[x265] [PATCH 3 of 8] asm:intra_pred_ang4_4_sse2

[dtyx265 at gmail.com]

# HG changeset patch
# User David T Yuen <dtyx265 at gmail.com>
# Date 1427140402 25200
# Node ID f41f56fc0438049de9c25ef609910af3a22168a4
# Parent  ac02f1184aa554cb2d3adbe688493f88f15cbd59
asm:intra_pred_ang4_4_sse2

This is backported from sse4 code and replaces c code.

64-bit

./test/TestBench --testbench intrapred | grep "intra_ang_4x4\[ 4\]"
intra_ang_4x4[ 4]	2.74x 	 709.98   	 1947.60

32-bit

./test/TestBench --testbench intrapred | grep "intra_ang_4x4\[ 4\]"
intra_ang_4x4[ 4]	3.97x 	 747.49   	 2970.13

diff -r ac02f1184aa5 -r f41f56fc0438 source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Mon Mar 23 12:35:33 2015 -0700
+++ b/source/common/x86/asm-primitives.cpp	Mon Mar 23 12:53:22 2015 -0700
@@ -1198,6 +1198,7 @@
 
         p.cu[BLOCK_4x4].intra_pred[2] = x265_intra_pred_ang4_2_sse2;
         p.cu[BLOCK_4x4].intra_pred[3] = x265_intra_pred_ang4_3_sse2;
+        p.cu[BLOCK_4x4].intra_pred[4] = x265_intra_pred_ang4_4_sse2;
 
         p.cu[BLOCK_4x4].calcresidual = x265_getResidual4_sse2;
         p.cu[BLOCK_8x8].calcresidual = x265_getResidual8_sse2;
diff -r ac02f1184aa5 -r f41f56fc0438 source/common/x86/intrapred.h
--- a/source/common/x86/intrapred.h	Mon Mar 23 12:35:33 2015 -0700
+++ b/source/common/x86/intrapred.h	Mon Mar 23 12:53:22 2015 -0700
@@ -49,6 +49,7 @@
 
 DECL_ANG(4, 2, sse2);
 DECL_ANG(4, 3, sse2);
+DECL_ANG(4, 4, sse2);
 
 DECL_ANG(4, 2, ssse3);
 DECL_ANG(4, 3, sse4);
diff -r ac02f1184aa5 -r f41f56fc0438 source/common/x86/intrapred8.asm
--- a/source/common/x86/intrapred8.asm	Mon Mar 23 12:35:33 2015 -0700
+++ b/source/common/x86/intrapred8.asm	Mon Mar 23 12:53:22 2015 -0700
@@ -1215,6 +1215,31 @@
     movd        [r0 + r1], m0
     RET
 
+cglobal intra_pred_ang4_4, 3,5,8
+    xor         r4, r4
+    inc         r4
+    cmp         r3m, byte 32
+    mov         r3, 9
+    cmove       r3, r4
+
+    movh        m0, [r2 + r3]    ; [8 7 6 5 4 3 2 1]
+    mova        m1, m0
+    psrldq      m1, 1           ; [x 8 7 6 5 4 3 2]
+    punpcklbw   m0, m1          ; [x 8 8 7 7 6 6 5 5 4 4 3 3 2 2 1]
+    mova        m1, m0
+    psrldq      m1, 2           ; [x x x x x x x x 6 5 5 4 4 3 3 2]
+    mova        m3, m0
+    psrldq      m3, 4           ; [x x x x x x x x 7 6 6 5 5 4 4 3]
+    punpcklqdq  m0, m1
+    punpcklqdq  m2, m1, m3
+
+    lea         r3, [pw_ang_table + 18 * 16]
+    mova        m4, [r3 +  3 * 16]  ; [21]
+    mova        m5, [r3 -  8 * 16]  ; [10]
+    mova        m6, [r3 + 13 * 16]  ; [31]
+    mova        m7, [r3 +  2 * 16]  ; [20]
+    jmp         mangle(private_prefix %+ _ %+ intra_pred_ang4_3 %+ SUFFIX %+ .do_filter4x4)
+
 ;---------------------------------------------------------------------------------------------
 ; void intra_pred_dc(pixel* dst, intptr_t dstStride, pixel *srcPix, int dirMode, int bFilter)
 ;---------------------------------------------------------------------------------------------