diff options
| author | Geoff Hill <geoff@geoffhill.org> | 2024-04-06 07:25:56 -0700 |
|---|---|---|
| committer | Martin Storsjö <martin@martin.st> | 2024-04-08 13:36:40 +0300 |
| commit | 6f6bd10531e439de67d1354c5fc6f78cc031c66b (patch) | |
| tree | 37c9e05d513519f37d4fd7b7ff651083528a4977 /libavcodec/aarch64 | |
| parent | b69486ea18ed1a278501911c161a5f72f1622ad3 (diff) | |
| download | ffmpeg-6f6bd10531e439de67d1354c5fc6f78cc031c66b.tar.gz | |
avcodec/ac3: Implement ac3_exponent_min for aarch64 NEON
Signed-off-by: Geoff Hill <geoff@geoffhill.org>
Signed-off-by: Martin Storsjö <martin@martin.st>
Diffstat (limited to 'libavcodec/aarch64')
| -rw-r--r-- | libavcodec/aarch64/ac3dsp_init_aarch64.c | 2 | ||||
| -rw-r--r-- | libavcodec/aarch64/ac3dsp_neon.S | 16 |
2 files changed, 18 insertions, 0 deletions
diff --git a/libavcodec/aarch64/ac3dsp_init_aarch64.c b/libavcodec/aarch64/ac3dsp_init_aarch64.c index e3320de0f5..8874b41393 100644 --- a/libavcodec/aarch64/ac3dsp_init_aarch64.c +++ b/libavcodec/aarch64/ac3dsp_init_aarch64.c @@ -25,6 +25,7 @@ #include "libavcodec/ac3dsp.h" #include "config.h" +void ff_ac3_exponent_min_neon(uint8_t *exp, int num_reuse_blocks, int nb_coefs); void ff_float_to_fixed24_neon(int32_t *dst, const float *src, size_t len); av_cold void ff_ac3dsp_init_aarch64(AC3DSPContext *c) @@ -32,5 +33,6 @@ av_cold void ff_ac3dsp_init_aarch64(AC3DSPContext *c) int cpu_flags = av_get_cpu_flags(); if (!have_neon(cpu_flags)) return; + c->ac3_exponent_min = ff_ac3_exponent_min_neon; c->float_to_fixed24 = ff_float_to_fixed24_neon; } diff --git a/libavcodec/aarch64/ac3dsp_neon.S b/libavcodec/aarch64/ac3dsp_neon.S index c4d204b51a..f916c32538 100644 --- a/libavcodec/aarch64/ac3dsp_neon.S +++ b/libavcodec/aarch64/ac3dsp_neon.S @@ -21,6 +21,22 @@ #include "libavutil/aarch64/asm.S" +function ff_ac3_exponent_min_neon, export=1 + cbz w1, 3f +1: ld1 {v0.16b}, [x0] + mov w3, w1 + add x4, x0, #256 +2: ld1 {v1.16b}, [x4] + umin v0.16b, v0.16b, v1.16b + add x4, x4, #256 + subs w3, w3, #1 + b.gt 2b + st1 {v0.16b}, [x0], #16 + subs w2, w2, #16 + b.gt 1b +3: ret +endfunc + function ff_float_to_fixed24_neon, export=1 1: ld1 {v0.4s, v1.4s}, [x1], #32 fcvtzs v0.4s, v0.4s, #24 |