di)__Y,
(__v4di)__Z);
}
#endif
static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_madd52hi_epu64(__m128i __W, __mmask8 __M, __m128i __X, __m128i __Y) {
return (__m128i)__builtin_ia32_selectq_128(
__M, (__v2di)__builtin_ia32_vpmadd52huq128(__W, __X, __Y), (__v2di)__W);
}
static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_madd52hi_epu64(__mmask8 __M, __m128i __X, __m128i __Y, __m128i __Z) {
return (__m128i)__builtin_ia32_selectq_128(
__M, (__v2di)__builtin_ia32_vpmadd52huq128(__X, __Y, __Z),
(__v2di)_mm_setzero_si128());
}
static __inline__ __m256i __DEFAULT_FN_ATTRS256 _mm256_mask_madd52hi_epu64(
__m256i __W, __mmask8 __M, __m256i __X, __m256i __Y) {
return (__m256i)__builtin_ia32_selectq_256(
__M, (__v4di)__builtin_ia32_vpmadd52huq256(__W, __X, __Y), (__v4di)__W);
}
static __inline__ __m256i __DEFAULT_FN_ATTRS256 _mm256_maskz_madd52hi_epu64(
__mmask8 __M, __m256i __X, __m256i __Y, __m256i __Z) {
return (__m256i)__builtin_ia32_selectq_256(
__M, (__v4di)__builtin_ia32_vpmadd52huq256(__X, __Y, __Z),
(__v4di)_mm256_setzero_si256());
}
static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_madd52lo_epu64(__m128i __W, __mmask8 __M, __m128i __X, __m128i __Y) {
return (__m128i)__builtin_ia32_selectq_128(
__M, (__v2di)__builtin_ia32_vpmadd52luq128(__W, __X, __Y), (__v2di)__W);
}
static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_madd52lo_epu64(__mmask8 __M, __m128i __X, __m128i __Y, __m128i __Z) {
return (__m128i)__builtin_ia32_selectq_128(
__M, (__v2di)__builtin_ia32_vpmadd52luq128(__X, __Y, __Z),
(__v2di)_mm_setzero_si128());
}
static __inline__ __m256i __DEFAULT_FN_ATTRS256 _mm256_mask_madd52lo_epu64(
__m256i __W, __mmask8 __M, __m256i __X, __m256i __Y) {
return (__m256i)__builtin_ia32_selectq_256(
__M, (__v4di)__builtin_ia32_vpmadd52luq256(__W, __X, __Y), (__v4di)__W);
}
static __inline__ __m256i __DEFAULT_FN_ATTRS256 _mm256_maskz_madd52lo_epu64(
__mmask8 __M, __m256i __X, __m256i __Y, __m256i __Z) {
return (__m256i)__builtin_ia32_selectq_256(
__M, (__v4di)__builtin_ia32_vpmadd52luq256(__X, __Y, __Z),
(__v4di)_mm256_setzero_si256());
}
#undef __DEFAULT_FN_ATTRS128
#undef __DEFAULT_FN_ATTRS256
#endif