[x265] [PATCH 6 of 8] asm:intra_pred_ang4_7_sse2

[dtyx265 at gmail.com]

# HG changeset patch
# User David T Yuen <dtyx265 at gmail.com>
# Date 1427141913 25200
# Node ID 9c51376d86b1be78104c3b0dd0f1ed8daeb11918
# Parent  36d7d61899a2a184241491d8512e151dab5abc2b
asm:intra_pred_ang4_7_sse2

This is backported from sse4 code and replaces c code.

64-bit

./test/TestBench --testbench intrapred | grep "intra_ang_4x4\[ 7\]"
intra_ang_4x4[ 7]	2.77x 	 655.00   	 1817.47

32-bit

./test/TestBench --testbench intrapred | grep "intra_ang_4x4\[ 7\]"
intra_ang_4x4[ 7]	3.56x 	 762.50   	 2714.98

diff -r 36d7d61899a2 -r 9c51376d86b1 source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Mon Mar 23 13:01:36 2015 -0700
+++ b/source/common/x86/asm-primitives.cpp	Mon Mar 23 13:18:33 2015 -0700
@@ -1201,6 +1201,7 @@
         p.cu[BLOCK_4x4].intra_pred[4] = x265_intra_pred_ang4_4_sse2;
         p.cu[BLOCK_4x4].intra_pred[5] = x265_intra_pred_ang4_5_sse2;
         p.cu[BLOCK_4x4].intra_pred[6] = x265_intra_pred_ang4_6_sse2;
+        p.cu[BLOCK_4x4].intra_pred[7] = x265_intra_pred_ang4_7_sse2;
 
         p.cu[BLOCK_4x4].calcresidual = x265_getResidual4_sse2;
         p.cu[BLOCK_8x8].calcresidual = x265_getResidual8_sse2;
diff -r 36d7d61899a2 -r 9c51376d86b1 source/common/x86/intrapred.h
--- a/source/common/x86/intrapred.h	Mon Mar 23 13:01:36 2015 -0700
+++ b/source/common/x86/intrapred.h	Mon Mar 23 13:18:33 2015 -0700
@@ -52,6 +52,7 @@
 DECL_ANG(4, 4, sse2);
 DECL_ANG(4, 5, sse2);
 DECL_ANG(4, 6, sse2);
+DECL_ANG(4, 7, sse2);
 
 DECL_ANG(4, 2, ssse3);
 DECL_ANG(4, 3, sse4);
diff -r 36d7d61899a2 -r 9c51376d86b1 source/common/x86/intrapred8.asm
--- a/source/common/x86/intrapred8.asm	Mon Mar 23 13:01:36 2015 -0700
+++ b/source/common/x86/intrapred8.asm	Mon Mar 23 13:18:33 2015 -0700
@@ -1288,6 +1288,29 @@
     mova        m7, [r3 +  1 * 16]  ; [20]
     jmp         mangle(private_prefix %+ _ %+ intra_pred_ang4_3 %+ SUFFIX %+ .do_filter4x4)
 
+cglobal intra_pred_ang4_7, 3,5,8
+    xor         r4, r4
+    inc         r4
+    cmp         r3m, byte 29
+    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        m3, m0
+    psrldq      m3, 2           ; [x x x x x x x x 6 5 5 4 4 3 3 2]
+    punpcklqdq  m2, m0, m3
+    punpcklqdq  m0, m0
+
+    lea         r3, [pw_ang_table + 20 * 16]
+    mova        m4, [r3 - 11 * 16]  ; [ 9]
+    mova        m5, [r3 -  2 * 16]  ; [18]
+    mova        m6, [r3 +  7 * 16]  ; [27]
+    mova        m7, [r3 - 16 * 16]  ; [ 4]
+    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)
 ;---------------------------------------------------------------------------------------------