[x265] [PATCH] Luma_hpp[32x8 , 32x16 , 32x24 , 32x32 , 32x64] avx2 asm code: improved 2132c->1466c, 4239c->2933c, 6568c->4641c, 8548c->6267c, 15942c->11567c

[aasaipriya at multicorewareinc.com]

# HG changeset patch
# User Aasaipriya Chandran <aasaipriya at multicorewareinc.com>
# Date 1416472630 -19800
#      Thu Nov 20 14:07:10 2014 +0530
# Node ID c874b8e79d5c7c0c7a9b221d1d20705a782ce702
# Parent  6ac5a38e0753f7966fd69fea3238719daa423161
Luma_hpp[32x8 , 32x16 , 32x24 , 32x32 , 32x64] avx2 asm code: improved 2132c->1466c, 4239c->2933c, 6568c->4641c, 8548c->6267c, 15942c->11567c

diff -r 6ac5a38e0753 -r c874b8e79d5c source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Thu Nov 20 13:26:24 2014 +0530
+++ b/source/common/x86/asm-primitives.cpp	Thu Nov 20 14:07:10 2014 +0530
@@ -1806,6 +1806,12 @@
     p.luma_hpp[LUMA_16x32] = x265_interp_8tap_horiz_pp_16x32_avx2;
     p.luma_hpp[LUMA_16x64] = x265_interp_8tap_horiz_pp_16x64_avx2;
 
+    p.luma_hpp[LUMA_32x32] = x265_interp_8tap_horiz_pp_32x32_avx2;
+    p.luma_hpp[LUMA_32x8] = x265_interp_8tap_horiz_pp_32x8_avx2;
+    p.luma_hpp[LUMA_32x16] = x265_interp_8tap_horiz_pp_32x16_avx2;
+    p.luma_hpp[LUMA_32x64] = x265_interp_8tap_horiz_pp_32x64_avx2;
+    p.luma_hpp[LUMA_32x24] = x265_interp_8tap_horiz_pp_32x24_avx2;
+
     p.luma_hpp[LUMA_64x64] = x265_interp_8tap_horiz_pp_64x64_avx2;
     p.luma_hpp[LUMA_64x32] = x265_interp_8tap_horiz_pp_64x32_avx2;
     p.luma_hpp[LUMA_64x48] = x265_interp_8tap_horiz_pp_64x48_avx2;
diff -r 6ac5a38e0753 -r c874b8e79d5c source/common/x86/ipfilter8.asm
--- a/source/common/x86/ipfilter8.asm	Thu Nov 20 13:26:24 2014 +0530
+++ b/source/common/x86/ipfilter8.asm	Thu Nov 20 14:07:10 2014 +0530
@@ -928,8 +928,75 @@
 %endmacro
 
 
-
-
+%macro IPFILTER_LUMA_32x_avx2 2
+INIT_YMM avx2
+cglobal interp_8tap_horiz_pp_%1x%2, 4,6,8
+    sub             r0, 3
+    mov             r4d, r4m
+%ifdef PIC
+    lea             r5, [tab_LumaCoeff]
+    vpbroadcastd    m0, [r5 + r4 * 8]
+    vpbroadcastd    m1, [r5 + r4 * 8 + 4]
+%else
+    vpbroadcastd    m0, [tab_LumaCoeff + r4 * 8]
+    vpbroadcastd    m1, [tab_LumaCoeff + r4 * 8 + 4]
+%endif
+    movu            m3, [tab_Tm + 16]
+    vpbroadcastd    m7, [pw_1]
+
+    ; register map
+    ; m0 , m1 interpolate coeff
+    ; m2 , m2  shuffle order table
+    ; m7 - pw_1
+
+    mov             r4d,  %2
+.loop:
+    ; Row 0
+    vbroadcasti128  m4, [r0]                        ; [x E D C B A 9 8 7 6 5 4 3 2 1 0]
+    pshufb          m5, m4, m3
+    pshufb          m4, [tab_Tm]
+    pmaddubsw       m4, m0
+    pmaddubsw       m5, m1
+    paddw           m4, m5
+    pmaddwd         m4, m7
+    vbroadcasti128  m5, [r0 + 8]                    
+    pshufb          m6, m5, m3
+    pshufb          m5, [tab_Tm]
+    pmaddubsw       m5, m0
+    pmaddubsw       m6, m1
+    paddw           m5, m6
+    pmaddwd         m5, m7
+    packssdw        m4, m5                          ; [17 16 15 14 07 06 05 04 13 12 11 10 03 02 01 00]
+    pmulhrsw        m4, [pw_512]
+    vbroadcasti128  m2, [r0 + 16]                  
+    pshufb          m5, m2, m3
+    pshufb          m2, [tab_Tm]
+    pmaddubsw       m2, m0
+    pmaddubsw       m5, m1
+    paddw           m2, m5
+    pmaddwd         m2, m7
+    vbroadcasti128  m5, [r0 + 24]                
+    pshufb          m6, m5, m3
+    pshufb          m5, [tab_Tm]
+    pmaddubsw       m5, m0
+    pmaddubsw       m6, m1
+    paddw           m5, m6
+    pmaddwd         m5, m7
+    packssdw        m2, m5                          
+    pmulhrsw        m2, [pw_512]
+    packuswb        m4, m2
+    vpermq          m4, m4, 11011000b
+    vextracti128    xm5,  m4, 1
+    pshufd          xm4,  xm4, 11011000b
+    pshufd          xm5,  xm5, 11011000b
+    movu            [r2], xm4
+    movu            [r2 + 16],xm5
+    lea             r0, [r0 + r1 ]
+    lea             r2, [r2 + r3]
+    dec             r4d
+    jnz             .loop
+    RET
+%endmacro
 
 
 %macro IPFILTER_LUMA_64x_avx2 2
@@ -1055,8 +1122,13 @@
     IPFILTER_LUMA_AVX2 16, 8
     IPFILTER_LUMA_AVX2 16, 32
     IPFILTER_LUMA_AVX2 16, 64
-    IPFILTER_LUMA_AVX2 16, 12 
-
+    IPFILTER_LUMA_AVX2 16, 12
+
+    IPFILTER_LUMA_32x_avx2 32 , 32
+    IPFILTER_LUMA_32x_avx2 32 , 8
+    IPFILTER_LUMA_32x_avx2 32 , 16
+    IPFILTER_LUMA_32x_avx2 32 , 64
+    IPFILTER_LUMA_32x_avx2 32 , 24
 
     IPFILTER_LUMA_64x_avx2 64 , 64
     IPFILTER_LUMA_64x_avx2 64 , 48