[x265] [PATCH] asm: 10bpp code for pixel_add_ps_6x8

[murugan at multicorewareinc.com]

# HG changeset patch
# User Murugan Vairavel <murugan at multicorewareinc.com>
# Date 1386571409 -19800
#      Mon Dec 09 12:13:29 2013 +0530
# Node ID 02b888130ed4fa64b5632544bea6a74e3e6f375b
# Parent  5bb46ef28bc59794404e59de5c62188928685437
asm: 10bpp code for pixel_add_ps_6x8

diff -r 5bb46ef28bc5 -r 02b888130ed4 source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Mon Dec 09 10:59:45 2013 +0800
+++ b/source/common/x86/asm-primitives.cpp	Mon Dec 09 12:13:29 2013 +0530
@@ -670,6 +670,7 @@
         p.chroma[X265_CSP_I420].add_ps[CHROMA_4x4] = x265_pixel_add_ps_4x4_sse2;
         p.chroma[X265_CSP_I420].add_ps[CHROMA_4x8] = x265_pixel_add_ps_4x8_sse2;
         p.chroma[X265_CSP_I420].add_ps[CHROMA_4x16] = x265_pixel_add_ps_4x16_sse2;
+        p.chroma[X265_CSP_I420].add_ps[CHROMA_6x8] = x265_pixel_add_ps_6x8_sse2;
     }
     if (cpuMask & X265_CPU_SSSE3)
     {
diff -r 5bb46ef28bc5 -r 02b888130ed4 source/common/x86/pixeladd8.asm
--- a/source/common/x86/pixeladd8.asm	Mon Dec 09 10:59:45 2013 +0800
+++ b/source/common/x86/pixeladd8.asm	Mon Dec 09 12:13:29 2013 +0530
@@ -364,6 +364,75 @@
 ; void pixel_add_ps_%1x%2(pixel *dest, intptr_t destride, pixel *src0, int16_t *scr1, intptr_t srcStride0, intptr_t srcStride1)
 ;-----------------------------------------------------------------------------
 %macro PIXEL_ADD_PS_W6_H4 2
+%if HIGH_BIT_DEPTH
+INIT_XMM sse2
+cglobal pixel_add_ps_%1x%2, 6, 7, 6, dest, destride, src0, scr1, srcStride0, srcStride1
+    mov     r6d,    %2/4
+    add      r1,    r1
+    add      r4,    r4
+    add      r5,    r5
+    pxor     m4,    m4
+    mova     m5,    [pw_pixel_max]
+.loop
+    movu        m0,    [r2]
+    movu        m1,    [r3]
+    mova        m2,    m0
+    mova        m3,    m1
+    punpckhqdq  m2,    m2
+    punpckhqdq  m3,    m3
+    paddw       m0,    m1
+    paddw       m2,    m3
+    CLIPW       m0,    m4,    m5
+    CLIPW       m2,    m4,    m5
+
+    movh        [r0],         m0
+    movd        [r0 + 8],     m2
+
+    movu        m0,    [r2 + r4]
+    movu        m1,    [r3 + r5]
+    mova        m2,    m0
+    mova        m3,    m1
+    punpckhqdq  m2,    m2
+    punpckhqdq  m3,    m3
+    paddw       m0,    m1
+    paddw       m2,    m3
+    CLIPW       m0,    m4,    m5
+    CLIPW       m2,    m4,    m5
+
+    movh        [r0 + r1],        m0
+    movd        [r0 + r1 + 8],    m2
+
+    lea         r2,    [r2 + 2 * r4]
+    lea         r3,    [r3 + 2 * r5]
+    lea         r0,    [r0 + 2 * r1]
+    movu        m0,    [r2]
+    movu        m1,    [r3]
+    mova        m2,    m0
+    mova        m3,    m1
+    punpckhqdq  m2,    m2
+    punpckhqdq  m3,    m3
+    paddw       m0,    m1
+    paddw       m2,    m3
+    CLIPW       m0,    m4,    m5
+    CLIPW       m2,    m4,    m5
+
+    movh        [r0],         m0
+    movd        [r0 + 8],     m2
+
+    movu        m0,    [r2 + r4]
+    movu        m1,    [r3 + r5]
+    mova        m2,    m0
+    mova        m3,    m1
+    punpckhqdq  m2,    m2
+    punpckhqdq  m3,    m3
+    paddw       m0,    m1
+    paddw       m2,    m3
+    CLIPW       m0,    m4,    m5
+    CLIPW       m2,    m4,    m5
+
+    movh        [r0 + r1],        m0
+    movd        [r0 + r1 + 8],    m2
+%else
 INIT_XMM sse4
 cglobal pixel_add_ps_%1x%2, 6, 7, 2, dest, destride, src0, scr1, srcStride0, srcStride1
 
@@ -411,7 +480,7 @@
 
       movd        [r0 + r1],         m0
       pextrw      [r0 + r1 + 4],     m0,        2
-
+%endif
       lea         r0,                [r0 + 2 * r1]
       lea         r2,                [r2 + 2 * r4]
       lea         r3,                [r3 + 2 * r5]