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
308 lines
13 KiB
C
308 lines
13 KiB
C
/*===----- avx10_2_512satcvtdsintrin.h - AVX10_2_512SATCVTDS 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 <avx10_2_512satcvtdsintrin.h> directly; include <immintrin.h> instead."
|
|
#endif
|
|
|
|
#ifndef __AVX10_2_512SATCVTDSINTRIN_H
|
|
#define __AVX10_2_512SATCVTDSINTRIN_H
|
|
|
|
/* Define the default attributes for the functions in this file. */
|
|
#define __DEFAULT_FN_ATTRS \
|
|
__attribute__((__always_inline__, __nodebug__, __target__("avx10.2"), \
|
|
__min_vector_width__(512)))
|
|
|
|
// 512 bit : Double -> Int
|
|
static __inline__ __m256i __DEFAULT_FN_ATTRS
|
|
_mm512_cvtts_pd_epi32(__m512d __A) {
|
|
return ((__m256i)__builtin_ia32_vcvttpd2dqs512_round_mask(
|
|
(__v8df)__A, (__v8si)_mm256_undefined_si256(), (__mmask8)-1,
|
|
_MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
static __inline__ __m256i __DEFAULT_FN_ATTRS
|
|
_mm512_mask_cvtts_pd_epi32(__m256i __W, __mmask8 __U, __m512d __A) {
|
|
return ((__m256i)__builtin_ia32_vcvttpd2dqs512_round_mask(
|
|
(__v8df)__A, (__v8si)__W, __U, _MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
static __inline__ __m256i __DEFAULT_FN_ATTRS
|
|
_mm512_maskz_cvtts_pd_epi32(__mmask8 __U, __m512d __A) {
|
|
return ((__m256i)__builtin_ia32_vcvttpd2dqs512_round_mask(
|
|
(__v8df)__A, (__v8si)_mm256_setzero_si256(), __U,
|
|
_MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
#define _mm512_cvtts_roundpd_epi32(__A, __R) \
|
|
((__m256i)__builtin_ia32_vcvttpd2dqs512_round_mask( \
|
|
(__v8df)(__m512d)(__A), (__v8si)_mm256_undefined_si256(), \
|
|
(__mmask8) - 1, (const int)(__R)))
|
|
|
|
#define _mm512_mask_cvtts_roundpd_epi32(__W, __U, __A, __R) \
|
|
((__m256i)__builtin_ia32_vcvttpd2dqs512_round_mask( \
|
|
(__v8df)(__m512d)(__A), (__v8si)(__m256i)(__W), (__mmask8)(__U), \
|
|
(const int)(__R)))
|
|
|
|
#define _mm512_maskz_cvtts_roundpd_epi32(__U, __A, __R) \
|
|
((__m256i)__builtin_ia32_vcvttpd2dqs512_round_mask( \
|
|
(__v8df)(__m512d)(__A), (__v8si)_mm256_setzero_si256(), (__mmask8)(__U), \
|
|
(const int)(__R)))
|
|
|
|
// 512 bit : Double -> uInt
|
|
static __inline__ __m256i __DEFAULT_FN_ATTRS
|
|
_mm512_cvtts_pd_epu32(__m512d __A) {
|
|
return ((__m256i)__builtin_ia32_vcvttpd2udqs512_round_mask(
|
|
(__v8df)__A, (__v8si)_mm256_undefined_si256(), (__mmask8)-1,
|
|
_MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
static __inline__ __m256i __DEFAULT_FN_ATTRS
|
|
_mm512_mask_cvtts_pd_epu32(__m256i __W, __mmask8 __U, __m512d __A) {
|
|
return ((__m256i)__builtin_ia32_vcvttpd2udqs512_round_mask(
|
|
(__v8df)__A, (__v8si)__W, __U, _MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
static __inline__ __m256i __DEFAULT_FN_ATTRS
|
|
_mm512_maskz_cvtts_pd_epu32(__mmask8 __U, __m512d __A) {
|
|
return ((__m256i)__builtin_ia32_vcvttpd2udqs512_round_mask(
|
|
(__v8df)__A, (__v8si)_mm256_setzero_si256(), __U,
|
|
_MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
#define _mm512_cvtts_roundpd_epu32(__A, __R) \
|
|
((__m256i)__builtin_ia32_vcvttpd2udqs512_round_mask( \
|
|
(__v8df)(__m512d)(__A), (__v8si)_mm256_undefined_si256(), \
|
|
(__mmask8) - 1, (const int)(__R)))
|
|
|
|
#define _mm512_mask_cvtts_roundpd_epu32(__W, __U, __A, __R) \
|
|
((__m256i)__builtin_ia32_vcvttpd2udqs512_round_mask( \
|
|
(__v8df)(__m512d)(__A), (__v8si)(__m256i)(__W), (__mmask8)(__U), \
|
|
(const int)(__R)))
|
|
|
|
#define _mm512_maskz_cvtts_roundpd_epu32(__U, __A, __R) \
|
|
((__m256i)__builtin_ia32_vcvttpd2udqs512_round_mask( \
|
|
(__v8df)(__m512d)(__A), (__v8si)_mm256_setzero_si256(), (__mmask8)(__U), \
|
|
(const int)(__R)))
|
|
|
|
// 512 bit : Double -> Long
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_cvtts_pd_epi64(__m512d __A) {
|
|
return ((__m512i)__builtin_ia32_vcvttpd2qqs512_round_mask(
|
|
(__v8df)__A, (__v8di)_mm512_undefined_epi32(), (__mmask8)-1,
|
|
_MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_mask_cvtts_pd_epi64(__m512i __W, __mmask8 __U, __m512d __A) {
|
|
return ((__m512i)__builtin_ia32_vcvttpd2qqs512_round_mask(
|
|
(__v8df)__A, (__v8di)__W, __U, _MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_maskz_cvtts_pd_epi64(__mmask8 __U, __m512d __A) {
|
|
return ((__m512i)__builtin_ia32_vcvttpd2qqs512_round_mask(
|
|
(__v8df)__A, (__v8di)_mm512_setzero_si512(), __U,
|
|
_MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
#define _mm512_cvtts_roundpd_epi64(__A, __R) \
|
|
((__m512i)__builtin_ia32_vcvttpd2qqs512_round_mask( \
|
|
(__v8df)(__m512d)(__A), (__v8di)_mm512_undefined_epi32(), \
|
|
(__mmask8) - 1, (const int)(__R)))
|
|
|
|
#define _mm512_mask_cvtts_roundpd_epi64(__W, __U, __A, __R) \
|
|
((__m512i)__builtin_ia32_vcvttpd2qqs512_round_mask( \
|
|
(__v8df)(__m512d)(__A), (__v8di)(__m512i)(__W), (__mmask8)(__U), \
|
|
(const int)(__R)))
|
|
|
|
#define _mm512_maskz_cvtts_roundpd_epi64(__U, __A, __R) \
|
|
((__m512i)__builtin_ia32_vcvttpd2qqs512_round_mask( \
|
|
(__v8df)(__m512d)(__A), (__v8di)_mm512_setzero_si512(), (__mmask8)(__U), \
|
|
(const int)(__R)))
|
|
|
|
// 512 bit : Double -> ULong
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_cvtts_pd_epu64(__m512d __A) {
|
|
return ((__m512i)__builtin_ia32_vcvttpd2uqqs512_round_mask(
|
|
(__v8df)__A, (__v8di)_mm512_undefined_epi32(), (__mmask8)-1,
|
|
_MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_mask_cvtts_pd_epu64(__m512i __W, __mmask8 __U, __m512d __A) {
|
|
return ((__m512i)__builtin_ia32_vcvttpd2uqqs512_round_mask(
|
|
(__v8df)__A, (__v8di)__W, __U, _MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_maskz_cvtts_pd_epu64(__mmask8 __U, __m512d __A) {
|
|
return ((__m512i)__builtin_ia32_vcvttpd2uqqs512_round_mask(
|
|
(__v8df)__A, (__v8di)_mm512_setzero_si512(), __U,
|
|
_MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
#define _mm512_cvtts_roundpd_epu64(__A, __R) \
|
|
((__m512i)__builtin_ia32_vcvttpd2uqqs512_round_mask( \
|
|
(__v8df)(__m512d)(__A), (__v8di)_mm512_undefined_epi32(), \
|
|
(__mmask8) - 1, (const int)(__R)))
|
|
|
|
#define _mm512_mask_cvtts_roundpd_epu64(__W, __U, __A, __R) \
|
|
((__m512i)__builtin_ia32_vcvttpd2uqqs512_round_mask( \
|
|
(__v8df)(__m512d)(__A), (__v8di)(__m512i)(__W), (__mmask8)(__U), \
|
|
(const int)(__R)))
|
|
|
|
#define _mm512_maskz_cvtts_roundpd_epu64(__U, __A, __R) \
|
|
((__m512i)__builtin_ia32_vcvttpd2uqqs512_round_mask( \
|
|
(__v8df)(__m512d)(__A), (__v8di)_mm512_setzero_si512(), (__mmask8)(__U), \
|
|
(const int)(__R)))
|
|
|
|
// 512 bit: Float -> int
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS _mm512_cvtts_ps_epi32(__m512 __A) {
|
|
return ((__m512i)__builtin_ia32_vcvttps2dqs512_round_mask(
|
|
(__v16sf)(__A), (__v16si)_mm512_undefined_epi32(), (__mmask16)-1,
|
|
_MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_mask_cvtts_ps_epi32(__m512i __W, __mmask16 __U, __m512 __A) {
|
|
return ((__m512i)__builtin_ia32_vcvttps2dqs512_round_mask(
|
|
(__v16sf)(__A), (__v16si)(__W), __U, _MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_maskz_cvtts_ps_epi32(__mmask16 __U, __m512 __A) {
|
|
return ((__m512i)__builtin_ia32_vcvttps2dqs512_round_mask(
|
|
(__v16sf)(__A), (__v16si)_mm512_setzero_si512(), __U,
|
|
_MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
#define _mm512_cvtts_roundps_epi32(__A, __R) \
|
|
((__m512i)__builtin_ia32_vcvttps2dqs512_round_mask( \
|
|
(__v16sf)(__m512)(__A), (__v16si)_mm512_undefined_epi32(), \
|
|
(__mmask16) - 1, (const int)(__R)))
|
|
|
|
#define _mm512_mask_cvtts_roundps_epi32(__W, __U, __A, __R) \
|
|
((__m512i)__builtin_ia32_vcvttps2dqs512_round_mask( \
|
|
(__v16sf)(__m512)(__A), (__v16si)(__m512i)(__W), (__mmask16)(__U), \
|
|
(const int)(__R)))
|
|
|
|
#define _mm512_maskz_cvtts_roundps_epi32(__U, __A, __R) \
|
|
((__m512i)__builtin_ia32_vcvttps2dqs512_round_mask( \
|
|
(__v16sf)(__m512)(__A), (__v16si)_mm512_setzero_si512(), \
|
|
(__mmask16)(__U), (const int)(__R)))
|
|
|
|
// 512 bit: Float -> uint
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS _mm512_cvtts_ps_epu32(__m512 __A) {
|
|
return ((__m512i)__builtin_ia32_vcvttps2udqs512_round_mask(
|
|
(__v16sf)(__A), (__v16si)_mm512_undefined_epi32(), (__mmask16)-1,
|
|
_MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_mask_cvtts_ps_epu32(__m512i __W, __mmask16 __U, __m512 __A) {
|
|
return ((__m512i)__builtin_ia32_vcvttps2udqs512_round_mask(
|
|
(__v16sf)(__A), (__v16si)(__W), __U, _MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_maskz_cvtts_ps_epu32(__mmask16 __U, __m512 __A) {
|
|
return ((__m512i)__builtin_ia32_vcvttps2udqs512_round_mask(
|
|
(__v16sf)(__A), (__v16si)_mm512_setzero_si512(), __U,
|
|
_MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
#define _mm512_cvtts_roundps_epu32(__A, __R) \
|
|
((__m512i)__builtin_ia32_vcvttps2udqs512_round_mask( \
|
|
(__v16sf)(__m512)(__A), (__v16si)_mm512_undefined_epi32(), \
|
|
(__mmask16) - 1, (const int)(__R)))
|
|
|
|
#define _mm512_mask_cvtts_roundps_epu32(__W, __U, __A, __R) \
|
|
((__m512i)__builtin_ia32_vcvttps2udqs512_round_mask( \
|
|
(__v16sf)(__m512)(__A), (__v16si)(__m512i)(__W), (__mmask16)(__U), \
|
|
(const int)(__R)))
|
|
|
|
#define _mm512_maskz_cvtts_roundps_epu32(__U, __A, __R) \
|
|
((__m512i)__builtin_ia32_vcvttps2udqs512_round_mask( \
|
|
(__v16sf)(__m512)(__A), (__v16si)_mm512_setzero_si512(), \
|
|
(__mmask16)(__U), (const int)(__R)))
|
|
|
|
// 512 bit : float -> long
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS _mm512_cvtts_ps_epi64(__m256 __A) {
|
|
return ((__m512i)__builtin_ia32_vcvttps2qqs512_round_mask(
|
|
(__v8sf)__A, (__v8di)_mm512_undefined_epi32(), (__mmask8)-1,
|
|
_MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_mask_cvtts_ps_epi64(__m512i __W, __mmask8 __U, __m256 __A) {
|
|
return ((__m512i)__builtin_ia32_vcvttps2qqs512_round_mask(
|
|
(__v8sf)__A, (__v8di)__W, __U, _MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_maskz_cvtts_ps_epi64(__mmask8 __U, __m256 __A) {
|
|
return ((__m512i)__builtin_ia32_vcvttps2qqs512_round_mask(
|
|
(__v8sf)__A, (__v8di)_mm512_setzero_si512(), __U,
|
|
_MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
#define _mm512_cvtts_roundps_epi64(__A, __R) \
|
|
((__m512i)__builtin_ia32_vcvttps2qqs512_round_mask( \
|
|
(__v8sf)(__m256)(__A), (__v8di)_mm512_undefined_epi32(), (__mmask8) - 1, \
|
|
(const int)(__R)))
|
|
|
|
#define _mm512_mask_cvtts_roundps_epi64(__W, __U, __A, __R) \
|
|
((__m512i)__builtin_ia32_vcvttps2qqs512_round_mask( \
|
|
(__v8sf)(__m256)(__A), (__v8di)(__m512i)(__W), (__mmask8)(__U), \
|
|
(const int)(__R)))
|
|
|
|
#define _mm512_maskz_cvtts_roundps_epi64(__U, __A, __R) \
|
|
((__m512i)__builtin_ia32_vcvttps2qqs512_round_mask( \
|
|
(__v8sf)(__m256)(__A), (__v8di)_mm512_setzero_si512(), (__mmask8)(__U), \
|
|
(const int)(__R)))
|
|
|
|
// 512 bit : float -> ulong
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS _mm512_cvtts_ps_epu64(__m256 __A) {
|
|
return ((__m512i)__builtin_ia32_vcvttps2uqqs512_round_mask(
|
|
(__v8sf)__A, (__v8di)_mm512_undefined_epi32(), (__mmask8)-1,
|
|
_MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_mask_cvtts_ps_epu64(__m512i __W, __mmask8 __U, __m256 __A) {
|
|
return ((__m512i)__builtin_ia32_vcvttps2uqqs512_round_mask(
|
|
(__v8sf)__A, (__v8di)__W, __U, _MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_maskz_cvtts_ps_epu64(__mmask8 __U, __m256 __A) {
|
|
return ((__m512i)__builtin_ia32_vcvttps2uqqs512_round_mask(
|
|
(__v8sf)__A, (__v8di)_mm512_setzero_si512(), __U,
|
|
_MM_FROUND_CUR_DIRECTION));
|
|
}
|
|
|
|
#define _mm512_cvtts_roundps_epu64(__A, __R) \
|
|
((__m512i)__builtin_ia32_vcvttps2uqqs512_round_mask( \
|
|
(__v8sf)(__m256)(__A), (__v8di)_mm512_undefined_epi32(), (__mmask8) - 1, \
|
|
(const int)(__R)))
|
|
|
|
#define _mm512_mask_cvtts_roundps_epu64(__W, __U, __A, __R) \
|
|
((__m512i)__builtin_ia32_vcvttps2uqqs512_round_mask( \
|
|
(__v8sf)(__m256)(__A), (__v8di)(__m512i)(__W), (__mmask8)(__U), \
|
|
(const int)(__R)))
|
|
|
|
#define _mm512_maskz_cvtts_roundps_epu64(__U, __A, __R) \
|
|
((__m512i)__builtin_ia32_vcvttps2uqqs512_round_mask( \
|
|
(__v8sf)(__m256)(__A), (__v8di)_mm512_setzero_si512(), (__mmask8)(__U), \
|
|
(const int)(__R)))
|
|
|
|
#undef __DEFAULT_FN_ATTRS
|
|
#endif // __AVX10_2_512SATCVTDSINTRIN_H
|