<div dir="ltr">Okay. I will keep the earlier SSE4 code.</div><div class="gmail_extra"><br><br><div class="gmail_quote">On Wed, Nov 13, 2013 at 4:59 PM, chen <span dir="ltr"><<a href="mailto:chenm003@163.com" target="_blank">chenm003@163.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div style="line-height:1.7;font-size:14px;font-family:arial"><div>At 2013-11-13 14:53:27,<a href="mailto:nabajit@multicorewareinc.com" target="_blank">nabajit@multicorewareinc.com</a> wrote:<div class="im">
<br>># HG changeset patch<br>># User Nabajit Deka<br>># Date 1384325281 -19800<br>># Wed Nov 13 12:18:01 2013 +0530<br>># Node ID 017763dc543d091170082eccf7b42a0c47c453ff<br>># Parent c4ca80d19105ccf1ba2ec14dd65915f2820a660d<br>
>asm: Replaced SSE4 instructions with SSE2 and general purpose instructions for chroma vsp filter functions.<br>><br>>diff -r c4ca80d19105 -r 017763dc543d source/common/x86/ipfilter8.asm<br>>--- a/source/common/x86/ipfilter8.asm Tue Nov 12 19:10:23 2013 +0530<br>
>+++ b/source/common/x86/ipfilter8.asm Wed Nov 13 12:18:01 2013 +0530<br>>@@ -3183,11 +3183,16 @@<br>> packssdw m0, m2<br>> packuswb m0, m0<br>> <br>>- pextrw [r2], m0, 0<br>>- pextrw [r2 + r3], m0, 1<br>
>- pextrw [r2 + 2 * r3], m0, 2<br>>+ movd r5d, m0<br>>+ mov [r2], r5w<br>>+ shr r5d, 16<br>>+ mov [r2 + r3], r5w<br>>+ pshufd m0, m0, 1<br>>+ movd r5d, m0<br>
</div>pshufd + movd is slower than pextrd</div><div class="im">
<div> </div>
<div>>+ mov [r2 + 2 * r3], r5w<br>>+ shr r5d, 16<br>> lea r2, [r2 + 2 * r3]<br>>- pextrw [r2 + r3], m0, 3<br>>+ mov [r2 + r3], r5w<br>> <br>> lea r2, [r2 + 2 * r3]<br>
> <br></div></div></div><br>_______________________________________________<br>
x265-devel mailing list<br>
<a href="mailto:x265-devel@videolan.org">x265-devel@videolan.org</a><br>
<a href="https://mailman.videolan.org/listinfo/x265-devel" target="_blank">https://mailman.videolan.org/listinfo/x265-devel</a><br>
<br></blockquote></div><br></div>