aarch64: Implement math acceleration via builtins

This patch converts asm statements into builtins for AArch64.  As an
example for the file sysdeps/aarch64/fpu/s_ceil.c, we convert the
function from

double
__ceil (double x)
{
  double result;
  asm ("frintp\t%d0, %d1" :
       "=w" (result) : "w" (x) );
  return result;
}

into

double
__ceil (double x)
{
  return __builtin_ceil (x);
}

Tested on aarch64-linux-gnu with gcc-4.9.4 and gcc-6.

	* sysdeps/aarch64/fpu/e_sqrt.c (ieee754_sqrt): Replace asm statements
	with __builtin_sqrt.
	* sysdeps/aarch64/fpu/e_sqrtf.c (ieee754_sqrtf): Replace asm statements
	with __builtin_sqrtf.
	* sysdeps/aarch64/fpu/s_ceil.c (__ceil): Replace asm statements
	with __builtin_ceil.
	* sysdeps/aarch64/fpu/s_ceilf.c (__ceilf): Replace asm statements
	with __builtin_ceilf.
	* sysdeps/aarch64/fpu/s_floor.c (__floor): Replace asm statements
	with __builtin_floor.
	* sysdeps/aarch64/fpu/s_floorf.c (__floorf): Replace asm statements
	with __builtin_floorf.
	* sysdeps/aarch64/fpu/s_fma.c (__fma): Replace asm statements
	with __builtin_fma.
	* sysdeps/aarch64/fpu/s_fmaf.c (__fmaf): Replace asm statements
	with __builtin_fmaf.
	* sysdeps/aarch64/fpu/s_fmax.c (__fmax): Replace asm statements
	with __builtin_fmax.
	* sysdeps/aarch64/fpu/s_fmaxf.c (__fmaxf): Replace asm statements
	with __builtin_fmaxf.
	* sysdeps/aarch64/fpu/s_fmin.c (__fmin): Replace asm statements
	with __builtin_fmin.
	* sysdeps/aarch64/fpu/s_fminf.c (__fminf): Replace asm statements
	with __builtin_fminf.
	* sysdeps/aarch64/fpu/s_frint.c: Delete file.
	* sysdeps/aarch64/fpu/s_frintf.c: Delete file.
	* sysdeps/aarch64/fpu/s_llrint.c (__llrint): Replace asm statements
	with builtin_rint and conversion to int.
	* sysdeps/aarch64/fpu/s_llrintf.c (__llrintf): Likewise.
	* sysdeps/aarch64/fpu/s_llround.c (__llround): Replace asm statements
	with builtin_llround.
	* sysdeps/aarch64/fpu/s_llroundf.c (__llroundf): Likewise.
	* sysdeps/aarch64/fpu/s_lrint.c (__lrint): Replace asm statements
	with builtin_rint and conversion to long int.
	* sysdeps/aarch64/fpu/s_lrintf.c (__lrintf): Likewise.
	* sysdeps/aarch64/fpu/s_lround.c (__lround): Replace asm statements
	with builtin_lround.
	* sysdeps/aarch64/fpu/s_lroundf.c (__lroundf): Replace asm statements
	with builtin_lroundf.
	* sysdeps/aarch64/fpu/s_nearbyint.c (__nearbyint): Replace asm
	statements with __builtin_nearbyint.
	* sysdeps/aarch64/fpu/s_nearbyintf.c (__nearbyintf): Replace asm
	statements with __builtin_nearbyintf.
	* sysdeps/aarch64/fpu/s_rint.c (__rint): Replace asm statements
	with __builtin_rint.
	* sysdeps/aarch64/fpu/s_rintf.c (__rintf): Replace asm statements
	with __builtin_rintf.
	* sysdeps/aarch64/fpu/s_round.c (__round): Replace asm statements
	with __builtin_round.
	* sysdeps/aarch64/fpu/s_roundf.c (__roundf): Replace asm statements
	with __builtin_roundf.
	* sysdeps/aarch64/fpu/s_trunc.c (__trunc): Replace asm statements
	with __builtin_trunc.
	* sysdeps/aarch64/fpu/s_truncf.c (__truncf): Replace asm statements
	with __builtin_truncf.
	* sysdeps/aarch64/fpu/Makefile: Build e_sqrt[f].c with -fno-math-errno.

1 files changed, 4 insertions, 22 deletions

diff --git a/sysdeps/aarch64/fpu/s_fma.c b/sysdeps/aarch64/fpu/s_fma.c
index 6f62ce2365..e496ec6438 100644
--- a/sysdeps/aarch64/fpu/s_fma.c
+++ b/sysdeps/aarch64/fpu/s_fma.c
@@ -18,28 +18,10 @@
 
 #include <math.h>
 
-#ifndef FUNC
-# define FUNC fma
-#endif
-
-#ifndef TYPE
-# define TYPE double
-# define REGS "d"
-#else
-# ifndef REGS
-#  error REGS not defined
-# endif
-#endif
-
-#define __CONCATX(a,b) __CONCAT(a,b)
-
-TYPE
-__CONCATX(__,FUNC) (TYPE x, TYPE y, TYPE z)
+double
+__fma (double x, double y, double z)
 {
-  TYPE result;
-  asm ( "fmadd" "\t%" REGS "0, %" REGS "1, %" REGS "2, %" REGS "3"
-        : "=w" (result) : "w" (x), "w" (y), "w" (z) );
-  return result;
+  return __builtin_fma (x, y, z);
 }
 
-weak_alias (__CONCATX(__,FUNC), FUNC)
+weak_alias (__fma, fma)