[x265] [PATCH] asm: avx2 code for sad[32x64] for 8bpp

[sumalatha at multicorewareinc.com]

# HG changeset patch
# User Sumalatha Polureddy<sumalatha at multicorewareinc.com>
# Date 1426074528 -19800
# Node ID 2d7b1eef74d0c0cc42035d5b82759750b62f2ba9
# Parent  ccf70e5d0142ee558c27968a70d1bc9a2002dbb9
asm: avx2 code for sad[32x64] for 8bpp

SSE3
sad[32x64]  37.61x   1402.92         52759.16

AVX2
sad[32x64]  53.95x   909.12          49048.07

diff -r ccf70e5d0142 -r 2d7b1eef74d0 source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Wed Mar 11 16:58:21 2015 +0530
+++ b/source/common/x86/asm-primitives.cpp	Wed Mar 11 17:18:48 2015 +0530
@@ -1447,6 +1447,7 @@
         p.pu[LUMA_32x8].sad = x265_pixel_sad_32x8_avx2;
         p.pu[LUMA_32x16].sad = x265_pixel_sad_32x16_avx2;
         p.pu[LUMA_32x24].sad = x265_pixel_sad_32x24_avx2;
+        p.pu[LUMA_32x64].sad = x265_pixel_sad_32x64_avx2;
 
         p.pu[LUMA_8x4].sad_x3 = x265_pixel_sad_x3_8x4_avx2;
         p.pu[LUMA_8x8].sad_x3 = x265_pixel_sad_x3_8x8_avx2;
diff -r ccf70e5d0142 -r 2d7b1eef74d0 source/common/x86/sad-a.asm
--- a/source/common/x86/sad-a.asm	Wed Mar 11 16:58:21 2015 +0530
+++ b/source/common/x86/sad-a.asm	Wed Mar 11 17:18:48 2015 +0530
@@ -4006,6 +4006,33 @@
     RET
 
 INIT_YMM avx2
+cglobal pixel_sad_32x64, 4,4,5
+    xorps           m0, m0
+%assign x 0
+%rep 32
+    movu           m1, [r0]               ; row 0 of pix0
+    movu           m2, [r2]               ; row 0 of pix1
+    movu           m3, [r0 + r1]          ; row 1 of pix0
+    movu           m4, [r2 + r3]          ; row 1 of pix1
+
+    psadbw         m1, m2
+    psadbw         m3, m4
+    paddd          m0, m1
+    paddd          m0, m3
+%assign x x+1
+  %if x < 32
+    lea     r2,     [r2 + 2 * r3]
+    lea     r0,     [r0 + 2 * r1]
+  %endif
+%endrep
+    vextracti128   xm1, m0, 1
+    paddd          xm0, xm1
+    pshufd         xm1, xm0, 2
+    paddd          xm0,xm1
+    movd           eax, xm0
+    RET
+
+INIT_YMM avx2
 cglobal pixel_sad_64x64, 4,4,5
     xorps           m0, m0