[x265] [PATCH] asm: chroma_hps[4xN, 8xN, 16xN, 32xN, 2x8]

aasaipriya at multicorewareinc.com aasaipriya at multicorewareinc.com
Fri Apr 17 13:13:58 CEST 2015


# HG changeset patch
# User Aasaipriya Chandran <aasaipriya at multicorewareinc.com>
# Date 1429269219 -19800
#      Fri Apr 17 16:43:39 2015 +0530
# Node ID 69f9822642d76f618f37ff72a81258df5a654d17
# Parent  660751206f5cf2089ac09036bdae53a2db23c4c3
asm: chroma_hps[4xN, 8xN, 16xN, 32xN, 2x8]

diff -r 660751206f5c -r 69f9822642d7 source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Fri Apr 17 16:19:58 2015 +0530
+++ b/source/common/x86/asm-primitives.cpp	Fri Apr 17 16:43:39 2015 +0530
@@ -2246,6 +2246,30 @@
         p.chroma[X265_CSP_I444].pu[LUMA_64x16].filter_hpp = x265_interp_4tap_horiz_pp_64x16_avx2;
         p.chroma[X265_CSP_I444].pu[LUMA_48x64].filter_hpp = x265_interp_4tap_horiz_pp_48x64_avx2;
 
+        p.chroma[X265_CSP_I422].pu[CHROMA_422_4x4].filter_hps = x265_interp_4tap_horiz_ps_4x4_avx2;
+        p.chroma[X265_CSP_I422].pu[CHROMA_422_4x8].filter_hps = x265_interp_4tap_horiz_ps_4x8_avx2;
+        p.chroma[X265_CSP_I422].pu[CHROMA_422_4x16].filter_hps = x265_interp_4tap_horiz_ps_4x16_avx2;
+
+        p.chroma[X265_CSP_I422].pu[CHROMA_422_8x4].filter_hps = x265_interp_4tap_horiz_ps_8x4_avx2;
+        p.chroma[X265_CSP_I422].pu[CHROMA_422_8x8].filter_hps = x265_interp_4tap_horiz_ps_8x8_avx2;
+        p.chroma[X265_CSP_I422].pu[CHROMA_422_8x16].filter_hps = x265_interp_4tap_horiz_ps_8x16_avx2;
+        p.chroma[X265_CSP_I422].pu[CHROMA_422_8x32].filter_hps = x265_interp_4tap_horiz_ps_8x32_avx2;
+        p.chroma[X265_CSP_I422].pu[CHROMA_422_8x64].filter_hps = x265_interp_4tap_horiz_ps_8x64_avx2; //adding macro call
+        p.chroma[X265_CSP_I422].pu[CHROMA_422_8x12].filter_hps = x265_interp_4tap_horiz_ps_8x12_avx2; //adding macro call
+
+        p.chroma[X265_CSP_I422].pu[CHROMA_422_16x8].filter_hps = x265_interp_4tap_horiz_ps_16x8_avx2;
+        p.chroma[X265_CSP_I422].pu[CHROMA_422_16x16].filter_hps = x265_interp_4tap_horiz_ps_16x16_avx2;
+        p.chroma[X265_CSP_I422].pu[CHROMA_422_16x32].filter_hps = x265_interp_4tap_horiz_ps_16x32_avx2;
+        p.chroma[X265_CSP_I422].pu[CHROMA_422_16x64].filter_hps = x265_interp_4tap_horiz_ps_16x64_avx2;//adding macro call
+        p.chroma[X265_CSP_I422].pu[CHROMA_422_16x24].filter_hps = x265_interp_4tap_horiz_ps_16x24_avx2;//adding macro call
+
+        p.chroma[X265_CSP_I422].pu[CHROMA_422_32x16].filter_hps = x265_interp_4tap_horiz_ps_32x16_avx2;
+        p.chroma[X265_CSP_I422].pu[CHROMA_422_32x32].filter_hps = x265_interp_4tap_horiz_ps_32x32_avx2;
+        p.chroma[X265_CSP_I422].pu[CHROMA_422_32x64].filter_hps = x265_interp_4tap_horiz_ps_32x64_avx2;
+        p.chroma[X265_CSP_I422].pu[CHROMA_422_32x48].filter_hps = x265_interp_4tap_horiz_ps_32x48_avx2;
+
+        p.chroma[X265_CSP_I422].pu[CHROMA_422_2x8].filter_hps = x265_interp_4tap_horiz_ps_2x8_avx2;
+
         //i444 chroma_hps
         p.chroma[X265_CSP_I444].pu[LUMA_64x32].filter_hps = x265_interp_4tap_horiz_ps_64x32_avx2;
         p.chroma[X265_CSP_I444].pu[LUMA_64x48].filter_hps = x265_interp_4tap_horiz_ps_64x48_avx2;
diff -r 660751206f5c -r 69f9822642d7 source/common/x86/ipfilter8.asm
--- a/source/common/x86/ipfilter8.asm	Fri Apr 17 16:19:58 2015 +0530
+++ b/source/common/x86/ipfilter8.asm	Fri Apr 17 16:43:39 2015 +0530
@@ -19960,6 +19960,8 @@
     IPFILTER_CHROMA_PS_16xN_AVX2  16 , 12
     IPFILTER_CHROMA_PS_16xN_AVX2  16 , 8
     IPFILTER_CHROMA_PS_16xN_AVX2  16 , 4
+    IPFILTER_CHROMA_PS_16xN_AVX2  16 , 24
+    IPFILTER_CHROMA_PS_16xN_AVX2  16 , 64
 
 ;-----------------------------------------------------------------------------------------------------------------------------
 ; void interp_4tap_horiz_ps_32xN(pixel *src, intptr_t srcStride, int16_t *dst, intptr_t dstStride, int coeffIdx, int isRowExt)
@@ -20035,6 +20037,8 @@
 IPFILTER_CHROMA_PS_32xN_AVX2  32 , 16
 IPFILTER_CHROMA_PS_32xN_AVX2  32 , 24
 IPFILTER_CHROMA_PS_32xN_AVX2  32 , 8
+IPFILTER_CHROMA_PS_32xN_AVX2  32 , 64
+IPFILTER_CHROMA_PS_32xN_AVX2  32 , 48
 ;-----------------------------------------------------------------------------------------------------------------------------
 ; void interp_4tap_horiz_ps_4x4(pixel *src, intptr_t srcStride, int16_t *dst, intptr_t dstStride, int coeffIdx, int isRowExt)
 ;-----------------------------------------------------------------------------------------------------------------------------
@@ -21245,6 +21249,8 @@
     IPFILTER_CHROMA_PS_8xN_AVX2  16
     IPFILTER_CHROMA_PS_8xN_AVX2  6
     IPFILTER_CHROMA_PS_8xN_AVX2  4
+    IPFILTER_CHROMA_PS_8xN_AVX2  12
+    IPFILTER_CHROMA_PS_8xN_AVX2  64
 
 INIT_YMM avx2
 cglobal interp_4tap_horiz_ps_2x4, 4, 7, 3


More information about the x265-devel mailing list