http://gcc.gnu.org/bugzilla/show_bug.cgi?id=49257
Uros Bizjak <ubizjak at gmail dot com> changed:
What |Removed |Added
----------------------------------------------------------------------------
Status|ASSIGNED |RESOLVED
Resolution| |WONTFIX
--- Comment #18 from Uros Bizjak <ubizjak at gmail dot com> 2012-01-20 11:06:16
UTC ---
The only way this could work is to put __builtin_ia32_emms into the loop, after
__builtin_ia32_movntq. -mfpmath=sse does not mean that x87 is disabled, only
that equivalent arithmetic instructions use SSE instructions. If there is no
equivalent SSE insn, x87 insn is used.
IIRC, even Intel's Instruction set reference suggests to group FP and MMX insn
together and put emms after MMX block.
Since a substantial effort would be needed to fix this questionable corner
case, and the test is violating recommended practice, I'm marking this PR as
WONTFIX.
