[PATCH] aarch64: Use GCC vector extensions for FP ml[as]_n intrinsics

[Jonathan Wright via Gcc-patches]

Hi,

As subject, this patch rewrites floating-point mla_n/mls_n intrinsics to use
a + b * c / a - b * c rather than inline assembly code, allowing for better
scheduling and optimization.

Regression tested and bootstrapped on aarch64-none-linux-gnu - no
issues.

Ok for master?

Thanks,
Jonathan

---

gcc/ChangeLog:

2021-01-18  Jonathan Wright  <jonathan.wri...@arm.com>

        * config/aarch64/arm_neon.h (vmla_n_f32): Use C rather than asm.
        (vmlaq_n_f32): Likewise.
        (vmls_n_f32): Likewise.
        (vmlsq_n_f32): Likewise.

diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index d891067f021a0bcc24af79dfbe2d9dd5889b23bc..d1ab3b7d54cd5b965f91e685139677864fcfe3e1 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -7233,13 +7233,7 @@ __extension__ extern __inline float32x2_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vmla_n_f32 (float32x2_t __a, float32x2_t __b, float32_t __c)
 {
-  float32x2_t __result;
-  float32x2_t __t1;
-  __asm__ ("fmul %1.2s, %3.2s, %4.s[0]; fadd %0.2s, %0.2s, %1.2s"
-           : "=w"(__result), "=w"(__t1)
-           : "0"(__a), "w"(__b), "w"(__c)
-           : /* No clobbers */);
-  return __result;
+  return __a + __b * __c;
 }
 
 __extension__ extern __inline int16x4_t
@@ -7734,13 +7728,7 @@ __extension__ extern __inline float32x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vmlaq_n_f32 (float32x4_t __a, float32x4_t __b, float32_t __c)
 {
-  float32x4_t __result;
-  float32x4_t __t1;
-  __asm__ ("fmul %1.4s, %3.4s, %4.s[0]; fadd %0.4s, %0.4s, %1.4s"
-           : "=w"(__result), "=w"(__t1)
-           : "0"(__a), "w"(__b), "w"(__c)
-           : /* No clobbers */);
-  return __result;
+  return __a + __b * __c;
 }
 
 __extension__ extern __inline int16x8_t
@@ -7827,13 +7815,7 @@ __extension__ extern __inline float32x2_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vmls_n_f32 (float32x2_t __a, float32x2_t __b, float32_t __c)
 {
-  float32x2_t __result;
-  float32x2_t __t1;
-  __asm__ ("fmul %1.2s, %3.2s, %4.s[0]; fsub %0.2s, %0.2s, %1.2s"
-           : "=w"(__result), "=w"(__t1)
-           : "0"(__a), "w"(__b), "w"(__c)
-           : /* No clobbers */);
-  return __result;
+  return __a - __b * __c;
 }
 
 __extension__ extern __inline int16x4_t
@@ -8324,13 +8306,7 @@ __extension__ extern __inline float32x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vmlsq_n_f32 (float32x4_t __a, float32x4_t __b, float32_t __c)
 {
-  float32x4_t __result;
-  float32x4_t __t1;
-  __asm__ ("fmul %1.4s, %3.4s, %4.s[0]; fsub %0.4s, %0.4s, %1.4s"
-           : "=w"(__result), "=w"(__t1)
-           : "0"(__a), "w"(__b), "w"(__c)
-           : /* No clobbers */);
-  return __result;
+  return __a - __b * __c;
 }
 
 __extension__ extern __inline int16x8_t