http://gcc.gnu.org/bugzilla/show_bug.cgi?id=56788
Uroš Bizjak <ubizjak at gmail dot com> changed:
What |Removed |Added
----------------------------------------------------------------------------
Target Milestone|--- |4.7.4
--- Comment #4 from Uroš Bizjak <ubizjak at gmail dot com> ---
gcc follows Microsoft definition [1]:
__m128d _mm_frcz_ss (
__m128 high,
__m128 src
);
This should be the same as other "vm" (vector merge) instructions, for example
_mm_add_ss [2], also commented in gcc's xmmintrin.h:
/* Perform the respective operation on the lower SPFP (single-precision
floating-point) values of A and B; the upper three SPFP values are
passed through from A. */
__m128 _mm_add_ss (__m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_addss ((__v4sf)__A, (__v4sf)__B);
}
[1] http://msdn.microsoft.com/en-us/library/vstudio/gg445126%28v=vs.100%29.aspx
[2] http://msdn.microsoft.com/en-us/library/be94x2y6%28v=vs.90%29.aspx