Skip to content
Snippets Groups Projects
Commit 66cb2288 authored by Craig Topper's avatar Craig Topper
Browse files

[X86] Rename the VEX scalar fma builtins to end with a '3' to match gcc

I think we need to use different builtins for the FMA4 instructions since those instructions zero the upper bits and FMA3 instructions pass the bits through.

So this moves the existing builtins to be the FMA3 versions. New versions will be added for FMA4.

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@317766 91177308-0d34-0410-b5e6-96231b3b80d8
parent 55982462
No related branches found
No related tags found
No related merge requests found
......@@ -682,20 +682,20 @@ TARGET_BUILTIN(__builtin_ia32_sha256msg2, "V4iV4iV4i", "", "sha")
// FMA
TARGET_BUILTIN(__builtin_ia32_vfmaddps, "V4fV4fV4fV4f", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfmaddpd, "V2dV2dV2dV2d", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfmaddss, "V4fV4fV4fV4f", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfmaddsd, "V2dV2dV2dV2d", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfmaddss3, "V4fV4fV4fV4f", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfmaddsd3, "V2dV2dV2dV2d", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfmsubps, "V4fV4fV4fV4f", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfmsubpd, "V2dV2dV2dV2d", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfmsubss, "V4fV4fV4fV4f", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfmsubsd, "V2dV2dV2dV2d", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfmsubss3, "V4fV4fV4fV4f", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfmsubsd3, "V2dV2dV2dV2d", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfnmaddps, "V4fV4fV4fV4f", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfnmaddpd, "V2dV2dV2dV2d", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfnmaddss, "V4fV4fV4fV4f", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfnmaddsd, "V2dV2dV2dV2d", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfnmaddss3, "V4fV4fV4fV4f", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfnmaddsd3, "V2dV2dV2dV2d", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfnmsubps, "V4fV4fV4fV4f", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfnmsubpd, "V2dV2dV2dV2d", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfnmsubss, "V4fV4fV4fV4f", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfnmsubsd, "V2dV2dV2dV2d", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfnmsubss3, "V4fV4fV4fV4f", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfnmsubsd3, "V2dV2dV2dV2d", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfmaddsubps, "V4fV4fV4fV4f", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfmaddsubpd, "V2dV2dV2dV2d", "", "fma|fma4")
TARGET_BUILTIN(__builtin_ia32_vfmsubaddps, "V4fV4fV4fV4f", "", "fma|fma4")
......
......@@ -48,13 +48,13 @@ _mm_macc_pd(__m128d __A, __m128d __B, __m128d __C)
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_macc_ss(__m128 __A, __m128 __B, __m128 __C)
{
return (__m128)__builtin_ia32_vfmaddss((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
return (__m128)__builtin_ia32_vfmaddss3((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
}
static __inline__ __m128d __DEFAULT_FN_ATTRS
_mm_macc_sd(__m128d __A, __m128d __B, __m128d __C)
{
return (__m128d)__builtin_ia32_vfmaddsd((__v2df)__A, (__v2df)__B, (__v2df)__C);
return (__m128d)__builtin_ia32_vfmaddsd3((__v2df)__A, (__v2df)__B, (__v2df)__C);
}
static __inline__ __m128 __DEFAULT_FN_ATTRS
......@@ -72,13 +72,13 @@ _mm_msub_pd(__m128d __A, __m128d __B, __m128d __C)
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_msub_ss(__m128 __A, __m128 __B, __m128 __C)
{
return (__m128)__builtin_ia32_vfmsubss((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
return (__m128)__builtin_ia32_vfmsubss3((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
}
static __inline__ __m128d __DEFAULT_FN_ATTRS
_mm_msub_sd(__m128d __A, __m128d __B, __m128d __C)
{
return (__m128d)__builtin_ia32_vfmsubsd((__v2df)__A, (__v2df)__B, (__v2df)__C);
return (__m128d)__builtin_ia32_vfmsubsd3((__v2df)__A, (__v2df)__B, (__v2df)__C);
}
static __inline__ __m128 __DEFAULT_FN_ATTRS
......@@ -96,13 +96,13 @@ _mm_nmacc_pd(__m128d __A, __m128d __B, __m128d __C)
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_nmacc_ss(__m128 __A, __m128 __B, __m128 __C)
{
return (__m128)__builtin_ia32_vfnmaddss((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
return (__m128)__builtin_ia32_vfnmaddss3((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
}
static __inline__ __m128d __DEFAULT_FN_ATTRS
_mm_nmacc_sd(__m128d __A, __m128d __B, __m128d __C)
{
return (__m128d)__builtin_ia32_vfnmaddsd((__v2df)__A, (__v2df)__B, (__v2df)__C);
return (__m128d)__builtin_ia32_vfnmaddsd3((__v2df)__A, (__v2df)__B, (__v2df)__C);
}
static __inline__ __m128 __DEFAULT_FN_ATTRS
......@@ -120,13 +120,13 @@ _mm_nmsub_pd(__m128d __A, __m128d __B, __m128d __C)
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_nmsub_ss(__m128 __A, __m128 __B, __m128 __C)
{
return (__m128)__builtin_ia32_vfnmsubss((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
return (__m128)__builtin_ia32_vfnmsubss3((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
}
static __inline__ __m128d __DEFAULT_FN_ATTRS
_mm_nmsub_sd(__m128d __A, __m128d __B, __m128d __C)
{
return (__m128d)__builtin_ia32_vfnmsubsd((__v2df)__A, (__v2df)__B, (__v2df)__C);
return (__m128d)__builtin_ia32_vfnmsubsd3((__v2df)__A, (__v2df)__B, (__v2df)__C);
}
static __inline__ __m128 __DEFAULT_FN_ATTRS
......
......@@ -46,13 +46,13 @@ _mm_fmadd_pd(__m128d __A, __m128d __B, __m128d __C)
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_fmadd_ss(__m128 __A, __m128 __B, __m128 __C)
{
return (__m128)__builtin_ia32_vfmaddss((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
return (__m128)__builtin_ia32_vfmaddss3((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
}
static __inline__ __m128d __DEFAULT_FN_ATTRS
_mm_fmadd_sd(__m128d __A, __m128d __B, __m128d __C)
{
return (__m128d)__builtin_ia32_vfmaddsd((__v2df)__A, (__v2df)__B, (__v2df)__C);
return (__m128d)__builtin_ia32_vfmaddsd3((__v2df)__A, (__v2df)__B, (__v2df)__C);
}
static __inline__ __m128 __DEFAULT_FN_ATTRS
......@@ -70,13 +70,13 @@ _mm_fmsub_pd(__m128d __A, __m128d __B, __m128d __C)
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_fmsub_ss(__m128 __A, __m128 __B, __m128 __C)
{
return (__m128)__builtin_ia32_vfmsubss((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
return (__m128)__builtin_ia32_vfmsubss3((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
}
static __inline__ __m128d __DEFAULT_FN_ATTRS
_mm_fmsub_sd(__m128d __A, __m128d __B, __m128d __C)
{
return (__m128d)__builtin_ia32_vfmsubsd((__v2df)__A, (__v2df)__B, (__v2df)__C);
return (__m128d)__builtin_ia32_vfmsubsd3((__v2df)__A, (__v2df)__B, (__v2df)__C);
}
static __inline__ __m128 __DEFAULT_FN_ATTRS
......@@ -94,13 +94,13 @@ _mm_fnmadd_pd(__m128d __A, __m128d __B, __m128d __C)
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_fnmadd_ss(__m128 __A, __m128 __B, __m128 __C)
{
return (__m128)__builtin_ia32_vfnmaddss((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
return (__m128)__builtin_ia32_vfnmaddss3((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
}
static __inline__ __m128d __DEFAULT_FN_ATTRS
_mm_fnmadd_sd(__m128d __A, __m128d __B, __m128d __C)
{
return (__m128d)__builtin_ia32_vfnmaddsd((__v2df)__A, (__v2df)__B, (__v2df)__C);
return (__m128d)__builtin_ia32_vfnmaddsd3((__v2df)__A, (__v2df)__B, (__v2df)__C);
}
static __inline__ __m128 __DEFAULT_FN_ATTRS
......@@ -118,13 +118,13 @@ _mm_fnmsub_pd(__m128d __A, __m128d __B, __m128d __C)
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_fnmsub_ss(__m128 __A, __m128 __B, __m128 __C)
{
return (__m128)__builtin_ia32_vfnmsubss((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
return (__m128)__builtin_ia32_vfnmsubss3((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
}
static __inline__ __m128d __DEFAULT_FN_ATTRS
_mm_fnmsub_sd(__m128d __A, __m128d __B, __m128d __C)
{
return (__m128d)__builtin_ia32_vfnmsubsd((__v2df)__A, (__v2df)__B, (__v2df)__C);
return (__m128d)__builtin_ia32_vfnmsubsd3((__v2df)__A, (__v2df)__B, (__v2df)__C);
}
static __inline__ __m128 __DEFAULT_FN_ATTRS
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment