[x265] [PATCH Review Only] asm-avx2: intra_pred_ang8_33, improved 265.79c -> 185.43c over sse4 asm code

[praveen at multicorewareinc.com]

# HG changeset patch
# User Praveen Tiwari <praveen at multicorewareinc.com>
# Date 1424854196 -19800
# Node ID 177fe9372668b4824c291e967349664766688179
# Parent  02bac78bde961d60d180e59b5260fad93b98d9b4
asm-avx2: intra_pred_ang8_33, improved 265.79c -> 185.43c over sse4 asm code

intra_ang_8x8[33]       10.56x   185.43          1957.47

diff -r 02bac78bde96 -r 177fe9372668 source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Wed Feb 25 13:46:58 2015 +0530
+++ b/source/common/x86/asm-primitives.cpp	Wed Feb 25 14:19:56 2015 +0530
@@ -1813,6 +1813,7 @@
 
         // intra_pred functions
         p.cu[BLOCK_8x8].intra_pred[3] = x265_intra_pred_ang8_3_avx2;
+        p.cu[BLOCK_8x8].intra_pred[33] = x265_intra_pred_ang8_33_avx2;
     }
 }
 #endif // if HIGH_BIT_DEPTH
diff -r 02bac78bde96 -r 177fe9372668 source/common/x86/intrapred.h
--- a/source/common/x86/intrapred.h	Wed Feb 25 13:46:58 2015 +0530
+++ b/source/common/x86/intrapred.h	Wed Feb 25 14:19:56 2015 +0530
@@ -158,6 +158,7 @@
 
 #undef DECL_ANG
 void x265_intra_pred_ang8_3_avx2(pixel* dst, intptr_t dstStride, const pixel* srcPix, int dirMode, int bFilter);
+void x265_intra_pred_ang8_33_avx2(pixel* dst, intptr_t dstStride, const pixel* srcPix, int dirMode, int bFilter);
 void x265_all_angs_pred_4x4_sse4(pixel *dest, pixel *refPix, pixel *filtPix, int bLuma);
 void x265_all_angs_pred_8x8_sse4(pixel *dest, pixel *refPix, pixel *filtPix, int bLuma);
 void x265_all_angs_pred_16x16_sse4(pixel *dest, pixel *refPix, pixel *filtPix, int bLuma);
diff -r 02bac78bde96 -r 177fe9372668 source/common/x86/intrapred8.asm
--- a/source/common/x86/intrapred8.asm	Wed Feb 25 13:46:58 2015 +0530
+++ b/source/common/x86/intrapred8.asm	Wed Feb 25 14:19:56 2015 +0530
@@ -32087,3 +32087,39 @@
     movq              [r0 + 2 * r1], xm2
     movhps            [r0 + r3], xm2
     RET
+
+INIT_YMM avx2
+cglobal intra_pred_ang8_33, 3,4,5
+    movu              m3, [pw_1024]
+    vbroadcasti128    m0, [r2 + 1]
+
+    pshufb            m1, m0, [c_ang8_src1_9_2_10]
+    pshufb            m2, m0, [c_ang8_src3_11_4_12]
+    pshufb            m4, m0, [c_ang8_src5_13_5_13]
+    pshufb            m4, m0, [c_ang8_src5_13_5_13]
+    pshufb            m0,     [c_ang8_src6_14_7_15]
+
+    pmaddubsw         m1, [c_ang8_26_20]
+    pmulhrsw          m1, m3
+    pmaddubsw         m2, [c_ang8_14_8]
+    pmulhrsw          m2, m3
+    pmaddubsw         m4, [c_ang8_2_28]
+    pmulhrsw          m4, m3
+    pmaddubsw         m0, [c_ang8_22_16]
+    pmulhrsw          m0, m3
+    packuswb          m1, m2
+    packuswb          m4, m0
+
+    lea               r3, [3 * r1]
+    movq              [r0], xm1
+    vextracti128      xm2, m1, 1
+    movq              [r0 + r1], xm2
+    movhps            [r0 + 2 * r1], xm1
+    movhps            [r0 + r3], xm2
+    lea               r0, [r0 + 4 * r1]
+    movq              [r0], xm4
+    vextracti128      xm2, m4, 1
+    movq              [r0 + r1], xm2
+    movhps            [r0 + 2 * r1], xm4
+    movhps            [r0 + r3], xm2
+    RET