Message ID | 20170608230502.29258-3-jdarnley@obe.tv |
---|---|
State | Accepted |
Commit | 88dcdfad0964a954b6f185936c023dfd1c5d5e99 |
Headers | show |
Hi, On Thu, Jun 8, 2017 at 7:04 PM, James Darnley <jdarnley@obe.tv> wrote: > From: Henrik Gramner <henrik@gramner.com> > > There's no point in emitting a rep prefix before ret on modern CPUs. > --- > libavutil/x86/x86inc.asm | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) LGTM. Ronald
diff --git a/libavutil/x86/x86inc.asm b/libavutil/x86/x86inc.asm index f2a6a3f1db..44069741cc 100644 --- a/libavutil/x86/x86inc.asm +++ b/libavutil/x86/x86inc.asm @@ -636,7 +636,7 @@ DECLARE_ARG 7, 8, 9, 10, 11, 12, 13, 14 ; We can automatically detect "follows a branch", but not a branch target. ; (SSSE3 is a sufficient condition to know that your cpu doesn't have this problem.) %macro REP_RET 0 - %if has_epilogue + %if has_epilogue || cpuflag(ssse3) RET %else rep ret
From: Henrik Gramner <henrik@gramner.com> There's no point in emitting a rep prefix before ret on modern CPUs. --- libavutil/x86/x86inc.asm | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)