math: Optimize fma call on acospif

The fma is required only for inputs less than 0x1.0fd288p-127.  Also
only add the extra check for !__FP_FAST_FMA targets.

Checked on x86_64-linux-gnu and aarch64-linux-gnu.
Reviewed-by: Paul Zimmermann <Paul.Zimmermann@inria.fr>

diff --git a/sysdeps/ieee754/flt-32/s_acospif.c b/sysdeps/ieee754/flt-32/s_acospif.c
index caf65d42f3d8f687ea4caa81ef596904176c59c4..63230bd3b37dd135ef959be8d9ea1599d64acc0e 100644 (file)
--- a/sysdeps/ieee754/flt-32/s_acospif.c
+++ b/sysdeps/ieee754/flt-32/s_acospif.c
@@ -67,7 +67,12 @@ __acospif (float x)
       /* For |x| <= 0x1.0fd288p-127, c0 += c4*(z4*z4) would raise a spurious
         underflow exception, we use an FMA instead, where c4 * z4 does not
         underflow. */
-      c0 = fma (c4 * z4, z4, c0);
+#ifndef __FP_FAST_FMA
+      if (__glibc_likely (ax > 0x1.0fd288p-127))
+       c0 = (c4 * z4) * z4 + c0;
+      else
+#endif
+       c0 = fma (c4 * z4, z4, c0);
       return 0.5 - z * c0;
     }
   else