* Copyright (c) 2013 Janne Grunau <janne-libav@jannau.net>
* Copyright (c) 2014 Janne Grunau <janne-libav@jannau.net>
*
- * This file is part of Libav.
+ * This file is part of FFmpeg.
*
- * Libav is free software; you can redistribute it and/or
+ * FFmpeg is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
- * Libav is distributed in the hope that it will be useful,
+ * FFmpeg 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
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
- * License along with Libav; if not, write to the Free Software
+ * License along with FFmpeg; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
ldr w6, [x4]
ccmp w3, #0, #0, ne
mov v24.S[0], w6
- and w6, w6, w6, lsl #16
+ and w8, w6, w6, lsl #16
b.eq 1f
- ands w6, w6, w6, lsl #8
+ ands w8, w8, w8, lsl #8
b.ge 2f
1:
ret
usubw v4.8H, v4.8H, v16.8B
and v26.8B, v26.8B, v30.8B
shl v4.8H, v4.8H, #2
- mov x2, v26.d[0]
+ mov x8, v26.d[0]
sli v24.8H, v24.8H, #8
uaddw v4.8H, v4.8H, v18.8B
- cbz x2, 9f
+ cbz x8, 9f
usubw v4.8H, v4.8H, v2.8B
rshrn v4.8B, v4.8H, #3
smin v4.8B, v4.8B, v24.8B
sxtw x1, w1
sub x0, x0, #2
+h_loop_filter_chroma420:
ld1 {v18.S}[0], [x0], x1
ld1 {v16.S}[0], [x0], x1
ld1 {v0.S}[0], [x0], x1
ret
endfunc
+function ff_h264_h_loop_filter_chroma422_neon, export=1
+ sxtw x1, w1
+ h264_loop_filter_start
+ add x5, x0, x1
+ sub x0, x0, #2
+ add x1, x1, x1
+ mov x7, x30
+ bl h_loop_filter_chroma420
+ mov x30, x7
+ sub x0, x5, #2
+ mov v24.s[0], w6
+ b h_loop_filter_chroma420
+endfunc
.macro h264_loop_filter_chroma_intra
uabd v26.8b, v16.8b, v17.8b // abs(p0 - q0)
sub x4, x0, #2
sub x0, x0, #1
+h_loop_filter_chroma420_intra:
ld1 {v18.8b}, [x4], x1
ld1 {v16.8b}, [x4], x1
ld1 {v17.8b}, [x4], x1
ld1 {v18.s}[1], [x4], x1
ld1 {v16.s}[1], [x4], x1
ld1 {v17.s}[1], [x4], x1
- ld1 {v19.s}[1], [x4]
+ ld1 {v19.s}[1], [x4], x1
transpose_4x8B v18, v16, v17, v19, v26, v27, v28, v29
ret
endfunc
+function ff_h264_h_loop_filter_chroma422_intra_neon, export=1
+ h264_loop_filter_start_intra
+ sub x4, x0, #2
+ add x5, x0, x1, lsl #3
+ sub x0, x0, #1
+ mov x7, x30
+ bl h_loop_filter_chroma420_intra
+ sub x0, x5, #1
+ mov x30, x7
+ b h_loop_filter_chroma420_intra
+endfunc
.macro biweight_16 macs, macd
dup v0.16B, w5