[x265] [PATCH] asm : chroma_hpp[24x32] avx2 - improved 4525c->4289c

[aasaipriya at multicorewareinc.com]

# HG changeset patch
# User Aasaipriya Chandran <aasaipriya at multicorewareinc.com>
# Date 1427258097 -19800
#      Wed Mar 25 10:04:57 2015 +0530
# Node ID 6effbf0a01cb706151b6f2003ac8081e70ea2694
# Parent  6278d89ebb3957cb27cbbcf4ed9ae20761455bdf
asm : chroma_hpp[24x32] avx2 - improved 4525c->4289c

diff -r 6278d89ebb39 -r 6effbf0a01cb source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Wed Mar 25 09:58:31 2015 +0530
+++ b/source/common/x86/asm-primitives.cpp	Wed Mar 25 10:04:57 2015 +0530
@@ -1741,6 +1741,7 @@
         p.chroma[X265_CSP_I420].pu[CHROMA_420_32x8].filter_hps = x265_interp_4tap_horiz_ps_32x8_avx2;
         p.chroma[X265_CSP_I420].pu[CHROMA_420_2x4].filter_hps = x265_interp_4tap_horiz_ps_2x4_avx2;
         p.chroma[X265_CSP_I420].pu[CHROMA_420_2x8].filter_hps = x265_interp_4tap_horiz_ps_2x8_avx2;
+        p.chroma[X265_CSP_I420].pu[CHROMA_420_24x32].filter_hpp = x265_interp_4tap_horiz_pp_24x32_avx2;
 
         p.chroma[X265_CSP_I422].pu[CHROMA_422_4x4].filter_vpp = x265_interp_4tap_vert_pp_4x4_avx2;
 
diff -r 6278d89ebb39 -r 6effbf0a01cb source/common/x86/ipfilter8.asm
--- a/source/common/x86/ipfilter8.asm	Wed Mar 25 09:58:31 2015 +0530
+++ b/source/common/x86/ipfilter8.asm	Wed Mar 25 10:04:57 2015 +0530
@@ -20426,3 +20426,61 @@
     dec               r4d
     jnz               .loop
     RET
+
+INIT_YMM avx2
+cglobal interp_4tap_horiz_pp_24x32, 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,          32
+
+.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