[x265] [PATCH 2 of 3] asm: chroma_hpp[24x64] for i422 - improved 9272c->8212c

[aasaipriya at multicorewareinc.com]

# HG changeset patch
# User Aasaipriya Chandran <aasaipriya at multicorewareinc.com>
# Date 1429088965 -19800
#      Wed Apr 15 14:39:25 2015 +0530
# Node ID ad71befbc5eb57cecd53b1a1d16421a9d9863a6f
# Parent  31d61d004adc25caff10a1bf08e66af61c3b526e
asm: chroma_hpp[24x64] for i422 -  improved 9272c->8212c

diff -r 31d61d004adc -r ad71befbc5eb source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Wed Apr 15 14:35:01 2015 +0530
+++ b/source/common/x86/asm-primitives.cpp	Wed Apr 15 14:39:25 2015 +0530
@@ -2128,6 +2128,7 @@
 
         //i422 for chroma_hpp
         p.chroma[X265_CSP_I422].pu[CHROMA_422_12x32].filter_hpp = x265_interp_4tap_horiz_pp_12x32_avx2;
+        p.chroma[X265_CSP_I422].pu[CHROMA_422_24x64].filter_hpp = x265_interp_4tap_horiz_pp_24x64_avx2;
 
         if ((cpuMask & X265_CPU_BMI1) && (cpuMask & X265_CPU_BMI2))
             p.findPosLast = x265_findPosLast_x64;
diff -r 31d61d004adc -r ad71befbc5eb source/common/x86/ipfilter8.asm
--- a/source/common/x86/ipfilter8.asm	Wed Apr 15 14:35:01 2015 +0530
+++ b/source/common/x86/ipfilter8.asm	Wed Apr 15 14:39:25 2015 +0530
@@ -21844,3 +21844,62 @@
     dec               r4d
     jnz               .loop
     RET
+
+INIT_YMM avx2
+cglobal interp_4tap_horiz_pp_24x64, 4,6,7
+    mov              r4d,           r4m
+
+%ifdef PIC
+    lea               r5,           [tab_ChromaCoeff]
+    vpbroadcastd      m0,           [r5 + r4 * 4]
+%else
+    vpbroadcastd      m0,           [tab_ChromaCoeff + r4 * 4]
+%endif
+
+    mova              m1,           [interp4_horiz_shuf1]
+    vpbroadcastd      m2,           [pw_1]
+    mova              m6,           [pw_512]
+    ; register map
+    ; m0 - interpolate coeff
+    ; m1 - shuffle order table
+    ; m2 - constant word 1
+
+    dec               r0
+    mov               r4d,          64
+
+.loop:
+    ; Row 0
+    vbroadcasti128    m3,           [r0]                        ; [x x x x x A 9 8 7 6 5 4 3 2 1 0]
+    pshufb            m3,           m1
+    pmaddubsw         m3,           m0
+    pmaddwd           m3,           m2
+    vbroadcasti128    m4,           [r0 + 4]
+    pshufb            m4,           m1
+    pmaddubsw         m4,           m0
+    pmaddwd           m4,           m2
+    packssdw          m3,           m4
+    pmulhrsw          m3,           m6
+
+    vbroadcasti128    m4,           [r0 + 16]
+    pshufb            m4,           m1
+    pmaddubsw         m4,           m0
+    pmaddwd           m4,           m2
+    vbroadcasti128    m5,           [r0 + 20]
+    pshufb            m5,           m1
+    pmaddubsw         m5,           m0
+    pmaddwd           m5,           m2
+    packssdw          m4,           m5
+    pmulhrsw          m4,           m6
+
+    packuswb          m3,           m4
+    vpermq            m3,           m3,      11011000b
+
+    vextracti128      xm4,          m3,       1
+    movu              [r2],         xm3
+    movq              [r2 + 16],    xm4
+    add               r2,           r3
+    add               r0,           r1
+    dec               r4d
+    jnz               .loop
+    RET
+