keep r3m are better, it reduce load instruction
At 2015-03-29 07:39:26,[email protected] wrote: ># HG changeset patch ># User David T Yuen <[email protected]> ># Date 1427585923 25200 ># Node ID 88b50a5f74d98018b1583761a6fc4c5c23f4d401 ># Parent 36d70728acc2d9d6103af7530493176c08298ded >asm:intra_pred_ang4_2 improved by ~4% 134.99 -> 129.95 with nits and tweaks > >Corrected parameter count >Changed r3m to r3d >Reduced xmm registers to 1 > >diff -r 36d70728acc2 -r 88b50a5f74d9 source/common/x86/intrapred8.asm >--- a/source/common/x86/intrapred8.asm Fri Mar 27 13:16:28 2015 -0500 >+++ b/source/common/x86/intrapred8.asm Sat Mar 28 16:38:43 2015 -0700 >@@ -1320,22 +1320,20 @@ > ; void intraPredAng4(pixel* dst, intptr_t dstStride, pixel* src, int dirMode, > int bFilter) > ;----------------------------------------------------------------------------------------- > INIT_XMM sse2 >-cglobal intra_pred_ang4_2, 3,5,3 >+cglobal intra_pred_ang4_2, 4,5,1 > lea r4, [r2 + 2] > add r2, 10 >- cmp r3m, byte 34 >+ cmp r3d, byte 34 > cmove r2, r4 > > movh m0, [r2] > movd [r0], m0 >- mova m1, m0 >- psrldq m1, 1 >- movd [r0 + r1], m1 >- mova m2, m0 >- psrldq m2, 2 >- movd [r0 + r1 * 2], m2 >+ psrldq m0, 1 >+ movd [r0 + r1], m0 >+ psrldq m0, 1 >+ movd [r0 + r1 * 2], m0 > lea r1, [r1 * 3] >- psrldq m0, 3 >+ psrldq m0, 1 > movd [r0 + r1], m0 > RET > >_______________________________________________ >x265-devel mailing list >[email protected] >https://mailman.videolan.org/listinfo/x265-devel
_______________________________________________ x265-devel mailing list [email protected] https://mailman.videolan.org/listinfo/x265-devel
