<div dir="ltr">Re-sending the patch after correcting the alignment problem.</div><div class="gmail_extra"><br><br><div class="gmail_quote">On Tue, Nov 26, 2013 at 4:59 PM, <span dir="ltr"><<a href="mailto:yuvaraj@multicorewareinc.com" target="_blank">yuvaraj@multicorewareinc.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"># HG changeset patch<br>
# User Yuvaraj Venkatesh <<a href="mailto:yuvaraj@multicorewareinc.com">yuvaraj@multicorewareinc.com</a>><br>
# Date 1385465357 -19800<br>
# Tue Nov 26 16:59:17 2013 +0530<br>
# Node ID 9aca23400805335f6cd3134d8dc045a00432c4d1<br>
# Parent 52738c22dce02e8d59cc4b09f1e1b23a0a8360c5<br>
asm: assembly code for pixel_sse_ss_48x64<br>
<br>
diff -r 52738c22dce0 -r 9aca23400805 source/common/x86/asm-primitives.cpp<br>
--- a/source/common/x86/asm-primitives.cpp Tue Nov 26 16:15:02 2013 +0530<br>
+++ b/source/common/x86/asm-primitives.cpp Tue Nov 26 16:59:17 2013 +0530<br>
@@ -108,7 +108,8 @@<br>
p.sse_ss[LUMA_32x16] = x265_pixel_ssd_ss_32x16_ ## cpu; \<br>
p.sse_ss[LUMA_32x24] = x265_pixel_ssd_ss_32x24_ ## cpu; \<br>
p.sse_ss[LUMA_32x32] = x265_pixel_ssd_ss_32x32_ ## cpu; \<br>
- p.sse_ss[LUMA_32x64] = x265_pixel_ssd_ss_32x64_ ## cpu;<br>
+ p.sse_ss[LUMA_32x64] = x265_pixel_ssd_ss_32x64_ ## cpu; \<br>
+ p.sse_ss[LUMA_48x64] = x265_pixel_ssd_ss_48x64_ ## cpu;<br>
<br>
#define SA8D_INTER_FROM_BLOCK(cpu) \<br>
p.sa8d_inter[LUMA_4x8] = x265_pixel_satd_4x8_ ## cpu; \<br>
diff -r 52738c22dce0 -r 9aca23400805 source/common/x86/pixel-a.asm<br>
--- a/source/common/x86/pixel-a.asm Tue Nov 26 16:15:02 2013 +0530<br>
+++ b/source/common/x86/pixel-a.asm Tue Nov 26 16:59:17 2013 +0530<br>
@@ -511,21 +511,90 @@<br>
RET<br>
%endmacro<br>
<br>
+%macro SSD_SS_48 0<br>
+cglobal pixel_ssd_ss_48x64, 4,7,6<br>
+ FIX_STRIDES r1, r3<br>
+ mov r4d, 32<br>
+ pxor m0, m0<br>
+.loop<br>
+ mova m1, [r0]<br>
+ psubw m1, [r2]<br>
+ pmaddwd m1, m1<br>
+ paddd m0, m1<br>
+ mova m1, [r0 + 16]<br>
+ psubw m1, [r2 + 16]<br>
+ pmaddwd m1, m1<br>
+ paddd m0, m1<br>
+ mova m1, [r0 + 32]<br>
+ psubw m1, [r2 + 32]<br>
+ pmaddwd m1, m1<br>
+ paddd m0, m1<br>
+ mova m1, [r0 + 48]<br>
+ psubw m1, [r2 + 48]<br>
+ pmaddwd m1, m1<br>
+ paddd m0, m1<br>
+ mova m1, [r0 + 64]<br>
+ psubw m1, [r2 + 64]<br>
+ pmaddwd m1, m1<br>
+ paddd m0, m1<br>
+ mova m1, [r0 + 80]<br>
+ psubw m1, [r2 + 80]<br>
+ pmaddwd m1, m1<br>
+ paddd m0, m1<br>
+ lea r0, [r0 + 2*r1]<br>
+ lea r2, [r2 + 2*r3]<br>
+ mova m1, [r0]<br>
+ psubw m1, [r2]<br>
+ pmaddwd m1, m1<br>
+ paddd m0, m1<br>
+ mova m1, [r0 + 16]<br>
+ psubw m1, [r2 + 16]<br>
+ pmaddwd m1, m1<br>
+ paddd m0, m1<br>
+ mova m1, [r0 + 32]<br>
+ psubw m1, [r2 + 32]<br>
+ pmaddwd m1, m1<br>
+ paddd m0, m1<br>
+ mova m1, [r0 + 48]<br>
+ psubw m1, [r2 + 48]<br>
+ pmaddwd m1, m1<br>
+ paddd m0, m1<br>
+ mova m1, [r0 + 64]<br>
+ psubw m1, [r2 + 64]<br>
+ pmaddwd m1, m1<br>
+ paddd m0, m1<br>
+ mova m1, [r0 + 80]<br>
+ psubw m1, [r2 + 80]<br>
+ pmaddwd m1, m1<br>
+ paddd m0, m1<br>
+ lea r0, [r0 + 2*r1]<br>
+ lea r2, [r2 + 2*r3]<br>
+ dec r4d<br>
+ jnz .loop<br>
+ phaddd m0, m0<br>
+ phaddd m0, m0<br>
+ movd eax, m0<br>
+ RET<br>
+%endmacro<br>
+<br>
INIT_XMM sse2<br>
SSD_SS_ONE<br>
SSD_SS_12x16<br>
SSD_SS_24<br>
SSD_SS_32xN<br>
+SSD_SS_48<br>
INIT_XMM sse4<br>
SSD_SS_ONE<br>
SSD_SS_12x16<br>
SSD_SS_24<br>
SSD_SS_32xN<br>
+SSD_SS_48<br>
INIT_XMM avx<br>
SSD_SS_ONE<br>
SSD_SS_12x16<br>
SSD_SS_24<br>
SSD_SS_32xN<br>
+SSD_SS_48<br>
%endif ; !HIGH_BIT_DEPTH<br>
<br>
%if HIGH_BIT_DEPTH == 0<br>
</blockquote></div><br></div>