[x265] [PATCH] asm: addAvg avx2 code for chroma sizes width >= 8, reused code from luma

[dnyaneshwar at multicorewareinc.com]

# HG changeset patch
# User Dnyaneshwar G <dnyaneshwar at multicorewareinc.com>
# Date 1426745611 -19800
#      Thu Mar 19 11:43:31 2015 +0530
# Node ID d2b99b5edfde84bd4ad22daaca6f87662d46c2df
# Parent  2807d9a5a494de78340ab6d09867205b6676330b
asm: addAvg avx2 code for chroma sizes width >= 8, reused code from luma

AVX2:
addAvg[  8x2]  7.79x    84.28           656.61
addAvg[  8x6]  10.92x   334.48          3654.07

SSE4:
addAvg[  8x2]  7.50x    89.67           672.36
addAvg[  8x6]  10.74x   342.18          3673.41

diff -r 2807d9a5a494 -r d2b99b5edfde source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Thu Mar 19 11:22:06 2015 +0530
+++ b/source/common/x86/asm-primitives.cpp	Thu Mar 19 11:43:31 2015 +0530
@@ -1446,6 +1446,26 @@
         p.pu[LUMA_64x48].addAvg = x265_addAvg_64x48_avx2;
         p.pu[LUMA_64x64].addAvg = x265_addAvg_64x64_avx2;
 
+        p.chroma[X265_CSP_I420].pu[CHROMA_420_8x2].addAvg = x265_addAvg_8x2_avx2;
+        p.chroma[X265_CSP_I420].pu[CHROMA_420_8x4].addAvg = x265_addAvg_8x4_avx2;
+        p.chroma[X265_CSP_I420].pu[CHROMA_420_8x6].addAvg = x265_addAvg_8x6_avx2;
+        p.chroma[X265_CSP_I420].pu[CHROMA_420_8x8].addAvg = x265_addAvg_8x8_avx2;
+        p.chroma[X265_CSP_I420].pu[CHROMA_420_8x16].addAvg = x265_addAvg_8x16_avx2;
+        p.chroma[X265_CSP_I420].pu[CHROMA_420_8x32].addAvg = x265_addAvg_8x32_avx2;
+
+        p.chroma[X265_CSP_I420].pu[CHROMA_420_12x16].addAvg = x265_addAvg_12x16_avx2;
+
+        p.chroma[X265_CSP_I420].pu[CHROMA_420_16x4].addAvg = x265_addAvg_16x4_avx2;
+        p.chroma[X265_CSP_I420].pu[CHROMA_420_16x8].addAvg = x265_addAvg_16x8_avx2;
+        p.chroma[X265_CSP_I420].pu[CHROMA_420_16x12].addAvg = x265_addAvg_16x12_avx2;
+        p.chroma[X265_CSP_I420].pu[CHROMA_420_16x16].addAvg = x265_addAvg_16x16_avx2;
+        p.chroma[X265_CSP_I420].pu[CHROMA_420_16x32].addAvg = x265_addAvg_16x32_avx2;
+
+        p.chroma[X265_CSP_I420].pu[CHROMA_420_32x8].addAvg = x265_addAvg_32x8_avx2;
+        p.chroma[X265_CSP_I420].pu[CHROMA_420_32x16].addAvg = x265_addAvg_32x16_avx2;
+        p.chroma[X265_CSP_I420].pu[CHROMA_420_32x24].addAvg = x265_addAvg_32x24_avx2;
+        p.chroma[X265_CSP_I420].pu[CHROMA_420_32x32].addAvg = x265_addAvg_32x32_avx2;
+
         p.cu[BLOCK_16x16].add_ps = x265_pixel_add_ps_16x16_avx2;
         p.cu[BLOCK_32x32].add_ps = x265_pixel_add_ps_32x32_avx2;
         p.cu[BLOCK_64x64].add_ps = x265_pixel_add_ps_64x64_avx2;
diff -r 2807d9a5a494 -r d2b99b5edfde source/common/x86/mc-a.asm
--- a/source/common/x86/mc-a.asm	Thu Mar 19 11:22:06 2015 +0530
+++ b/source/common/x86/mc-a.asm	Thu Mar 19 11:43:31 2015 +0530
@@ -1762,6 +1762,84 @@
 ; addAvg avx2 code start
 ;-----------------------------------------------------------------------------
 
+INIT_YMM avx2
+cglobal addAvg_8x2, 6,6,4, pSrc0, src0, src1, dst, src0Stride, src1tride, dstStride
+    movu            xm0, [r0]
+    vinserti128     m0, m0, [r0 + 2 * r3], 1
+
+    movu            xm2, [r1]
+    vinserti128     m2, m2, [r1 + 2 * r4], 1
+
+    paddw           m0, m2
+    pmulhrsw        m0, [pw_256]
+    paddw           m0, [pw_128]
+
+    packuswb        m0, m0
+    vextracti128    xm1, m0, 1
+    movq            [r2], xm0
+    movq            [r2 + r5], xm1
+    RET
+
+cglobal addAvg_8x6, 6,6,6, pSrc0, src0, src1, dst, src0Stride, src1tride, dstStride
+    mova            m4, [pw_256]
+    mova            m5, [pw_128]
+    add             r3, r3
+    add             r4, r4
+
+    movu            xm0, [r0]
+    vinserti128     m0, m0, [r0 + r3], 1
+
+    movu            xm2, [r1]
+    vinserti128     m2, m2, [r1 + r4], 1
+
+    paddw           m0, m2
+    pmulhrsw        m0, m4
+    paddw           m0, m5
+
+    packuswb        m0, m0
+    vextracti128    xm1, m0, 1
+    movq            [r2], xm0
+    movq            [r2 + r5], xm1
+
+    lea             r2, [r2 + 2 * r5]
+    lea             r0, [r0 + 2 * r3]
+    lea             r1, [r1 + 2 * r4]
+
+    movu            xm0, [r0]
+    vinserti128     m0, m0, [r0+  r3], 1
+
+    movu            xm2, [r1]
+    vinserti128     m2, m2, [r1 + r4], 1
+
+    paddw           m0, m2
+    pmulhrsw        m0, m4
+    paddw           m0, m5
+
+    packuswb        m0, m0
+    vextracti128    xm1, m0, 1
+    movq            [r2], xm0
+    movq            [r2 + r5], xm1
+
+    lea             r2, [r2 + 2 * r5]
+    lea             r0, [r0 + 2 * r3]
+    lea             r1, [r1 + 2 * r4]
+
+    movu            xm0, [r0]
+    vinserti128     m0, m0, [r0 + r3], 1
+
+    movu            xm2, [r1]
+    vinserti128     m2, m2, [r1 + r4], 1
+
+    paddw           m0, m2
+    pmulhrsw        m0, m4
+    paddw           m0, m5
+
+    packuswb        m0, m0
+    vextracti128    xm1, m0, 1
+    movq            [r2], xm0
+    movq            [r2 + r5], xm1
+    RET
+
 %macro ADDAVG_W8_H4_AVX2 1
 INIT_YMM avx2
 cglobal addAvg_8x%1, 6,7,6, pSrc0, src0, src1, dst, src0Stride, src1tride, dstStride