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
175 lines
6.8 KiB
C
175 lines
6.8 KiB
C
/*===--------- movrs_avx10_2intrin.h - AVX10.2-MOVRS 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 <movrs_avx10_2intrin.h> directly; include <immintrin.h> instead."
|
|
#endif
|
|
|
|
#ifndef __MOVRS_AVX10_2INTRIN_H
|
|
#define __MOVRS_AVX10_2INTRIN_H
|
|
#ifdef __x86_64__
|
|
|
|
/* Define the default attributes for the functions in this file. */
|
|
#define __DEFAULT_FN_ATTRS128 \
|
|
__attribute__((__always_inline__, __nodebug__, __target__("movrs,avx10.2"), \
|
|
__min_vector_width__(128)))
|
|
#define __DEFAULT_FN_ATTRS256 \
|
|
__attribute__((__always_inline__, __nodebug__, __target__("movrs,avx10.2"), \
|
|
__min_vector_width__(256)))
|
|
|
|
static __inline__ __m128i __DEFAULT_FN_ATTRS128
|
|
_mm_loadrs_epi8(void const *__A) {
|
|
return (__m128i)__builtin_ia32_vmovrsb128((const __v16qi *)(__A));
|
|
}
|
|
|
|
static __inline__ __m128i __DEFAULT_FN_ATTRS128
|
|
_mm_mask_loadrs_epi8(__m128i __W, __mmask16 __U, void const *__A) {
|
|
return (__m128i)__builtin_ia32_selectb_128(
|
|
(__mmask16)__U, (__v16qi)_mm_loadrs_epi8(__A), (__v16qi)__W);
|
|
}
|
|
|
|
static __inline__ __m128i __DEFAULT_FN_ATTRS128
|
|
_mm_maskz_loadrs_epi8(__mmask16 __U, void const *__A) {
|
|
return (__m128i)__builtin_ia32_selectb_128((__mmask16)__U,
|
|
(__v16qi)_mm_loadrs_epi8(__A),
|
|
(__v16qi)_mm_setzero_si128());
|
|
}
|
|
|
|
static __inline__ __m256i __DEFAULT_FN_ATTRS256
|
|
_mm256_loadrs_epi8(void const *__A) {
|
|
return (__m256i)__builtin_ia32_vmovrsb256((const __v32qi *)(__A));
|
|
}
|
|
|
|
static __inline__ __m256i __DEFAULT_FN_ATTRS256
|
|
_mm256_mask_loadrs_epi8(__m256i __W, __mmask32 __U, void const *__A) {
|
|
return (__m256i)__builtin_ia32_selectb_256(
|
|
(__mmask32)__U, (__v32qi)_mm256_loadrs_epi8(__A), (__v32qi)__W);
|
|
}
|
|
|
|
static __inline__ __m256i __DEFAULT_FN_ATTRS256
|
|
_mm256_maskz_loadrs_epi8(__mmask32 __U, void const *__A) {
|
|
return (__m256i)__builtin_ia32_selectb_256((__mmask32)__U,
|
|
(__v32qi)_mm256_loadrs_epi8(__A),
|
|
(__v32qi)_mm256_setzero_si256());
|
|
}
|
|
|
|
static __inline__ __m128i __DEFAULT_FN_ATTRS128
|
|
_mm_loadrs_epi32(void const *__A) {
|
|
return (__m128i)__builtin_ia32_vmovrsd128((const __v4si *)(__A));
|
|
}
|
|
|
|
static __inline__ __m128i __DEFAULT_FN_ATTRS128
|
|
_mm_mask_loadrs_epi32(__m128i __W, __mmask8 __U, void const *__A) {
|
|
return (__m128i)__builtin_ia32_selectd_128(
|
|
(__mmask8)__U, (__v4si)_mm_loadrs_epi32(__A), (__v4si)__W);
|
|
}
|
|
|
|
static __inline__ __m128i __DEFAULT_FN_ATTRS128
|
|
_mm_maskz_loadrs_epi32(__mmask8 __U, void const *__A) {
|
|
return (__m128i)__builtin_ia32_selectd_128((__mmask8)__U,
|
|
(__v4si)_mm_loadrs_epi32(__A),
|
|
(__v4si)_mm_setzero_si128());
|
|
}
|
|
|
|
static __inline__ __m256i __DEFAULT_FN_ATTRS256
|
|
_mm256_loadrs_epi32(void const *__A) {
|
|
return (__m256i)__builtin_ia32_vmovrsd256((const __v8si *)(__A));
|
|
}
|
|
|
|
static __inline__ __m256i __DEFAULT_FN_ATTRS256
|
|
_mm256_mask_loadrs_epi32(__m256i __W, __mmask8 __U, void const *__A) {
|
|
return (__m256i)__builtin_ia32_selectd_256(
|
|
(__mmask8)__U, (__v8si)_mm256_loadrs_epi32(__A), (__v8si)__W);
|
|
}
|
|
|
|
static __inline__ __m256i __DEFAULT_FN_ATTRS256
|
|
_mm256_maskz_loadrs_epi32(__mmask8 __U, void const *__A) {
|
|
return (__m256i)__builtin_ia32_selectd_256((__mmask8)__U,
|
|
(__v8si)_mm256_loadrs_epi32(__A),
|
|
(__v8si)_mm256_setzero_si256());
|
|
}
|
|
|
|
static __inline__ __m128i __DEFAULT_FN_ATTRS128
|
|
_mm_loadrs_epi64(void const *__A) {
|
|
return (__m128i)__builtin_ia32_vmovrsq128((const __v2di *)(__A));
|
|
}
|
|
|
|
static __inline__ __m128i __DEFAULT_FN_ATTRS128
|
|
_mm_mask_loadrs_epi64(__m128i __W, __mmask8 __U, void const *__A) {
|
|
return (__m128i)__builtin_ia32_selectq_128(
|
|
(__mmask8)__U, (__v2di)_mm_loadrs_epi64(__A), (__v2di)__W);
|
|
}
|
|
|
|
static __inline__ __m128i __DEFAULT_FN_ATTRS128
|
|
_mm_maskz_loadrs_epi64(__mmask8 __U, void const *__A) {
|
|
return (__m128i)__builtin_ia32_selectq_128((__mmask8)__U,
|
|
(__v2di)_mm_loadrs_epi64(__A),
|
|
(__v2di)_mm_setzero_si128());
|
|
}
|
|
|
|
static __inline__ __m256i __DEFAULT_FN_ATTRS256
|
|
_mm256_loadrs_epi64(void const *__A) {
|
|
return (__m256i)__builtin_ia32_vmovrsq256((const __v4di *)(__A));
|
|
}
|
|
|
|
static __inline__ __m256i __DEFAULT_FN_ATTRS256
|
|
_mm256_mask_loadrs_epi64(__m256i __W, __mmask8 __U, void const *__A) {
|
|
return (__m256i)__builtin_ia32_selectq_256(
|
|
(__mmask8)__U, (__v4di)_mm256_loadrs_epi64(__A), (__v4di)__W);
|
|
}
|
|
|
|
static __inline__ __m256i __DEFAULT_FN_ATTRS256
|
|
_mm256_maskz_loadrs_epi64(__mmask8 __U, void const *__A) {
|
|
return (__m256i)__builtin_ia32_selectq_256((__mmask8)__U,
|
|
(__v4di)_mm256_loadrs_epi64(__A),
|
|
(__v4di)_mm256_setzero_si256());
|
|
}
|
|
|
|
static __inline__ __m128i __DEFAULT_FN_ATTRS128
|
|
_mm_loadrs_epi16(void const *__A) {
|
|
return (__m128i)__builtin_ia32_vmovrsw128((const __v8hi *)(__A));
|
|
}
|
|
|
|
static __inline__ __m128i __DEFAULT_FN_ATTRS128
|
|
_mm_mask_loadrs_epi16(__m128i __W, __mmask8 __U, void const *__A) {
|
|
return (__m128i)__builtin_ia32_selectw_128(
|
|
(__mmask8)__U, (__v8hi)_mm_loadrs_epi16(__A), (__v8hi)__W);
|
|
}
|
|
|
|
static __inline__ __m128i __DEFAULT_FN_ATTRS128
|
|
_mm_maskz_loadrs_epi16(__mmask8 __U, void const *__A) {
|
|
return (__m128i)__builtin_ia32_selectw_128((__mmask8)__U,
|
|
(__v8hi)_mm_loadrs_epi16(__A),
|
|
(__v8hi)_mm_setzero_si128());
|
|
}
|
|
|
|
static __inline__ __m256i __DEFAULT_FN_ATTRS256
|
|
_mm256_loadrs_epi16(void const *__A) {
|
|
return (__m256i)__builtin_ia32_vmovrsw256((const __v16hi *)(__A));
|
|
}
|
|
|
|
static __inline__ __m256i __DEFAULT_FN_ATTRS256
|
|
_mm256_mask_loadrs_epi16(__m256i __W, __mmask16 __U, void const *__A) {
|
|
return (__m256i)__builtin_ia32_selectw_256(
|
|
(__mmask16)__U, (__v16hi)_mm256_loadrs_epi16(__A), (__v16hi)__W);
|
|
}
|
|
|
|
static __inline__ __m256i __DEFAULT_FN_ATTRS256
|
|
_mm256_maskz_loadrs_epi16(__mmask16 __U, void const *__A) {
|
|
return (__m256i)__builtin_ia32_selectw_256((__mmask16)__U,
|
|
(__v16hi)_mm256_loadrs_epi16(__A),
|
|
(__v16hi)_mm256_setzero_si256());
|
|
}
|
|
|
|
#undef __DEFAULT_FN_ATTRS128
|
|
#undef __DEFAULT_FN_ATTRS256
|
|
|
|
#endif /* __x86_64__ */
|
|
#endif /* __MOVRS_AVX10_2INTRIN_H */
|