summaryrefslogtreecommitdiff
path: root/libavfilter/x86/vf_interlace.asm
diff options
context:
space:
mode:
authorKieran Kunhya <kierank@obe.tv>2014-11-11 18:43:42 +0000
committerLuca Barbato <lu_zero@gentoo.org>2014-11-15 00:35:31 +0100
commit2e1704059ae8625beda2ffde847ad22c5ba416dc (patch)
tree31d07ed04dab0d25596c2f0d845f66bbb5e6c5ca /libavfilter/x86/vf_interlace.asm
parentd16ec1b6db25bc348b0d4800c9a0c9b7070e3710 (diff)
vf_interlace: Add SIMD for lowpass filter
Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
Diffstat (limited to 'libavfilter/x86/vf_interlace.asm')
-rw-r--r--libavfilter/x86/vf_interlace.asm75
1 files changed, 75 insertions, 0 deletions
diff --git a/libavfilter/x86/vf_interlace.asm b/libavfilter/x86/vf_interlace.asm
new file mode 100644
index 0000000000..8c2e9b099c
--- /dev/null
+++ b/libavfilter/x86/vf_interlace.asm
@@ -0,0 +1,75 @@
+;*****************************************************************************
+;* x86-optimized functions for interlace filter
+;*
+;* Copyright (C) 2014 Kieran Kunhya <kierank@obe.tv>
+;*
+;* This file is part of Libav.
+;*
+;* Libav is free software; you can redistribute it and/or modify
+;* it under the terms of the GNU General Public License as published by
+;* the Free Software Foundation; either version 2 of the License, or
+;* (at your option) any later version.
+;*
+;* Libav is distributed in the hope that it will be useful,
+;* but WITHOUT ANY WARRANTY; without even the implied warranty of
+;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+;* GNU General Public License for more details.
+;*
+;* You should have received a copy of the GNU General Public License along
+;* with Libav; if not, write to the Free Software Foundation, Inc.,
+;* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+;******************************************************************************
+
+%include "libavutil/x86/x86util.asm"
+
+SECTION_RODATA
+
+SECTION .text
+
+%macro LOWPASS_LINE 0
+cglobal lowpass_line, 5, 5, 7
+ add r0, r1
+ add r2, r1
+ add r3, r1
+ add r4, r1
+ neg r1
+
+ pxor m6, m6
+
+.loop
+ mova m0, [r2+r1]
+ punpcklbw m1, m0, m6
+ punpckhbw m0, m6
+ paddw m0, m0
+ paddw m1, m1
+
+ mova m2, [r3+r1]
+ punpcklbw m3, m2, m6
+ punpckhbw m2, m6
+
+ mova m4, [r4+r1]
+ punpcklbw m5, m4, m6
+ punpckhbw m4, m6
+
+ paddw m1, m3
+ pavgw m1, m5
+
+ paddw m0, m2
+ pavgw m0, m4
+
+ psrlw m0, 1
+ psrlw m1, 1
+
+ packuswb m1, m0
+ mova [r0+r1], m1
+
+ add r1, mmsize
+ jl .loop
+REP_RET
+%endmacro
+
+INIT_XMM sse2
+LOWPASS_LINE
+
+INIT_XMM avx
+LOWPASS_LINE