diff options
author | Geoff Hill <geoff@geoffhill.org> | 2024-04-06 07:25:51 -0700 |
---|---|---|
committer | Martin Storsjö <martin@martin.st> | 2024-04-08 13:36:28 +0300 |
commit | b69486ea18ed1a278501911c161a5f72f1622ad3 (patch) | |
tree | a30ceddae941075020100c462dcf57d73a8e6f88 /libavcodec/aarch64/ac3dsp_neon.S | |
parent | 2d33d6bfcc2ab4031862aeb35bc0cb536019ac09 (diff) | |
download | ffmpeg-b69486ea18ed1a278501911c161a5f72f1622ad3.tar.gz |
avcodec/ac3: Implement float_to_fixed24 for aarch64 NEON
Signed-off-by: Geoff Hill <geoff@geoffhill.org>
Signed-off-by: Martin Storsjö <martin@martin.st>
Diffstat (limited to 'libavcodec/aarch64/ac3dsp_neon.S')
-rw-r--r-- | libavcodec/aarch64/ac3dsp_neon.S | 36 |
1 files changed, 36 insertions, 0 deletions
diff --git a/libavcodec/aarch64/ac3dsp_neon.S b/libavcodec/aarch64/ac3dsp_neon.S new file mode 100644 index 0000000000..c4d204b51a --- /dev/null +++ b/libavcodec/aarch64/ac3dsp_neon.S @@ -0,0 +1,36 @@ +/* + * Copyright (c) 2011 Mans Rullgard <mans@mansr.com> + * Copyright (c) 2024 Geoff Hill <geoff@geoffhill.org> + * + * This file is part of FFmpeg. + * + * FFmpeg 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. + * + * 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 General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with FFmpeg; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + */ + +#include "libavutil/aarch64/asm.S" + +function ff_float_to_fixed24_neon, export=1 +1: ld1 {v0.4s, v1.4s}, [x1], #32 + fcvtzs v0.4s, v0.4s, #24 + ld1 {v2.4s, v3.4s}, [x1], #32 + fcvtzs v1.4s, v1.4s, #24 + fcvtzs v2.4s, v2.4s, #24 + st1 {v0.4s, v1.4s}, [x0], #32 + fcvtzs v3.4s, v3.4s, #24 + st1 {v2.4s, v3.4s}, [x0], #32 + subs w2, w2, #16 + b.ne 1b + ret +endfunc |