summaryrefslogtreecommitdiffstats
path: root/lib/Headers/avx512fintrin.h
diff options
context:
space:
mode:
authorCraig Topper <craig.topper@gmail.com>2016-10-26 05:35:38 +0000
committerCraig Topper <craig.topper@gmail.com>2016-10-26 05:35:38 +0000
commit26c2965d0f8434b1b923c32f0f6f4d0ce998e6d2 (patch)
tree903a1d613e56ae1c2f0429ca7d628ac867942b75 /lib/Headers/avx512fintrin.h
parenta703dbcdce9b95fc4a6ae294b03a5a8707b16f4d (diff)
[AVX-512] Fix the operand order for all calls to __builtin_ia32_vfmaddss3_mask.
Summary: The preserved input should be the first argument and the vector inputs should be in the same order as the intrinsics it is used to implement. Reviewers: igorb, delena Subscribers: cfe-commits Differential Revision: https://reviews.llvm.org/D25902 git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@285175 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib/Headers/avx512fintrin.h')
-rw-r--r--lib/Headers/avx512fintrin.h80
1 files changed, 40 insertions, 40 deletions
diff --git a/lib/Headers/avx512fintrin.h b/lib/Headers/avx512fintrin.h
index f9b63e1258..be90b70848 100644
--- a/lib/Headers/avx512fintrin.h
+++ b/lib/Headers/avx512fintrin.h
@@ -8338,17 +8338,17 @@ __builtin_ia32_gatherdiv16sf ((__v8sf) __v1_old,\
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_mask_fmadd_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
{
- return (__m128) __builtin_ia32_vfmaddss3_mask ((__v4sf) __A,
+ return (__m128) __builtin_ia32_vfmaddss3_mask ((__v4sf) __W,
+ (__v4sf) __A,
(__v4sf) __B,
- (__v4sf) __W,
(__mmask8) __U,
_MM_FROUND_CUR_DIRECTION);
}
#define _mm_mask_fmadd_round_ss(W, U, A, B, R) __extension__({\
- (__m128)__builtin_ia32_vfmaddss3_mask((__v4sf)(__m128)(A), \
- (__v4sf)(__m128)(B), \
- (__v4sf)(__m128)(W), (__mmask8)(U), \
+ (__m128)__builtin_ia32_vfmaddss3_mask((__v4sf)(__m128)(W), \
+ (__v4sf)(__m128)(A), \
+ (__v4sf)(__m128)(B), (__mmask8)(U), \
(int)(R)); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
@@ -8386,17 +8386,17 @@ _mm_mask3_fmadd_ss (__m128 __W, __m128 __X, __m128 __Y, __mmask8 __U)
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_mask_fmsub_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
{
- return (__m128) __builtin_ia32_vfmaddss3_mask ((__v4sf) __A,
+ return (__m128) __builtin_ia32_vfmaddss3_mask ((__v4sf) __W,
+ (__v4sf) __A,
-(__v4sf) __B,
- (__v4sf) __W,
(__mmask8) __U,
_MM_FROUND_CUR_DIRECTION);
}
#define _mm_mask_fmsub_round_ss(W, U, A, B, R) __extension__ ({\
- (__m128)__builtin_ia32_vfmaddss3_mask((__v4sf)(__m128)(A), \
- -(__v4sf)(__m128)(B), \
- (__v4sf)(__m128)(W), (__mmask8)(U), \
+ (__m128)__builtin_ia32_vfmaddss3_mask((__v4sf)(__m128)(W), \
+ (__v4sf)(__m128)(A), \
+ (__v4sf)(__m128)(B), (__mmask8)(U), \
(int)(R)); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
@@ -8434,17 +8434,17 @@ _mm_mask3_fmsub_ss (__m128 __W, __m128 __X, __m128 __Y, __mmask8 __U)
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_mask_fnmadd_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
{
- return (__m128) __builtin_ia32_vfmaddss3_mask (-(__v4sf) __A,
+ return (__m128) __builtin_ia32_vfmaddss3_mask ((__v4sf) __W,
+ -(__v4sf) __A,
(__v4sf) __B,
- (__v4sf) __W,
(__mmask8) __U,
_MM_FROUND_CUR_DIRECTION);
}
#define _mm_mask_fnmadd_round_ss(W, U, A, B, R) __extension__ ({\
- (__m128)__builtin_ia32_vfmaddss3_mask(-(__v4sf)(__m128)(A), \
- (__v4sf)(__m128)(B), \
- (__v4sf)(__m128)(W), (__mmask8)(U), \
+ (__m128)__builtin_ia32_vfmaddss3_mask((__v4sf)(__m128)(W), \
+ -(__v4sf)(__m128)(A), \
+ (__v4sf)(__m128)(B), (__mmask8)(U), \
(int)(R)); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
@@ -8482,17 +8482,17 @@ _mm_mask3_fnmadd_ss (__m128 __W, __m128 __X, __m128 __Y, __mmask8 __U)
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_mask_fnmsub_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
{
- return (__m128) __builtin_ia32_vfmaddss3_mask (-(__v4sf) __A,
+ return (__m128) __builtin_ia32_vfmaddss3_mask ((__v4sf) __W,
+ -(__v4sf) __A,
-(__v4sf) __B,
- (__v4sf) __W,
(__mmask8) __U,
_MM_FROUND_CUR_DIRECTION);
}
#define _mm_mask_fnmsub_round_ss(W, U, A, B, R) __extension__ ({\
- (__m128)__builtin_ia32_vfmaddss3_mask(-(__v4sf)(__m128)(A), \
- -(__v4sf)(__m128)(B), \
- (__v4sf)(__m128)(W), (__mmask8)(U), \
+ (__m128)__builtin_ia32_vfmaddss3_mask((__v4sf)(__m128)(W), \
+ -(__v4sf)(__m128)(A), \
+ -(__v4sf)(__m128)(B), (__mmask8)(U), \
(int)(R)); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
@@ -8530,17 +8530,17 @@ _mm_mask3_fnmsub_ss (__m128 __W, __m128 __X, __m128 __Y, __mmask8 __U)
static __inline__ __m128d __DEFAULT_FN_ATTRS
_mm_mask_fmadd_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
{
- return (__m128d) __builtin_ia32_vfmaddsd3_mask ( (__v2df) __A,
+ return (__m128d) __builtin_ia32_vfmaddsd3_mask ( (__v2df) __W,
+ (__v2df) __A,
(__v2df) __B,
- (__v2df) __W,
(__mmask8) __U,
_MM_FROUND_CUR_DIRECTION);
}
#define _mm_mask_fmadd_round_sd(W, U, A, B, R) __extension__({\
- (__m128d)__builtin_ia32_vfmaddsd3_mask((__v2df)(__m128d)(A), \
- (__v2df)(__m128d)(B), \
- (__v2df)(__m128d)(W), (__mmask8)(U), \
+ (__m128d)__builtin_ia32_vfmaddsd3_mask((__v2df)(__m128d)(W), \
+ (__v2df)(__m128d)(A), \
+ (__v2df)(__m128d)(B), (__mmask8)(U), \
(int)(R)); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
@@ -8578,17 +8578,17 @@ _mm_mask3_fmadd_sd (__m128d __W, __m128d __X, __m128d __Y, __mmask8 __U)
static __inline__ __m128d __DEFAULT_FN_ATTRS
_mm_mask_fmsub_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
{
- return (__m128d) __builtin_ia32_vfmaddsd3_mask ( (__v2df) __A,
+ return (__m128d) __builtin_ia32_vfmaddsd3_mask ( (__v2df) __W,
+ (__v2df) __A,
-(__v2df) __B,
- (__v2df) __W,
(__mmask8) __U,
_MM_FROUND_CUR_DIRECTION);
}
#define _mm_mask_fmsub_round_sd(W, U, A, B, R) __extension__ ({\
- (__m128d)__builtin_ia32_vfmaddsd3_mask((__v2df)(__m128d)(A), \
- -(__v2df)(__m128d)(B), \
- (__v2df)(__m128d)(W), (__mmask8)(U), \
+ (__m128d)__builtin_ia32_vfmaddsd3_mask((__v2df)(__m128d)(W), \
+ (__v2df)(__m128d)(A), \
+ -(__v2df)(__m128d)(B), (__mmask8)(U), \
(int)(R)); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
@@ -8626,17 +8626,17 @@ _mm_mask3_fmsub_sd (__m128d __W, __m128d __X, __m128d __Y, __mmask8 __U)
static __inline__ __m128d __DEFAULT_FN_ATTRS
_mm_mask_fnmadd_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
{
- return (__m128d) __builtin_ia32_vfmaddsd3_mask ( -(__v2df) __A,
+ return (__m128d) __builtin_ia32_vfmaddsd3_mask ( (__v2df) __W,
+ -(__v2df) __A,
(__v2df) __B,
- (__v2df) __W,
(__mmask8) __U,
_MM_FROUND_CUR_DIRECTION);
}
#define _mm_mask_fnmadd_round_sd(W, U, A, B, R) __extension__ ({\
- (__m128d)__builtin_ia32_vfmaddsd3_mask(-(__v2df)(__m128d)(A), \
- (__v2df)(__m128d)(B), \
- (__v2df)(__m128d)(W), (__mmask8)(U), \
+ (__m128d)__builtin_ia32_vfmaddsd3_mask((__v2df)(__m128d)(W), \
+ -(__v2df)(__m128d)(A), \
+ (__v2df)(__m128d)(B), (__mmask8)(U), \
(int)(R)); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
@@ -8674,17 +8674,17 @@ _mm_mask3_fnmadd_sd (__m128d __W, __m128d __X, __m128d __Y, __mmask8 __U)
static __inline__ __m128d __DEFAULT_FN_ATTRS
_mm_mask_fnmsub_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
{
- return (__m128d) __builtin_ia32_vfmaddsd3_mask ( -(__v2df) __A,
+ return (__m128d) __builtin_ia32_vfmaddsd3_mask ( (__v2df) __W,
+ -(__v2df) __A,
-(__v2df) __B,
- (__v2df) __W,
(__mmask8) __U,
_MM_FROUND_CUR_DIRECTION);
}
#define _mm_mask_fnmsub_round_sd(W, U, A, B, R) __extension__ ({\
- (__m128d)__builtin_ia32_vfmaddsd3_mask(-(__v2df)(__m128d)(A), \
- -(__v2df)(__m128d)(B), \
- (__v2df)(__m128d)(W), (__mmask8)(U), \
+ (__m128d)__builtin_ia32_vfmaddsd3_mask((__v2df)(__m128d)(W), \
+ -(__v2df)(__m128d)(A), \
+ -(__v2df)(__m128d)(B), (__mmask8)(U), \
(int)(R)); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
generated by cgit v1.2.3 (git 2.25.1) at 2024-06-16 23:10:55 +0000