24194090e1
This is an alternative of D157485 and a pre-feature to support AVX10. AVX10 Architecture Specification: https://cdrdv2.intel.com/v1/dl/getContent/784267 AVX10 Technical Paper: https://cdrdv2.intel.com/v1/dl/getContent/784343 RFC: https://discourse.llvm.org/t/rfc-design-for-avx10-feature-support/72661 Based on the feedbacks from LLVM and GCC community, we have agreed to start from supporting `-m[no-]evex512` on existing AVX512 features. The option `-mno-evex512` can be used with `-mavx512xxx` to build binaries that can run on both legacy AVX512 targets and AVX10-256. There're still arguments about what's the expected behavior when this option as well as `-mavx512xxx` used together with `-mavx10.1-256`. We decided to defer the support of `-mavx10.1` after we made consensus. Or furthermore, we start from supporting AVX10.2 and not providing any AVX10.1 options. Reviewed By: RKSimon, skan Differential Revision: https://reviews.llvm.org/D159250
107 lines
3.8 KiB
C
107 lines
3.8 KiB
C
/*===------------- avx512vbmiintrin.h - VBMI 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 <avx512vbmiintrin.h> directly; include <immintrin.h> instead."
|
|
#endif
|
|
|
|
#ifndef __VBMIINTRIN_H
|
|
#define __VBMIINTRIN_H
|
|
|
|
/* Define the default attributes for the functions in this file. */
|
|
#define __DEFAULT_FN_ATTRS \
|
|
__attribute__((__always_inline__, __nodebug__, \
|
|
__target__("avx512vbmi,evex512"), __min_vector_width__(512)))
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_permutex2var_epi8(__m512i __A, __m512i __I, __m512i __B)
|
|
{
|
|
return (__m512i)__builtin_ia32_vpermi2varqi512((__v64qi)__A, (__v64qi)__I,
|
|
(__v64qi) __B);
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_mask_permutex2var_epi8(__m512i __A, __mmask64 __U, __m512i __I,
|
|
__m512i __B)
|
|
{
|
|
return (__m512i)__builtin_ia32_selectb_512(__U,
|
|
(__v64qi)_mm512_permutex2var_epi8(__A, __I, __B),
|
|
(__v64qi)__A);
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_mask2_permutex2var_epi8(__m512i __A, __m512i __I, __mmask64 __U,
|
|
__m512i __B)
|
|
{
|
|
return (__m512i)__builtin_ia32_selectb_512(__U,
|
|
(__v64qi)_mm512_permutex2var_epi8(__A, __I, __B),
|
|
(__v64qi)__I);
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_maskz_permutex2var_epi8(__mmask64 __U, __m512i __A, __m512i __I,
|
|
__m512i __B)
|
|
{
|
|
return (__m512i)__builtin_ia32_selectb_512(__U,
|
|
(__v64qi)_mm512_permutex2var_epi8(__A, __I, __B),
|
|
(__v64qi)_mm512_setzero_si512());
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_permutexvar_epi8 (__m512i __A, __m512i __B)
|
|
{
|
|
return (__m512i)__builtin_ia32_permvarqi512((__v64qi) __B, (__v64qi) __A);
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_maskz_permutexvar_epi8 (__mmask64 __M, __m512i __A,
|
|
__m512i __B)
|
|
{
|
|
return (__m512i)__builtin_ia32_selectb_512((__mmask64)__M,
|
|
(__v64qi)_mm512_permutexvar_epi8(__A, __B),
|
|
(__v64qi)_mm512_setzero_si512());
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_mask_permutexvar_epi8 (__m512i __W, __mmask64 __M, __m512i __A,
|
|
__m512i __B)
|
|
{
|
|
return (__m512i)__builtin_ia32_selectb_512((__mmask64)__M,
|
|
(__v64qi)_mm512_permutexvar_epi8(__A, __B),
|
|
(__v64qi)__W);
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_multishift_epi64_epi8(__m512i __X, __m512i __Y)
|
|
{
|
|
return (__m512i)__builtin_ia32_vpmultishiftqb512((__v64qi)__X, (__v64qi) __Y);
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_mask_multishift_epi64_epi8(__m512i __W, __mmask64 __M, __m512i __X,
|
|
__m512i __Y)
|
|
{
|
|
return (__m512i)__builtin_ia32_selectb_512((__mmask64)__M,
|
|
(__v64qi)_mm512_multishift_epi64_epi8(__X, __Y),
|
|
(__v64qi)__W);
|
|
}
|
|
|
|
static __inline__ __m512i __DEFAULT_FN_ATTRS
|
|
_mm512_maskz_multishift_epi64_epi8(__mmask64 __M, __m512i __X, __m512i __Y)
|
|
{
|
|
return (__m512i)__builtin_ia32_selectb_512((__mmask64)__M,
|
|
(__v64qi)_mm512_multishift_epi64_epi8(__X, __Y),
|
|
(__v64qi)_mm512_setzero_si512());
|
|
}
|
|
|
|
|
|
#undef __DEFAULT_FN_ATTRS
|
|
|
|
#endif
|