[x265] [PATCH 7 of 8] asm:intra_pred_ang4_8_sse2

[dtyx265 at gmail.com]

# HG changeset patch
# User David T Yuen <dtyx265 at gmail.com>
# Date 1427142143 25200
# Node ID 285479649d24146867b809d7a00644ff5c645656
# Parent  9c51376d86b1be78104c3b0dd0f1ed8daeb11918
asm:intra_pred_ang4_8_sse2

This is backported from sse4 code and replaces c code.

64-bit

./test/TestBench --testbench intrapred | grep "intra_ang_4x4\[ 8\]"
intra_ang_4x4[ 8]	3.04x 	 640.00   	 1942.47

32-bit

./test/TestBench --testbench intrapred | grep "intra_ang_4x4\[ 8\]"
intra_ang_4x4[ 8]	3.97x 	 722.50   	 2864.98

diff -r 9c51376d86b1 -r 285479649d24 source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Mon Mar 23 13:18:33 2015 -0700
+++ b/source/common/x86/asm-primitives.cpp	Mon Mar 23 13:22:23 2015 -0700
@@ -1202,6 +1202,7 @@
         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].intra_pred[8] = x265_intra_pred_ang4_8_sse2;
 
         p.cu[BLOCK_4x4].calcresidual = x265_getResidual4_sse2;
         p.cu[BLOCK_8x8].calcresidual = x265_getResidual8_sse2;
diff -r 9c51376d86b1 -r 285479649d24 source/common/x86/intrapred.h
--- a/source/common/x86/intrapred.h	Mon Mar 23 13:18:33 2015 -0700
+++ b/source/common/x86/intrapred.h	Mon Mar 23 13:22:23 2015 -0700
@@ -53,6 +53,7 @@
 DECL_ANG(4, 5, sse2);
 DECL_ANG(4, 6, sse2);
 DECL_ANG(4, 7, sse2);
+DECL_ANG(4, 8, sse2);
 
 DECL_ANG(4, 2, ssse3);
 DECL_ANG(4, 3, sse4);
diff -r 9c51376d86b1 -r 285479649d24 source/common/x86/intrapred8.asm
--- a/source/common/x86/intrapred8.asm	Mon Mar 23 13:18:33 2015 -0700
+++ b/source/common/x86/intrapred8.asm	Mon Mar 23 13:22:23 2015 -0700
@@ -1311,6 +1311,27 @@
     mova        m7, [r3 - 16 * 16]  ; [ 4]
     jmp         mangle(private_prefix %+ _ %+ intra_pred_ang4_3 %+ SUFFIX %+ .do_filter4x4)
 
+cglobal intra_pred_ang4_8, 3,5,8
+    xor         r4, r4
+    inc         r4
+    cmp         r3m, byte 28
+    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]
+    punpcklqdq  m0, m0
+    mova        m2, m0
+
+    lea         r3, [pw_ang_table + 13 * 16]
+    mova        m4, [r3 -  8 * 16]  ; [ 5]
+    mova        m5, [r3 -  3 * 16]  ; [10]
+    mova        m6, [r3 +  2 * 16]  ; [15]
+    mova        m7, [r3 +  7 * 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)
 ;---------------------------------------------------------------------------------------------