[x265] [PATCH] asm-avx2: intra_pred_ang8_11

chen chenm003 at 163.com
Mon Mar 9 21:40:04 CET 2015


 

At 2015-03-09 17:17:46,praveen at multicorewareinc.com wrote:
># HG changeset patch
># User Praveen Tiwari <praveen at multicorewareinc.com>
># Date 1425892546 -19800
># Node ID 243800689d05b42fb15fdab041d015fa5d2dcb8b
># Parent  fb4c73f908b8e6fe93299f83a8b2175780cd402e
>asm-avx2: intra_pred_ang8_11
>
>diff -r fb4c73f908b8 -r 243800689d05 source/common/x86/asm-primitives.cpp
>--- a/source/common/x86/asm-primitives.cpp	Mon Mar 09 14:10:04 2015 +0530
>+++ b/source/common/x86/asm-primitives.cpp	Mon Mar 09 14:45:46 2015 +0530
>@@ -1495,6 +1495,7 @@
>         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;
>+        p.cu[BLOCK_8x8].intra_pred[11] = x265_intra_pred_ang8_11_avx2;
>         p.cu[BLOCK_8x8].intra_pred[25] = x265_intra_pred_ang8_25_avx2;
> 
>         // copy_sp primitives
>diff -r fb4c73f908b8 -r 243800689d05 source/common/x86/intrapred.h
>--- a/source/common/x86/intrapred.h	Mon Mar 09 14:10:04 2015 +0530
>+++ b/source/common/x86/intrapred.h	Mon Mar 09 14:45:46 2015 +0530
>@@ -178,6 +178,7 @@
> 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_intra_pred_ang8_11_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_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 fb4c73f908b8 -r 243800689d05 source/common/x86/intrapred8.asm
>--- a/source/common/x86/intrapred8.asm	Mon Mar 09 14:10:04 2015 +0530
>+++ b/source/common/x86/intrapred8.asm	Mon Mar 09 14:45:46 2015 +0530
>@@ -33287,3 +33287,49 @@
>     movhps            [r0 + 2 * r1], xm4
>     movhps            [r0 + r3], xm2
>     RET
>+
>+INIT_YMM avx2
>+cglobal intra_pred_ang8_11, 3, 5, 6
when you do below modify, you may reduce m5

>+    mova              m3, [pw_1024]
>+    movu              xm1, [r2 + 16]
>+    pinsrb            xm1, [r2], 0
>+    vinserti128       m0, m1, xm1, 1

+
>+    mova              m5, [c_ang8_src1_9_1_9]
>+    pshufb            m0, m5

you just use  [c_ang8_src1_9_1_9] once, so may combo pshufb and aligned constant
>+
>+    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
>_______________________________________________
>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/20150310/6af1c805/attachment.html>


More information about the x265-devel mailing list