git
/
gcc
mirror of git://gcc.gnu.org/git/gcc.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[Patch ARM arm_neon.h] s/__FAST_MATH/__FAST_MATH__/g 

gcc/

	* config/arm/arm_neon.h (vadd_f32): replace __FAST_MATH with
	__FAST_MATH__.
	(vaddq_f32): Likewise.
	(vmul_f32): Likewise.
	(vmulq_f32): Likewise.
	(vsub_f32): Likewise.
	(vsubq_f32): Likewise.

From-SVN: r237553
This commit is contained in:
James Greenhalgh 2016-06-17 10:28:34 +00:00 committed by James Greenhalgh
parent d3ee260a28
commit 6ffccb58d6
2 changed files with 16 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
gcc/ChangeLog
View File

@ -1,3 +1,13 @@
2016-06-17 James Greenhalgh <james.greenhalgh@arm.com>
* config/arm/arm_neon.h (vadd_f32): replace __FAST_MATH with
__FAST_MATH__.
(vaddq_f32): Likewise.
(vmul_f32): Likewise.
(vmulq_f32): Likewise.
(vsub_f32): Likewise.
(vsubq_f32): Likewise.
2016-06-17 Bin Cheng <bin.cheng@arm.com> 2016-06-17 Bin Cheng <bin.cheng@arm.com>
PR tree-optimization/71347 PR tree-optimization/71347

12
gcc/config/arm/arm_neon.h
View File

@ -530,7 +530,7 @@ vadd_s32 (int32x2_t __a, int32x2_t __b)
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) __extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vadd_f32 (float32x2_t __a, float32x2_t __b) vadd_f32 (float32x2_t __a, float32x2_t __b)
{ {
#ifdef __FAST_MATH #ifdef __FAST_MATH__
return __a + __b; return __a + __b;
#else #else
return (float32x2_t) __builtin_neon_vaddv2sf (__a, __b); return (float32x2_t) __builtin_neon_vaddv2sf (__a, __b);
@ -594,7 +594,7 @@ vaddq_s64 (int64x2_t __a, int64x2_t __b)
__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) __extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vaddq_f32 (float32x4_t __a, float32x4_t __b) vaddq_f32 (float32x4_t __a, float32x4_t __b)
{ {
#ifdef __FAST_MATH #ifdef __FAST_MATH__
return __a + __b; return __a + __b;
#else #else
return (float32x4_t) __builtin_neon_vaddv4sf (__a, __b); return (float32x4_t) __builtin_neon_vaddv4sf (__a, __b);
@ -1030,7 +1030,7 @@ vmul_s32 (int32x2_t __a, int32x2_t __b)
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) __extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmul_f32 (float32x2_t __a, float32x2_t __b) vmul_f32 (float32x2_t __a, float32x2_t __b)
{ {
#ifdef __FAST_MATH #ifdef __FAST_MATH__
return __a * __b; return __a * __b;
#else #else
return (float32x2_t) __builtin_neon_vmulfv2sf (__a, __b); return (float32x2_t) __builtin_neon_vmulfv2sf (__a, __b);
@ -1077,7 +1077,7 @@ vmulq_s32 (int32x4_t __a, int32x4_t __b)
__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) __extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmulq_f32 (float32x4_t __a, float32x4_t __b) vmulq_f32 (float32x4_t __a, float32x4_t __b)
{ {
#ifdef __FAST_MATH #ifdef __FAST_MATH__
return __a * __b; return __a * __b;
#else #else
return (float32x4_t) __builtin_neon_vmulfv4sf (__a, __b); return (float32x4_t) __builtin_neon_vmulfv4sf (__a, __b);
@ -1678,7 +1678,7 @@ vsub_s32 (int32x2_t __a, int32x2_t __b)
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) __extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vsub_f32 (float32x2_t __a, float32x2_t __b) vsub_f32 (float32x2_t __a, float32x2_t __b)
{ {
#ifdef __FAST_MATH #ifdef __FAST_MATH__
return __a - __b; return __a - __b;
#else #else
return (float32x2_t) __builtin_neon_vsubv2sf (__a, __b); return (float32x2_t) __builtin_neon_vsubv2sf (__a, __b);
@ -1742,7 +1742,7 @@ vsubq_s64 (int64x2_t __a, int64x2_t __b)
__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) __extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vsubq_f32 (float32x4_t __a, float32x4_t __b) vsubq_f32 (float32x4_t __a, float32x4_t __b)
{ {
#ifdef __FAST_MATH #ifdef __FAST_MATH__
return __a - __b; return __a - __b;
#else #else
return (float32x4_t) __builtin_neon_vsubv4sf (__a, __b); return (float32x4_t) __builtin_neon_vsubv4sf (__a, __b);