<div style="line-height:1.7;color:#000000;font-size:14px;font-family:arial"><DIV>On Fri, Oct 25, 2013 at 7:25 AM, Min Chen <SPAN dir="ltr"><<A href="mailto:chenm003@163.com" target="_blank">chenm003@163.com</A>></SPAN> wrote:<BR></DIV>
<BLOCKQUOTE id="isReplyContent" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">
<DIV dir="ltr">
<DIV class="gmail_extra">
<DIV class="gmail_quote">
<BLOCKQUOTE class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid"># HG changeset patch<BR># User Min Chen <<A href="mailto:chenm003@163.com">chenm003@163.com</A>><BR># Date 1382703678 -28800<BR># Node ID 2221e3abb479b1e9a586d80d769373d13c7f7980<BR># Parent  4ca4da7bdd36fbef00b9eefe54c0a56bf11633f3<BR>asm: interp_8tap_hv_pp_8x8() for InterpolateHV_8x8<BR></BLOCKQUOTE>
<DIV><BR></DIV>
<DIV>How does this compare, performance wise, to the combined h_ps + v_sp intrinsic functions?</DIV>
<DIV> </DIV>
<DIV>[MC] about 2.8x</DIV>
<DIV> </DIV></DIV></DIV></DIV></BLOCKQUOTE></div>