[x265] [PATCH] blockcopy_sp_8x8, optimized asm code

[praveen at multicorewareinc.com]

# HG changeset patch
# User Praveen Tiwari
# Date 1383911937 -19800
# Node ID d9fd009d7118c9cb76b84e94e01732b10d7bf313
# Parent  de021d66138911513648828b3a657c3cba3e9dba
blockcopy_sp_8x8, optimized asm code

diff -r de021d661389 -r d9fd009d7118 source/common/x86/blockcopy8.asm
--- a/source/common/x86/blockcopy8.asm	Fri Nov 08 17:20:44 2013 +0530
+++ b/source/common/x86/blockcopy8.asm	Fri Nov 08 17:28:57 2013 +0530
@@ -1175,45 +1175,38 @@
 ; void blockcopy_sp_8x8(pixel *dest, intptr_t destStride, int16_t *src, intptr_t srcStride)
 ;-----------------------------------------------------------------------------
 INIT_XMM sse2
-cglobal blockcopy_sp_8x8, 4, 6, 8, dest, destStride, src, srcStride
+cglobal blockcopy_sp_8x8, 4, 4, 8, dest, destStride, src, srcStride
 
 add        r3,      r3
 
-mova       m0,      [tab_Vm]
+movu       m0,      [r2]
+movu       m1,      [r2 + r3]
+movu       m2,      [r2 + 2 * r3]
+lea        r2,      [r2 + 2 * r3]
+movu       m3,      [r2 + r3]
+movu       m4,      [r2 + 2 * r3]
+lea        r2,      [r2 + 2 * r3]
+movu       m5,      [r2 + r3]
+movu       m6,      [r2 + 2 * r3]
+lea        r2,      [r2 + 2 * r3]
+movu       m7,      [r2 + r3]
 
-movu       m1,      [r2]
-movu       m2,      [r2 + r3]
-movu       m3,      [r2 + 2 * r3]
-lea        r4,      [r2 + 2 * r3]
-movu       m4,      [r4 + r3]
-movu       m5,      [r4 + 2 * r3]
-lea        r4,      [r4 + 2 * r3]
-movu       m6,      [r4 + r3]
-movu       m7,      [r4 + 2 * r3]
-lea        r5,      [r4 + 2 * r3]
+packuswb   m0,      m1
+packuswb   m2,      m3
+packuswb   m4,      m5
+packuswb   m6,      m7
 
-pshufb     m1,      m0
-pshufb     m2,      m0
-pshufb     m3,      m0
-pshufb     m4,      m0
-pshufb     m5,      m0
-pshufb     m6,      m0
-pshufb     m7,      m0
-
-movh       [r0],            m1
-movh       [r0 + r1],       m2
-movh       [r0 + 2 * r1],   m3
-lea        r4,              [r0 + 2 * r1]
-movh       [r4 + r1],       m4
-movh       [r4 + 2 * r1],   m5
-lea        r4,              [r4 + 2 * r1]
-movh       [r4 + r1],       m6
-movh       [r4 + 2 * r1],   m7
-
-movu       m1,              [r5 + r3]
-pshufb     m1,              m0
-lea        r4,              [r4 + 2 * r1]
-movh       [r4 + r1],       m1
+movlps     [r0],          m0
+movhps     [r0 + r1],     m0
+movlps     [r0 + 2 * r1], m2
+lea        r0,            [r0 + 2 * r1]
+movhps     [r0 + r1],     m2
+movlps     [r0 + 2 * r1], m4
+lea        r0,            [r0 + 2 * r1]
+movhps     [r0 + r1],     m4
+movlps     [r0 + 2 * r1], m6
+lea        r0,            [r0 + 2 * r1]
+movhps     [r0 + r1],     m6
 
 RET