This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: [Patch] Fix instruction length of jcc_fused
On Sat, Sep 20, 2008 at 1:15 PM, Ye, Joey <joey.ye@intel.com> wrote:
> HJ wrote:
>> I looked at the generated code without TARGET_FUSE_CMP_AND_BRANCH.
>> In most cases, gcc doesn't put any instructions between TEST/CMP
>> and JCC and we get macro-fusion optimization automatically even
>> if TARGET_FUSE_CMP_AND_BRANCH is off.
> HJ, do you have performance number without macro-fusion patterns for
> Core2?
>
I tried your testcase against gcc 4.3. The performance regression is gone.
Please verify performance regressions in SPEC CPU 2000/2006 are
also fixed.
Thanks.
--
H.J.