[x265] [PATCH] asm-intra_pred_ang8_11: improved, 317.84c -> 230.29c over SSE4 asm code

[praveen at multicorewareinc.com]

# HG changeset patch
# User Praveen Tiwari <praveen at multicorewareinc.com>
# Date 1426137409 -19800
# Node ID 9630d70abbca154e2faffa0e6a4789530ef9662a
# Parent  b931c50d55011a1ddc08f0a230b9632fcb4674d7
asm-intra_pred_ang8_11: improved, 317.84c -> 230.29c over SSE4 asm code

AVX2:
intra_ang_8x8[11]       14.15x   230.29          3259.04

SSE4:
intra_ang_8x8[11]       10.25x   317.84          3258.71

diff -r b931c50d5501 -r 9630d70abbca source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Wed Mar 11 21:58:02 2015 -0500
+++ b/source/common/x86/asm-primitives.cpp	Thu Mar 12 10:46:49 2015 +0530
@@ -1501,6 +1501,7 @@
         p.cu[BLOCK_8x8].intra_pred[9] = x265_intra_pred_ang8_9_avx2;
         p.cu[BLOCK_8x8].intra_pred[27] = x265_intra_pred_ang8_27_avx2;
         p.cu[BLOCK_8x8].intra_pred[25] = x265_intra_pred_ang8_25_avx2;
+        p.cu[BLOCK_8x8].intra_pred[11] = x265_intra_pred_ang8_11_avx2;
 
         // copy_sp primitives
         p.cu[BLOCK_16x16].copy_sp = x265_blockcopy_sp_16x16_avx2;
diff -r b931c50d5501 -r 9630d70abbca source/common/x86/intrapred.h
--- a/source/common/x86/intrapred.h	Wed Mar 11 21:58:02 2015 -0500
+++ b/source/common/x86/intrapred.h	Thu Mar 12 10:46:49 2015 +0530
@@ -179,6 +179,7 @@
 void x265_intra_pred_ang8_9_avx2(pixel* dst, intptr_t dstStride, const pixel* srcPix, int dirMode, int bFilter);
 void x265_intra_pred_ang8_27_avx2(pixel* dst, intptr_t dstStride, const pixel* srcPix, int dirMode, int bFilter);
 void x265_intra_pred_ang8_25_avx2(pixel* dst, intptr_t dstStride, const pixel* srcPix, int dirMode, int bFilter);
+void x265_intra_pred_ang8_11_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 b931c50d5501 -r 9630d70abbca source/common/x86/intrapred8.asm
--- a/source/common/x86/intrapred8.asm	Wed Mar 11 21:58:02 2015 -0500
+++ b/source/common/x86/intrapred8.asm	Thu Mar 12 10:46:49 2015 +0530
@@ -10317,3 +10317,48 @@
     movhps            [r0 + 2 * r1], xm4
     movhps            [r0 + r3], xm2
     RET
+
+
+INIT_YMM avx2
+cglobal intra_pred_ang8_11, 3, 5, 5
+    mova              m3, [pw_1024]
+    movu              xm1, [r2 + 16]
+    pinsrb            xm1, [r2], 0
+    pshufb            xm1, [intra_pred_shuff_0_8]
+    vinserti128       m0, m1, xm1, 1
+
+    lea               r4, [c_ang8_mode_25]
+    pmaddubsw         m1, m0, [r4]
+    pmulhrsw          m1, m3
+    pmaddubsw         m2, m0, [r4 + mmsize]
+    pmulhrsw          m2, m3
+    pmaddubsw         m4, m0, [r4 + 2 * mmsize]
+    pmulhrsw          m4, m3
+    pmaddubsw         m0, [r4 + 3 * mmsize]
+    pmulhrsw          m0, m3
+    packuswb          m1, m2
+    packuswb          m4, m0
+
+    vperm2i128        m2, m1, m4, 00100000b
+    vperm2i128        m1, m1, m4, 00110001b
+    punpcklbw         m4, m2, m1
+    punpckhbw         m2, m1
+    punpcklwd         m1, m4, m2
+    punpckhwd         m4, m2
+    mova              m0, [trans8_shuf]
+    vpermd            m1, m0, m1
+    vpermd            m4, m0, m4
+
+    lea               r3, [3 * r1]
+    movq              [r0], xm1
+    movhps            [r0 + r1], xm1
+    vextracti128      xm2, m1, 1
+    movq              [r0 + 2 * r1], xm2
+    movhps            [r0 + r3], xm2
+    lea               r0, [r0 + 4 * r1]
+    movq              [r0], xm4
+    movhps            [r0 + r1], xm4
+    vextracti128      xm2, m4, 1
+    movq              [r0 + 2 * r1], xm2
+    movhps            [r0 + r3], xm2
+    RET