[x265] [PATCH] asm: intra_pred_ang8_12 8bpp, improved 360.00c -> 259.13c

[chen]

right, just improve on [trans8_shuf] in future

At 2015-03-10 16:33:43,praveen at multicorewareinc.com wrote:
># HG changeset patch
># User Praveen Tiwari <praveen at multicorewareinc.com>
># Date 1425976286 -19800
># Node ID fc805c02d0f28815e86e65c2f6d0bfea69db0f7b
># Parent  f79f44d2e55fa9ddb88955a5ffa136efa550ca8f
>asm: intra_pred_ang8_12 8bpp, improved 360.00c -> 259.13c
>
>AVX2:
>intra_ang_8x8[12]       12.92x   259.13          3349.04
>
>SSE4:
>intra_ang_8x8[12]       9.15x    360.00          3295.50
>
>diff -r f79f44d2e55f -r fc805c02d0f2 source/common/x86/asm-primitives.cpp
>--- a/source/common/x86/asm-primitives.cpp	Tue Mar 10 12:44:28 2015 +0530
>+++ b/source/common/x86/asm-primitives.cpp	Tue Mar 10 14:01:26 2015 +0530
>@@ -1497,6 +1497,7 @@
>         p.cu[BLOCK_8x8].intra_pred[27] = x265_intra_pred_ang8_27_avx2;
>         p.cu[BLOCK_8x8].intra_pred[25] = x265_intra_pred_ang8_25_avx2;
>         p.cu[BLOCK_8x8].intra_pred[11] = x265_intra_pred_ang8_11_avx2;
>+        p.cu[BLOCK_8x8].intra_pred[12] = x265_intra_pred_ang8_12_avx2;
>         p.cu[BLOCK_8x8].intra_pred[24] = x265_intra_pred_ang8_24_avx2;
> 
>         // copy_sp primitives
>diff -r f79f44d2e55f -r fc805c02d0f2 source/common/x86/intrapred.h
>--- a/source/common/x86/intrapred.h	Tue Mar 10 12:44:28 2015 +0530
>+++ b/source/common/x86/intrapred.h	Tue Mar 10 14:01:26 2015 +0530
>@@ -180,6 +180,7 @@
> void x265_intra_pred_ang8_27_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_intra_pred_ang8_11_avx2(pixel* dst, intptr_t dstStride, const pixel* srcPix, int dirMode, int bFilter);
>+void x265_intra_pred_ang8_12_avx2(pixel* dst, intptr_t dstStride, const pixel* srcPix, int dirMode, int bFilter);
> void x265_intra_pred_ang8_24_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 f79f44d2e55f -r fc805c02d0f2 source/common/x86/intrapred8.asm
>--- a/source/common/x86/intrapred8.asm	Tue Mar 10 12:44:28 2015 +0530
>+++ b/source/common/x86/intrapred8.asm	Tue Mar 10 14:01:26 2015 +0530
>@@ -10403,3 +10403,51 @@
>     movhps            [r0 + 2 * r1], xm4
>     movhps            [r0 + r3], xm2
>     RET
>+
>+INIT_YMM avx2
>+cglobal intra_pred_ang8_12, 3, 5, 5
>+    mova              m3, [pw_1024]
>+    movu              xm1, [r2 + 16]
>+    pinsrb            xm1, [r2], 0
>+    pshufb            xm1, [intra_pred_shuff_0_8]
>+    vinserti128       m0, m1, xm1, 1
>+
>+    lea               r4, [c_ang8_mode_24]
>+    pmaddubsw         m1, m0, [r4]
>+    pmulhrsw          m1, m3
>+    pmaddubsw         m2, m0, [r4 + mmsize]
>+    pmulhrsw          m2, m3
>+    pmaddubsw         m4, m0, [r4 + 2 * mmsize]
>+    pmulhrsw          m4, m3
>+    pslldq            xm0, 2
>+    pinsrb            xm0, [r2 + 6], 0
>+    pinsrb            xm0, [r2 + 0], 1
>+    vinserti128       m0, m0, xm0, 1
>+    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/20150311/a6916321/attachment.html>