diff mbox

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

Message ID 1466097500-35271-1-git-send-email-james.greenhalgh@arm.com
State New
Headers show

Commit Message

James Greenhalgh June 16, 2016, 5:18 p.m. UTC 
Hi,

As subject, config/arm/arm_neon.h currently uses __FAST_MATH, but:

  $ gcc -E -dM - -ffast-math < /dev/null | grep FAST_MATH
  #define __FAST_MATH__ 1

It should be spelled as __FAST_MATH__.

I've made that change, and confirmed that it causes the preprocessor to
do what was intended for these intrinsics under -ffast-math.

Currently bootstrapped on arm-none-linux-gnueabihf with no issues.

This could also be backported to release branches. I think Ramana's patch
went in for GCC 5.0, so backports to gcc_5_branch and gcc_6_branch would
be feasible.

Thanks,
James

---
2016-06-16  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.

Comments

Ramana Radhakrishnan June 17, 2016, 8:25 a.m. UTC | #1 
On Thu, Jun 16, 2016 at 6:18 PM, James Greenhalgh
<james.greenhalgh@arm.com> wrote:
>
> Hi,
>
> As subject, config/arm/arm_neon.h currently uses __FAST_MATH, but:
>
>   $ gcc -E -dM - -ffast-math < /dev/null | grep FAST_MATH
>   #define __FAST_MATH__ 1
>
> It should be spelled as __FAST_MATH__.
>
> I've made that change, and confirmed that it causes the preprocessor to
> do what was intended for these intrinsics under -ffast-math.
>
> Currently bootstrapped on arm-none-linux-gnueabihf with no issues.

Ok, thanks for finding this - I'm not sure how that got messed up and
given its so far back I don't have any records left.

>
> This could also be backported to release branches. I think Ramana's patch
> went in for GCC 5.0, so backports to gcc_5_branch and gcc_6_branch would
> be feasible.
>

It's not a regression fix , so lets just keep this on trunk.

Ramana

> Thanks,
> James
>
> ---
> 2016-06-16  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.
>
diff mbox

Patch

diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h
index 7997cb4..32ee06c 100644
--- a/gcc/config/arm/arm_neon.h
+++ b/gcc/config/arm/arm_neon.h
@@ -530,7 +530,7 @@  vadd_s32 (int32x2_t __a, int32x2_t __b)
 __extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
 vadd_f32 (float32x2_t __a, float32x2_t __b)
 {
-#ifdef __FAST_MATH
+#ifdef __FAST_MATH__
   return __a + __b;
 #else
   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__))
 vaddq_f32 (float32x4_t __a, float32x4_t __b)
 {
-#ifdef __FAST_MATH
+#ifdef __FAST_MATH__
   return __a + __b;
 #else
   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__))
 vmul_f32 (float32x2_t __a, float32x2_t __b)
 {
-#ifdef __FAST_MATH
+#ifdef __FAST_MATH__
   return __a * __b;
 #else
   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__))
 vmulq_f32 (float32x4_t __a, float32x4_t __b)
 {
-#ifdef __FAST_MATH
+#ifdef __FAST_MATH__
   return __a * __b;
 #else
   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__))
 vsub_f32 (float32x2_t __a, float32x2_t __b)
 {
-#ifdef __FAST_MATH
+#ifdef __FAST_MATH__
   return __a - __b;
 #else
   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__))
 vsubq_f32 (float32x4_t __a, float32x4_t __b)
 {
-#ifdef __FAST_MATH
+#ifdef __FAST_MATH__
   return __a - __b;
 #else
   return (float32x4_t) __builtin_neon_vsubv4sf (__a, __b);