lavr: x86: improve non-SSE4 version of S16_TO_S32_SX macro

Removes a false dependency on existing contents of the 2nd dst register, giving better performance for OOE.
2012-06-26 16:50:10 -04:00 · 2012-06-26 16:50:10 -04:00 · e9da9a3111
parent 743f07062a
commit e9da9a3111
1 changed files with 2 additions and 1 deletions
--- a/libavresample/x86/util.asm
+++ b/libavresample/x86/util.asm
@ -26,7 +26,8 @@
    pmovsxwd     m%1, m%1
    SWAP %1, %2
 %else
-    punpckhwd    m%2, m%1
+    mova         m%2, m%1
+    punpckhwd    m%2, m%2
    punpcklwd    m%1, m%1
    psrad        m%2, 16
    psrad        m%1, 16