[x265] [PATCH] asm: intra_pred_dc32 high_bit_depth code

[dnyaneshwar at multicorewareinc.com]

# HG changeset patch
# User Dnyaneshwar G <dnyaneshwar at multicorewareinc.com>
# Date 1431408860 -19800
#      Tue May 12 11:04:20 2015 +0530
# Node ID 5bf9096a4d93fd8c47e9c81e3dafba5d37391114
# Parent  f2081ef64fd27dfd3a5bec92ee1a835a74061761
asm: intra_pred_dc32 high_bit_depth code

AVX2:
intra_dc_32x32    19.36x   780.92          15118.54

SSE:
intra_dc_32x32    10.41x   1457.15         15167.84

diff -r f2081ef64fd2 -r 5bf9096a4d93 source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Mon May 11 18:50:03 2015 -0500
+++ b/source/common/x86/asm-primitives.cpp	Tue May 12 11:04:20 2015 +0530
@@ -1181,6 +1181,8 @@
     }
     if (cpuMask & X265_CPU_AVX2)
     {
+        p.cu[BLOCK_32x32].intra_pred[DC_IDX] = x265_intra_pred_dc32_avx2;
+
         p.pu[LUMA_48x64].satd = x265_pixel_satd_48x64_avx2;
 
         p.pu[LUMA_64x16].satd = x265_pixel_satd_64x16_avx2;
diff -r f2081ef64fd2 -r 5bf9096a4d93 source/common/x86/intrapred16.asm
--- a/source/common/x86/intrapred16.asm	Mon May 11 18:50:03 2015 -0500
+++ b/source/common/x86/intrapred16.asm	Tue May 12 11:04:20 2015 +0530
@@ -448,6 +448,106 @@
 %endrep
     RET
 
+;---------------------------------------------------------------------------------------------
+; void intra_pred_dc(pixel* dst, intptr_t dstStride, pixel *srcPix, int dirMode, int bFilter)
+;---------------------------------------------------------------------------------------------
+INIT_YMM avx2
+cglobal intra_pred_dc32, 3, 3, 2
+    add              r2, 2
+    add             r1d, r1d
+    movu             m0, [r2]
+    movu             m1, [r2 + 32]
+    add              r2, mmsize*4        ; r2 += 128
+    paddw            m0, m1
+    movu             m1, [r2]
+    paddw            m0, m1
+    movu             m1, [r2 + 32]
+    paddw            m0, m1
+    vextracti128    xm1, m0, 1
+    paddw           xm0, xm1
+    movhlps         xm1, xm0
+    paddw           xm0, xm1
+    phaddw          xm0, xm0
+    pmaddwd         xm0, [pw_1]
+    paddd           xm0, [pd_32]         ; sum = sum + 32
+    psrld           xm0, 6               ; sum = sum / 64
+    vpbroadcastw     m0, xm0
+
+    lea              r2, [r1 * 3]
+    ; store DC 32x32
+    movu            [r0 + r1 * 0 +  0], m0
+    movu            [r0 + r1 * 0 + mmsize], m0
+    movu            [r0 + r1 * 1 +  0], m0
+    movu            [r0 + r1 * 1 + mmsize], m0
+    movu            [r0 + r1 * 2 +  0], m0
+    movu            [r0 + r1 * 2 + mmsize], m0
+    movu            [r0 + r2 * 1 +  0], m0
+    movu            [r0 + r2 * 1 + mmsize], m0
+    lea             r0, [r0 + r1 * 4]
+    movu            [r0 + r1 * 0 +  0], m0
+    movu            [r0 + r1 * 0 + mmsize], m0
+    movu            [r0 + r1 * 1 +  0], m0
+    movu            [r0 + r1 * 1 + mmsize], m0
+    movu            [r0 + r1 * 2 +  0], m0
+    movu            [r0 + r1 * 2 + mmsize], m0
+    movu            [r0 + r2 * 1 +  0], m0
+    movu            [r0 + r2 * 1 + mmsize], m0
+    lea             r0, [r0 + r1 * 4]
+    movu            [r0 + r1 * 0 +  0], m0
+    movu            [r0 + r1 * 0 + mmsize], m0
+    movu            [r0 + r1 * 1 +  0], m0
+    movu            [r0 + r1 * 1 + mmsize], m0
+    movu            [r0 + r1 * 2 +  0], m0
+    movu            [r0 + r1 * 2 + mmsize], m0
+    movu            [r0 + r2 * 1 +  0], m0
+    movu            [r0 + r2 * 1 + mmsize], m0
+    lea             r0, [r0 + r1 * 4]
+    movu            [r0 + r1 * 0 +  0], m0
+    movu            [r0 + r1 * 0 + mmsize], m0
+    movu            [r0 + r1 * 1 +  0], m0
+    movu            [r0 + r1 * 1 + mmsize], m0
+    movu            [r0 + r1 * 2 +  0], m0
+    movu            [r0 + r1 * 2 + mmsize], m0
+    movu            [r0 + r2 * 1 +  0], m0
+    movu            [r0 + r2 * 1 + mmsize], m0
+    lea             r0, [r0 + r1 * 4]
+    movu            [r0 + r1 * 0 +  0], m0
+    movu            [r0 + r1 * 0 + mmsize], m0
+    movu            [r0 + r1 * 1 +  0], m0
+    movu            [r0 + r1 * 1 + mmsize], m0
+    movu            [r0 + r1 * 2 +  0], m0
+    movu            [r0 + r1 * 2 + mmsize], m0
+    movu            [r0 + r2 * 1 +  0], m0
+    movu            [r0 + r2 * 1 + mmsize], m0
+    lea             r0, [r0 + r1 * 4]
+    movu            [r0 + r1 * 0 +  0], m0
+    movu            [r0 + r1 * 0 + mmsize], m0
+    movu            [r0 + r1 * 1 +  0], m0
+    movu            [r0 + r1 * 1 + mmsize], m0
+    movu            [r0 + r1 * 2 +  0], m0
+    movu            [r0 + r1 * 2 + mmsize], m0
+    movu            [r0 + r2 * 1 +  0], m0
+    movu            [r0 + r2 * 1 + mmsize], m0
+    lea             r0, [r0 + r1 * 4]
+    movu            [r0 + r1 * 0 +  0], m0
+    movu            [r0 + r1 * 0 + mmsize], m0
+    movu            [r0 + r1 * 1 +  0], m0
+    movu            [r0 + r1 * 1 + mmsize], m0
+    movu            [r0 + r1 * 2 +  0], m0
+    movu            [r0 + r1 * 2 + mmsize], m0
+    movu            [r0 + r2 * 1 +  0], m0
+    movu            [r0 + r2 * 1 + mmsize], m0
+    lea             r0, [r0 + r1 * 4]
+    movu            [r0 + r1 * 0 +  0], m0
+    movu            [r0 + r1 * 0 + mmsize], m0
+    movu            [r0 + r1 * 1 +  0], m0
+    movu            [r0 + r1 * 1 + mmsize], m0
+    movu            [r0 + r1 * 2 +  0], m0
+    movu            [r0 + r1 * 2 + mmsize], m0
+    movu            [r0 + r2 * 1 +  0], m0
+    movu            [r0 + r2 * 1 + mmsize], m0
+    RET
+
 ;---------------------------------------------------------------------------------------
 ; void intra_pred_planar(pixel* dst, intptr_t dstStride, pixel*srcPix, int, int filter)
 ;---------------------------------------------------------------------------------------