Patchwork [AArch64] Rewrite vca<ge, gt, le, lt> Neon patterns in C.

login
register
mail settings
Submitter James Greenhalgh
Date April 30, 2013, 3:13 p.m.
Message ID <1367334790-23048-1-git-send-email-james.greenhalgh@arm.com>
Download mbox | patch
Permalink /patch/240642/
State New
Headers show

Comments

James Greenhalgh - April 30, 2013, 3:13 p.m.
Hi,

This patch renames the vac<ge, gt> neon intrinsics to vca<ge, gt>
as required by the newest version of the neon intrinsics spec.

While we are there, we also update all the vca* intrinsics to
a C implimentation.

Regression tested on aarch64-none-elf with no regressions.

OK?

Thanks,
James

---
gcc/

2013-04-30  James Greenhalgh  <james.greenhalgh@arm.com>

	* config/aarch64/arm_neon.h
	(vac<ge, gt><sd>_f<32, 64>): Rename to...
	(vca<ge, gt><sd>_f<32, 64>): ...this, reimpliment in C.
	(vca<ge, gt, lt, le><q>_f<32, 64>): Reimpliment in C.
Marcus Shawcroft - April 30, 2013, 5:23 p.m.
OK
/Marcus

On 30 April 2013 16:13, James Greenhalgh <james.greenhalgh@arm.com> wrote:
>
> Hi,
>
> This patch renames the vac<ge, gt> neon intrinsics to vca<ge, gt>
> as required by the newest version of the neon intrinsics spec.
>
> While we are there, we also update all the vca* intrinsics to
> a C implimentation.
>
> Regression tested on aarch64-none-elf with no regressions.
>
> OK?
>
> Thanks,
> James
>
> ---
> gcc/
>
> 2013-04-30  James Greenhalgh  <james.greenhalgh@arm.com>
>
>         * config/aarch64/arm_neon.h
>         (vac<ge, gt><sd>_f<32, 64>): Rename to...
>         (vca<ge, gt><sd>_f<32, 64>): ...this, reimpliment in C.
>         (vca<ge, gt, lt, le><q>_f<32, 64>): Reimpliment in C.

Patch

diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index d822130..5f1ab11 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -4545,50 +4545,6 @@  vabsq_s64 (int64x2_t a)
   return result;
 }
 
-__extension__ static __inline float64_t __attribute__ ((__always_inline__))
-vacged_f64 (float64_t a, float64_t b)
-{
-  float64_t result;
-  __asm__ ("facge %d0,%d1,%d2"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline float32_t __attribute__ ((__always_inline__))
-vacges_f32 (float32_t a, float32_t b)
-{
-  float32_t result;
-  __asm__ ("facge %s0,%s1,%s2"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline float64_t __attribute__ ((__always_inline__))
-vacgtd_f64 (float64_t a, float64_t b)
-{
-  float64_t result;
-  __asm__ ("facgt %d0,%d1,%d2"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline float32_t __attribute__ ((__always_inline__))
-vacgts_f32 (float32_t a, float32_t b)
-{
-  float32_t result;
-  __asm__ ("facgt %s0,%s1,%s2"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
 __extension__ static __inline int16_t __attribute__ ((__always_inline__))
 vaddlv_s8 (int8x8_t a)
 {
@@ -5062,138 +5018,6 @@  vbslq_u64 (uint64x2_t a, uint64x2_t b, uint64x2_t c)
   return result;
 }
 
-__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
-vcage_f32 (float32x2_t a, float32x2_t b)
-{
-  uint32x2_t result;
-  __asm__ ("facge %0.2s, %1.2s, %2.2s"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
-vcageq_f32 (float32x4_t a, float32x4_t b)
-{
-  uint32x4_t result;
-  __asm__ ("facge %0.4s, %1.4s, %2.4s"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
-vcageq_f64 (float64x2_t a, float64x2_t b)
-{
-  uint64x2_t result;
-  __asm__ ("facge %0.2d, %1.2d, %2.2d"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
-vcagt_f32 (float32x2_t a, float32x2_t b)
-{
-  uint32x2_t result;
-  __asm__ ("facgt %0.2s, %1.2s, %2.2s"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
-vcagtq_f32 (float32x4_t a, float32x4_t b)
-{
-  uint32x4_t result;
-  __asm__ ("facgt %0.4s, %1.4s, %2.4s"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
-vcagtq_f64 (float64x2_t a, float64x2_t b)
-{
-  uint64x2_t result;
-  __asm__ ("facgt %0.2d, %1.2d, %2.2d"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
-vcale_f32 (float32x2_t a, float32x2_t b)
-{
-  uint32x2_t result;
-  __asm__ ("facge %0.2s, %2.2s, %1.2s"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
-vcaleq_f32 (float32x4_t a, float32x4_t b)
-{
-  uint32x4_t result;
-  __asm__ ("facge %0.4s, %2.4s, %1.4s"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
-vcaleq_f64 (float64x2_t a, float64x2_t b)
-{
-  uint64x2_t result;
-  __asm__ ("facge %0.2d, %2.2d, %1.2d"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
-vcalt_f32 (float32x2_t a, float32x2_t b)
-{
-  uint32x2_t result;
-  __asm__ ("facgt %0.2s, %2.2s, %1.2s"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
-vcaltq_f32 (float32x4_t a, float32x4_t b)
-{
-  uint32x4_t result;
-  __asm__ ("facgt %0.4s, %2.4s, %1.4s"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
-vcaltq_f64 (float64x2_t a, float64x2_t b)
-{
-  uint64x2_t result;
-  __asm__ ("facgt %0.2d, %2.2d, %1.2d"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
 __extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
 vcls_s8 (int8x8_t a)
 {
@@ -18584,6 +18408,110 @@  vaddvq_f64 (float64x2_t __a)
   return vgetq_lane_f64 (t, 0);
 }
 
+/* vcage  */
+
+__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
+vcages_f32 (float32_t __a, float32_t __b)
+{
+  return __builtin_fabsf (__a) >= __builtin_fabsf (__b) ? -1 : 0;
+}
+
+__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
+vcage_f32 (float32x2_t __a, float32x2_t __b)
+{
+  return vabs_f32 (__a) >= vabs_f32 (__b);
+}
+
+__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
+vcageq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return vabsq_f32 (__a) >= vabsq_f32 (__b);
+}
+
+__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
+vcaged_f64 (float64_t __a, float64_t __b)
+{
+  return __builtin_fabs (__a) >= __builtin_fabs (__b) ? -1 : 0;
+}
+
+__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
+vcageq_f64 (float64x2_t __a, float64x2_t __b)
+{
+  return vabsq_f64 (__a) >= vabsq_f64 (__b);
+}
+
+/* vcagt  */
+
+__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
+vcagts_f32 (float32_t __a, float32_t __b)
+{
+  return __builtin_fabsf (__a) > __builtin_fabsf (__b) ? -1 : 0;
+}
+
+__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
+vcagt_f32 (float32x2_t __a, float32x2_t __b)
+{
+  return vabs_f32 (__a) > vabs_f32 (__b);
+}
+
+__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
+vcagtq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return vabsq_f32 (__a) > vabsq_f32 (__b);
+}
+
+__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
+vcagtd_f64 (float64_t __a, float64_t __b)
+{
+  return __builtin_fabs (__a) > __builtin_fabs (__b) ? -1 : 0;
+}
+
+__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
+vcagtq_f64 (float64x2_t __a, float64x2_t __b)
+{
+  return vabsq_f64 (__a) > vabsq_f64 (__b);
+}
+
+/* vcale  */
+
+__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
+vcale_f32 (float32x2_t __a, float32x2_t __b)
+{
+  return vabs_f32 (__a) <= vabs_f32 (__b);
+}
+
+__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
+vcaleq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return vabsq_f32 (__a) <= vabsq_f32 (__b);
+}
+
+__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
+vcaleq_f64 (float64x2_t __a, float64x2_t __b)
+{
+  return vabsq_f64 (__a) <= vabsq_f64 (__b);
+}
+
+/* vcalt  */
+
+__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
+vcalt_f32 (float32x2_t __a, float32x2_t __b)
+{
+  return vabs_f32 (__a) < vabs_f32 (__b);
+}
+
+__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
+vcaltq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return vabsq_f32 (__a) < vabsq_f32 (__b);
+}
+
+__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
+vcaltq_f64 (float64x2_t __a, float64x2_t __b)
+{
+  return vabsq_f64 (__a) < vabsq_f64 (__b);
+}
+
 /* vceq - vector.  */
 
 __extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))