[x265] [PATCH] asm-avx2: intra_pred_ang8_9

[chen]

right



At 2015-03-06 12:02:26,praveen at multicorewareinc.com wrote:
># HG changeset patch
># User Praveen Tiwari <praveen at multicorewareinc.com>
># Date 1425614537 -19800
># Node ID fe9c058f216d4315ea995b09384aab2b1a28d1ec
># Parent  bc78f328b894d302bd4f58a43f21189212baa2a2
>asm-avx2: intra_pred_ang8_9
>
>diff -r bc78f328b894 -r fe9c058f216d source/common/x86/asm-primitives.cpp
>--- a/source/common/x86/asm-primitives.cpp	Fri Mar 06 09:17:28 2015 +0530
>+++ b/source/common/x86/asm-primitives.cpp	Fri Mar 06 09:32:17 2015 +0530
>@@ -1510,6 +1510,7 @@
>         p.cu[BLOCK_8x8].intra_pred[29] = x265_intra_pred_ang8_29_avx2;
>         p.cu[BLOCK_8x8].intra_pred[8] = x265_intra_pred_ang8_8_avx2;
>         p.cu[BLOCK_8x8].intra_pred[28] = x265_intra_pred_ang8_28_avx2;
>+        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;
> 
>         // copy_sp primitives
>diff -r bc78f328b894 -r fe9c058f216d source/common/x86/intrapred.h
>--- a/source/common/x86/intrapred.h	Fri Mar 06 09:17:28 2015 +0530
>+++ b/source/common/x86/intrapred.h	Fri Mar 06 09:32:17 2015 +0530
>@@ -173,6 +173,7 @@
> void x265_intra_pred_ang8_29_avx2(pixel* dst, intptr_t dstStride, const pixel* srcPix, int dirMode, int bFilter);
> void x265_intra_pred_ang8_8_avx2(pixel* dst, intptr_t dstStride, const pixel* srcPix, int dirMode, int bFilter);
> void x265_intra_pred_ang8_28_avx2(pixel* dst, intptr_t dstStride, const pixel* srcPix, int dirMode, int bFilter);
>+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_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);
>diff -r bc78f328b894 -r fe9c058f216d source/common/x86/intrapred8.asm
>--- a/source/common/x86/intrapred8.asm	Fri Mar 06 09:17:28 2015 +0530
>+++ b/source/common/x86/intrapred8.asm	Fri Mar 06 09:32:17 2015 +0530
>@@ -32981,6 +32981,51 @@
>     movhps            [r0 + r3], xm2
>     RET
> 
>+
>+INIT_YMM avx2
>+cglobal intra_pred_ang8_9, 3, 5, 6
>+    mova              m3, [pw_1024]
>+    vbroadcasti128    m0, [r2 + 17]
>+    movu              m5, [c_ang8_src1_9_1_9]
>+
>+    pshufb            m0, m5
>+
>+    lea               r4, [c_ang8_mode_27]
>+    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
>+
> INIT_YMM avx2
> cglobal intra_pred_ang8_27, 3, 5, 6
>     mova              m3, [pw_1024]
>_______________________________________________
>x265-devel mailing list
>x265-devel at videolan.org
>https://mailman.videolan.org/listinfo/x265-devel
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.videolan.org/pipermail/x265-devel/attachments/20150307/7d835ed0/attachment-0001.html>