[x265] [PATCH] asm: assembly code for pixel_sad_64x48 and pixel_sad_64x64

[dnyaneshwar at multicorewareinc.com]

# HG changeset patch
# User Dnyaneshwar Gorade <dnyaneshwar at multicorewareinc.com>
# Date 1383122501 -19800
#      Wed Oct 30 14:11:41 2013 +0530
# Node ID 1f32144338f3399a962fddbaf2f261242128425c
# Parent  c08f78ad73bf677164f3ffec707a1fb22de21d59
asm: assembly code for pixel_sad_64x48 and pixel_sad_64x64

diff -r c08f78ad73bf -r 1f32144338f3 source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Wed Oct 30 13:45:38 2013 +0530
+++ b/source/common/x86/asm-primitives.cpp	Wed Oct 30 14:11:41 2013 +0530
@@ -248,6 +248,8 @@
 
         p.sad[LUMA_64x16]  = x265_pixel_sad_64x16_sse2;
         p.sad[LUMA_64x32]  = x265_pixel_sad_64x32_sse2;
+        p.sad[LUMA_64x48]  = x265_pixel_sad_64x48_sse2;
+        p.sad[LUMA_64x64]  = x265_pixel_sad_64x64_sse2;
 
         ASSGN_SSE(sse2);
         INIT2(sad, _sse2);
diff -r c08f78ad73bf -r 1f32144338f3 source/common/x86/sad-a.asm
--- a/source/common/x86/sad-a.asm	Wed Oct 30 13:45:38 2013 +0530
+++ b/source/common/x86/sad-a.asm	Wed Oct 30 14:11:41 2013 +0530
@@ -804,6 +804,66 @@
     movd    eax, m0
     RET
 
+;-----------------------------------------------------------------------------
+; int pixel_sad_64x48( uint8_t *, intptr_t, uint8_t *, intptr_t )
+;-----------------------------------------------------------------------------
+cglobal pixel_sad_64x48, 4,4,5
+    pxor  m0,  m0
+    mov   r4,  48
+
+.loop
+    PROCESS_SAD_64x4
+    lea     r2,  [r2 + r3]
+    lea     r0,  [r0 + r1]
+
+    PROCESS_SAD_64x4
+    lea     r2,  [r2 + r3]
+    lea     r0,  [r0 + r1]
+
+    sub   r4,  8
+    cmp   r4,  8
+
+jnz .loop
+    PROCESS_SAD_64x4
+    lea   r2,  [r2 + r3]
+    lea   r0,  [r0 + r1]
+    PROCESS_SAD_64x4
+
+    movhlps m1,  m0
+    paddd   m0,  m1
+    movd    eax, m0
+    RET
+
+;-----------------------------------------------------------------------------
+; int pixel_sad_64x64( uint8_t *, intptr_t, uint8_t *, intptr_t )
+;-----------------------------------------------------------------------------
+cglobal pixel_sad_64x64, 4,4,5
+    pxor  m0,  m0
+    mov   r4,  64
+
+.loop
+    PROCESS_SAD_64x4
+    lea     r2,  [r2 + r3]
+    lea     r0,  [r0 + r1]
+
+    PROCESS_SAD_64x4
+    lea     r2,  [r2 + r3]
+    lea     r0,  [r0 + r1]
+
+    sub   r4,  8
+    cmp   r4,  8
+
+jnz .loop
+    PROCESS_SAD_64x4
+    lea   r2,  [r2 + r3]
+    lea   r0,  [r0 + r1]
+    PROCESS_SAD_64x4
+
+    movhlps m1,  m0
+    paddd   m0,  m1
+    movd    eax, m0
+    RET
+
 %endmacro
 
 INIT_XMM sse2