llvm-project/clang/lib/Headers/vaesintrin.h

99 lines
3.2 KiB
C
Raw Normal View History

/*===------------------ vaesintrin.h - VAES intrinsics ---------------------===
*
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*
*===-----------------------------------------------------------------------===
*/
#ifndef __IMMINTRIN_H
#error "Never use <vaesintrin.h> directly; include <immintrin.h> instead."
#endif
#ifndef __VAESINTRIN_H
#define __VAESINTRIN_H
/* Default attributes for YMM forms. */
[Builtins][Attributes][X86] Tag all X86 builtins with their required vector width. Add a min_vector_width function attribute and tag all x86 instrinsics with it This is part of an ongoing attempt at making 512 bit vectors illegal in the X86 backend type legalizer due to CPU frequency penalties associated with wide vectors on Skylake Server CPUs. We want the loop vectorizer to be able to emit IR containing wide vectors as intermediate operations in vectorized code and allow these wide vectors to be legalized to 256 bits by the X86 backend even though we are targetting a CPU that supports 512 bit vectors. This is similar to what happens with an AVX2 CPU, the vectorizer can emit wide vectors and the backend will split them. We want this splitting behavior, but still be able to use new Skylake instructions that work on 256-bit vectors and support things like masking and gather/scatter. Of course if the user uses explicit vector code in their source code we need to not split those operations. Especially if they have used any of the 512-bit vector intrinsics from immintrin.h. And we need to make it so that merely using the intrinsics produces the expected code in order to be backwards compatible. To support this goal, this patch adds a new IR function attribute "min-legal-vector-width" that can indicate the need for a minimum vector width to be legal in the backend. We need to ensure this attribute is set to the largest vector width needed by any intrinsics from immintrin.h that the function uses. The inliner will be reponsible for merging this attribute when a function is inlined. We may also need a way to limit inlining in the future as well, but we can discuss that in the future. To make things more complicated, there are two different ways intrinsics are implemented in immintrin.h. Either as an always_inline function containing calls to builtins(can be target specific or target independent) or vector extension code. Or as a macro wrapper around a taget specific builtin. I believe I've removed all cases where the macro was around a target independent builtin. To support the always_inline function case this patch adds attribute((min_vector_width(128))) that can be used to tag these functions with their vector width. All x86 intrinsic functions that operate on vectors have been tagged with this attribute. To support the macro case, all x86 specific builtins have also been tagged with the vector width that they require. Use of any builtin with this property will implicitly increase the min_vector_width of the function that calls it. I've done this as a new property in the attribute string for the builtin rather than basing it on the type string so that we can opt into it on a per builtin basis and avoid any impact to target independent builtins. There will be future work to support vectors passed as function arguments and supporting inline assembly. And whatever else we can find that isn't covered by this patch. Special thanks to Chandler who suggested this direction and reviewed a preview version of this patch. And thanks to Eric Christopher who has had many conversations with me about this issue. Differential Revision: https://reviews.llvm.org/D48617 llvm-svn: 336583
2018-07-10 03:00:16 +08:00
#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("vaes"), __min_vector_width__(256)))
/* Default attributes for ZMM forms. */
[Builtins][Attributes][X86] Tag all X86 builtins with their required vector width. Add a min_vector_width function attribute and tag all x86 instrinsics with it This is part of an ongoing attempt at making 512 bit vectors illegal in the X86 backend type legalizer due to CPU frequency penalties associated with wide vectors on Skylake Server CPUs. We want the loop vectorizer to be able to emit IR containing wide vectors as intermediate operations in vectorized code and allow these wide vectors to be legalized to 256 bits by the X86 backend even though we are targetting a CPU that supports 512 bit vectors. This is similar to what happens with an AVX2 CPU, the vectorizer can emit wide vectors and the backend will split them. We want this splitting behavior, but still be able to use new Skylake instructions that work on 256-bit vectors and support things like masking and gather/scatter. Of course if the user uses explicit vector code in their source code we need to not split those operations. Especially if they have used any of the 512-bit vector intrinsics from immintrin.h. And we need to make it so that merely using the intrinsics produces the expected code in order to be backwards compatible. To support this goal, this patch adds a new IR function attribute "min-legal-vector-width" that can indicate the need for a minimum vector width to be legal in the backend. We need to ensure this attribute is set to the largest vector width needed by any intrinsics from immintrin.h that the function uses. The inliner will be reponsible for merging this attribute when a function is inlined. We may also need a way to limit inlining in the future as well, but we can discuss that in the future. To make things more complicated, there are two different ways intrinsics are implemented in immintrin.h. Either as an always_inline function containing calls to builtins(can be target specific or target independent) or vector extension code. Or as a macro wrapper around a taget specific builtin. I believe I've removed all cases where the macro was around a target independent builtin. To support the always_inline function case this patch adds attribute((min_vector_width(128))) that can be used to tag these functions with their vector width. All x86 intrinsic functions that operate on vectors have been tagged with this attribute. To support the macro case, all x86 specific builtins have also been tagged with the vector width that they require. Use of any builtin with this property will implicitly increase the min_vector_width of the function that calls it. I've done this as a new property in the attribute string for the builtin rather than basing it on the type string so that we can opt into it on a per builtin basis and avoid any impact to target independent builtins. There will be future work to support vectors passed as function arguments and supporting inline assembly. And whatever else we can find that isn't covered by this patch. Special thanks to Chandler who suggested this direction and reviewed a preview version of this patch. And thanks to Eric Christopher who has had many conversations with me about this issue. Differential Revision: https://reviews.llvm.org/D48617 llvm-svn: 336583
2018-07-10 03:00:16 +08:00
#define __DEFAULT_FN_ATTRS_F __attribute__((__always_inline__, __nodebug__, __target__("avx512f,vaes"), __min_vector_width__(512)))
static __inline__ __m256i __DEFAULT_FN_ATTRS
_mm256_aesenc_epi128(__m256i __A, __m256i __B)
{
return (__m256i) __builtin_ia32_aesenc256((__v4di) __A,
(__v4di) __B);
}
static __inline__ __m512i __DEFAULT_FN_ATTRS_F
_mm512_aesenc_epi128(__m512i __A, __m512i __B)
{
return (__m512i) __builtin_ia32_aesenc512((__v8di) __A,
(__v8di) __B);
}
static __inline__ __m256i __DEFAULT_FN_ATTRS
_mm256_aesdec_epi128(__m256i __A, __m256i __B)
{
return (__m256i) __builtin_ia32_aesdec256((__v4di) __A,
(__v4di) __B);
}
static __inline__ __m512i __DEFAULT_FN_ATTRS_F
_mm512_aesdec_epi128(__m512i __A, __m512i __B)
{
return (__m512i) __builtin_ia32_aesdec512((__v8di) __A,
(__v8di) __B);
}
static __inline__ __m256i __DEFAULT_FN_ATTRS
_mm256_aesenclast_epi128(__m256i __A, __m256i __B)
{
return (__m256i) __builtin_ia32_aesenclast256((__v4di) __A,
(__v4di) __B);
}
static __inline__ __m512i __DEFAULT_FN_ATTRS_F
_mm512_aesenclast_epi128(__m512i __A, __m512i __B)
{
return (__m512i) __builtin_ia32_aesenclast512((__v8di) __A,
(__v8di) __B);
}
static __inline__ __m256i __DEFAULT_FN_ATTRS
_mm256_aesdeclast_epi128(__m256i __A, __m256i __B)
{
return (__m256i) __builtin_ia32_aesdeclast256((__v4di) __A,
(__v4di) __B);
}
static __inline__ __m512i __DEFAULT_FN_ATTRS_F
_mm512_aesdeclast_epi128(__m512i __A, __m512i __B)
{
return (__m512i) __builtin_ia32_aesdeclast512((__v8di) __A,
(__v8di) __B);
}
#undef __DEFAULT_FN_ATTRS
#undef __DEFAULT_FN_ATTRS_F
#endif