diff options
author | Joseph Myers <joseph@codesourcery.com> | 2015-02-13 16:20:36 +0000 |
---|---|---|
committer | Joseph Myers <joseph@codesourcery.com> | 2015-02-13 16:20:36 +0000 |
commit | 95c26233a1c7dd73a852a4f3bffd2d2eeba5e2fd (patch) | |
tree | f6e64cd9b63a30a3c22cb4200515f99b376acbf1 /sysdeps/powerpc/fpu/s_fminf.S | |
parent | 3f293d614c9e641a0d96d347df5c1c5ee687762f (diff) | |
download | glibc-95c26233a1c7dd73a852a4f3bffd2d2eeba5e2fd.zip glibc-95c26233a1c7dd73a852a4f3bffd2d2eeba5e2fd.tar.gz glibc-95c26233a1c7dd73a852a4f3bffd2d2eeba5e2fd.tar.bz2 |
Fix powerpc software sqrtf (bug 17967).
Similarly to sqrt in
<https://sourceware.org/ml/libc-alpha/2015-02/msg00353.html>, the
powerpc sqrtf implementation for when _ARCH_PPCSQ is not defined also
relies on a * b + c being contracted into a fused multiply-add.
Although this contraction is not explicitly disabled for e_sqrtf.c, it
still seems appropriate to make the file explicit about its
requirements by using __builtin_fmaf; this patch does so.
Furthermore, it turns out that doing so fixes the observed inaccuracy
and missing exceptions (that is, that without explicit __builtin_fmaf
usage, it was not being compiled as intended).
Tested for powerpc32 (hard float).
[BZ #17967]
* sysdeps/powerpc/fpu/e_sqrtf.c (__slow_ieee754_sqrtf): Use
__builtin_fmaf instead of relying on contraction of a * b + c.
Diffstat (limited to 'sysdeps/powerpc/fpu/s_fminf.S')
0 files changed, 0 insertions, 0 deletions