maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AVX-512] Use scalar vfmsub/vfnmsub mask3 intrinsics instead of inverting the mask argument of a vfmadd intrinsic. 

Summary: Inverting the mask argument does not reflect the intended semantics of the intrinsic.

Reviewers: igorb, delena

Subscribers: cfe-commits

Differential Revision: https://reviews.llvm.org/D26019

llvm-svn: 286733
This commit is contained in:
Craig Topper 2016-11-12 23:24:34 +00:00
parent 79c6f7a0c5
commit 2c8f49e67b
3 changed files with 28 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
clang/include/clang/Basic/BuiltinsX86.def
View File

@ -1743,6 +1743,10 @@ TARGET_BUILTIN(__builtin_ia32_vfmaddss3_mask3, "V4fV4fV4fV4fUcIi", "", "avx512f"
TARGET_BUILTIN(__builtin_ia32_vfmaddsd3_mask, "V2dV2dV2dV2dUcIi", "", "avx512f")
TARGET_BUILTIN(__builtin_ia32_vfmaddsd3_maskz, "V2dV2dV2dV2dUcIi", "", "avx512f")
TARGET_BUILTIN(__builtin_ia32_vfmaddsd3_mask3, "V2dV2dV2dV2dUcIi", "", "avx512f")
TARGET_BUILTIN(__builtin_ia32_vfmsubsd3_mask3, "V2dV2dV2dV2dUcIi", "", "avx512f")
TARGET_BUILTIN(__builtin_ia32_vfmsubss3_mask3, "V4fV4fV4fV4fUcIi", "", "avx512f")
TARGET_BUILTIN(__builtin_ia32_vfnmsubsd3_mask3, "V2dV2dV2dV2dUcIi", "", "avx512f")
TARGET_BUILTIN(__builtin_ia32_vfnmsubss3_mask3, "V4fV4fV4fV4fUcIi", "", "avx512f")
TARGET_BUILTIN(__builtin_ia32_permvarhi512_mask, "V32sV32sV32sV32sUi","","avx512bw")
TARGET_BUILTIN(__builtin_ia32_permvardf512_mask, "V8dV8dV8LLiV8dUc","","avx512f")
TARGET_BUILTIN(__builtin_ia32_permvardi512_mask, "V8LLiV8LLiV8LLiV8LLiUc","","avx512f")

32
clang/lib/Headers/avx512fintrin.h
View File

@ -8470,17 +8470,17 @@ _mm_maskz_fmsub_ss (__mmask8 __U, __m128 __A, __m128 __B, __m128 __C)
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_mask3_fmsub_ss (__m128 __W, __m128 __X, __m128 __Y, __mmask8 __U)
{
return (__m128) __builtin_ia32_vfmaddss3_mask3 ((__v4sf) __W,
return (__m128) __builtin_ia32_vfmsubss3_mask3 ((__v4sf) __W,
(__v4sf) __X,
-(__v4sf) __Y,
(__v4sf) __Y,
(__mmask8) __U,
_MM_FROUND_CUR_DIRECTION);
}
#define _mm_mask3_fmsub_round_ss(W, X, Y, U, R) __extension__ ({\
(__m128)__builtin_ia32_vfmaddss3_mask3((__v4sf)(__m128)(W), \
(__m128)__builtin_ia32_vfmsubss3_mask3((__v4sf)(__m128)(W), \
(__v4sf)(__m128)(X), \
-(__v4sf)(__m128)(Y), (__mmask8)(U), \
(__v4sf)(__m128)(Y), (__mmask8)(U), \
(int)(R)); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
@ -8566,17 +8566,17 @@ _mm_maskz_fnmsub_ss (__mmask8 __U, __m128 __A, __m128 __B, __m128 __C)
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_mask3_fnmsub_ss (__m128 __W, __m128 __X, __m128 __Y, __mmask8 __U)
{
return (__m128) __builtin_ia32_vfmaddss3_mask3 (-(__v4sf) __W,
return (__m128) __builtin_ia32_vfnmsubss3_mask3 ((__v4sf) __W,
(__v4sf) __X,
-(__v4sf) __Y,
(__v4sf) __Y,
(__mmask8) __U,
_MM_FROUND_CUR_DIRECTION);
}
#define _mm_mask3_fnmsub_round_ss(W, X, Y, U, R) __extension__({\
(__m128)__builtin_ia32_vfmaddss3_mask3(-(__v4sf)(__m128)(W), \
(__m128)__builtin_ia32_vfnmsubss3_mask3((__v4sf)(__m128)(W), \
(__v4sf)(__m128)(X), \
-(__v4sf)(__m128)(Y), (__mmask8)(U), \
(__v4sf)(__m128)(Y), (__mmask8)(U), \
(int)(R)); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
@ -8662,17 +8662,17 @@ _mm_maskz_fmsub_sd (__mmask8 __U, __m128d __A, __m128d __B, __m128d __C)
static __inline__ __m128d __DEFAULT_FN_ATTRS
_mm_mask3_fmsub_sd (__m128d __W, __m128d __X, __m128d __Y, __mmask8 __U)
{
return (__m128d) __builtin_ia32_vfmaddsd3_mask3 ((__v2df) __W,
return (__m128d) __builtin_ia32_vfmsubsd3_mask3 ((__v2df) __W,
(__v2df) __X,
-(__v2df) __Y,
(__v2df) __Y,
(__mmask8) __U,
_MM_FROUND_CUR_DIRECTION);
}
#define _mm_mask3_fmsub_round_sd(W, X, Y, U, R) __extension__ ({\
(__m128d)__builtin_ia32_vfmaddsd3_mask3((__v2df)(__m128d)(W), \
(__m128d)__builtin_ia32_vfmsubsd3_mask3((__v2df)(__m128d)(W), \
(__v2df)(__m128d)(X), \
-(__v2df)(__m128d)(Y), \
(__v2df)(__m128d)(Y), \
(__mmask8)(U), (int)(R)); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
@ -8759,17 +8759,17 @@ _mm_maskz_fnmsub_sd (__mmask8 __U, __m128d __A, __m128d __B, __m128d __C)
static __inline__ __m128d __DEFAULT_FN_ATTRS
_mm_mask3_fnmsub_sd (__m128d __W, __m128d __X, __m128d __Y, __mmask8 __U)
{
return (__m128d) __builtin_ia32_vfmaddsd3_mask3 (-(__v2df) (__W),
return (__m128d) __builtin_ia32_vfnmsubsd3_mask3 ((__v2df) (__W),
(__v2df) __X,
-(__v2df) (__Y),
(__v2df) (__Y),
(__mmask8) __U,
_MM_FROUND_CUR_DIRECTION);
}
#define _mm_mask3_fnmsub_round_sd(W, X, Y, U, R) __extension__({\
(__m128d)__builtin_ia32_vfmaddsd3_mask3(-(__v2df)(__m128d)(W), \
(__m128d)__builtin_ia32_vfnmsubsd3_mask3((__v2df)(__m128d)(W), \
(__v2df)(__m128d)(X), \
-(__v2df)(__m128d)(Y), \
(__v2df)(__m128d)(Y), \
(__mmask8)(U), (int)(R)); })
#define _mm512_permutex_pd(X, C) __extension__ ({ \

16
clang/test/CodeGen/avx512f-builtins.c
View File

@ -5813,13 +5813,13 @@ __m128 test_mm_maskz_fmsub_round_ss(__mmask8 __U, __m128 __A, __m128 __B, __m128
__m128 test_mm_mask3_fmsub_ss(__m128 __W, __m128 __X, __m128 __Y, __mmask8 __U){
// CHECK-LABEL: @test_mm_mask3_fmsub_ss
// CHECK: @llvm.x86.avx512.mask3.vfmadd.ss
// CHECK: @llvm.x86.avx512.mask3.vfmsub.ss
return _mm_mask3_fmsub_ss(__W, __X, __Y, __U);
}
__m128 test_mm_mask3_fmsub_round_ss(__m128 __W, __m128 __X, __m128 __Y, __mmask8 __U){
// CHECK-LABEL: @test_mm_mask3_fmsub_round_ss
// CHECK: @llvm.x86.avx512.mask3.vfmadd.ss
// CHECK: @llvm.x86.avx512.mask3.vfmsub.ss
return _mm_mask3_fmsub_round_ss(__W, __X, __Y, __U, _MM_FROUND_CUR_DIRECTION);
}
@ -5885,13 +5885,13 @@ __m128 test_mm_maskz_fnmsub_round_ss(__mmask8 __U, __m128 __A, __m128 __B, __m12
__m128 test_mm_mask3_fnmsub_ss(__m128 __W, __m128 __X, __m128 __Y, __mmask8 __U){
// CHECK-LABEL: @test_mm_mask3_fnmsub_ss
// CHECK: @llvm.x86.avx512.mask3.vfmadd.ss
// CHECK: @llvm.x86.avx512.mask3.vfnmsub.ss
return _mm_mask3_fnmsub_ss(__W, __X, __Y, __U);
}
__m128 test_mm_mask3_fnmsub_round_ss(__m128 __W, __m128 __X, __m128 __Y, __mmask8 __U){
// CHECK-LABEL: @test_mm_mask3_fnmsub_round_ss
// CHECK: @llvm.x86.avx512.mask3.vfmadd.ss
// CHECK: @llvm.x86.avx512.mask3.vfnmsub.ss
return _mm_mask3_fnmsub_round_ss(__W, __X, __Y, __U, _MM_FROUND_CUR_DIRECTION);
}
@ -5957,13 +5957,13 @@ __m128d test_mm_maskz_fmsub_round_sd(__mmask8 __U, __m128d __A, __m128d __B, __m
__m128d test_mm_mask3_fmsub_sd(__m128d __W, __m128d __X, __m128d __Y, __mmask8 __U){
// CHECK-LABEL: @test_mm_mask3_fmsub_sd
// CHECK: @llvm.x86.avx512.mask3.vfmadd.sd
// CHECK: @llvm.x86.avx512.mask3.vfmsub.sd
return _mm_mask3_fmsub_sd(__W, __X, __Y, __U);
}
__m128d test_mm_mask3_fmsub_round_sd(__m128d __W, __m128d __X, __m128d __Y, __mmask8 __U){
// CHECK-LABEL: @test_mm_mask3_fmsub_round_sd
// CHECK: @llvm.x86.avx512.mask3.vfmadd.sd
// CHECK: @llvm.x86.avx512.mask3.vfmsub.sd
return _mm_mask3_fmsub_round_sd(__W, __X, __Y, __U, _MM_FROUND_CUR_DIRECTION);
}
@ -6029,13 +6029,13 @@ __m128d test_mm_maskz_fnmsub_round_sd(__mmask8 __U, __m128d __A, __m128d __B, __
__m128d test_mm_mask3_fnmsub_sd(__m128d __W, __m128d __X, __m128d __Y, __mmask8 __U){
// CHECK-LABEL: @test_mm_mask3_fnmsub_sd
// CHECK: @llvm.x86.avx512.mask3.vfmadd.sd
// CHECK: @llvm.x86.avx512.mask3.vfnmsub.sd
return _mm_mask3_fnmsub_sd(__W, __X, __Y, __U);
}
__m128d test_mm_mask3_fnmsub_round_sd(__m128d __W, __m128d __X, __m128d __Y, __mmask8 __U){
// CHECK-LABEL: @test_mm_mask3_fnmsub_round_sd
// CHECK: @llvm.x86.avx512.mask3.vfmadd.sd
// CHECK: @llvm.x86.avx512.mask3.vfnmsub.sd
return _mm_mask3_fnmsub_round_sd(__W, __X, __Y, __U, _MM_FROUND_CUR_DIRECTION);
}