diff options
| author | Hubert Mazur <hum@semihalf.com> | 2022-10-28 11:34:37 +0000 |
|---|---|---|
| committer | Martin Storsjö <martin@martin.st> | 2022-11-01 15:24:43 +0200 |
| commit | 1e9cfa5bb0253784798029bda377823ab5d1a529 (patch) | |
| tree | 4a2e3df1746a882819b45dfecaacffb2aa2493eb /libswscale/aarch64/swscale.c | |
| parent | 16af424bf983409e00a84af1c98bbe7171ddd79f (diff) | |
| download | ffmpeg-1e9cfa5bb0253784798029bda377823ab5d1a529.tar.gz | |
sw_scale: Add specializations for hscale 8 to 19
Add arm64 neon implementations for hscale 8 to 19 with filter
sizes 4, 4X and 8. Both implementations are based on very similar ones
dedicated to hscale 8 to 15. The major changes refer to saving
the data - instead of writing the result as int16_t it is done
with int32_t.
These functions are heavily inspired on patches provided by J. Swinney
and M. Storsjö for hscale8to15 which were slightly adapted for
hscale8to19.
The tests and benchmarks run on AWS Graviton 2 instances. The results
from a checkasm tool shown below.
hscale_8_to_19__fs_4_dstW_512_c: 5663.2
hscale_8_to_19__fs_4_dstW_512_neon: 1259.7
hscale_8_to_19__fs_8_dstW_512_c: 9306.0
hscale_8_to_19__fs_8_dstW_512_neon: 2020.2
hscale_8_to_19__fs_12_dstW_512_c: 12932.7
hscale_8_to_19__fs_12_dstW_512_neon: 2462.5
hscale_8_to_19__fs_16_dstW_512_c: 16844.2
hscale_8_to_19__fs_16_dstW_512_neon: 4671.2
hscale_8_to_19__fs_32_dstW_512_c: 32803.7
hscale_8_to_19__fs_32_dstW_512_neon: 5474.2
hscale_8_to_19__fs_40_dstW_512_c: 40948.0
hscale_8_to_19__fs_40_dstW_512_neon: 6669.7
Signed-off-by: Hubert Mazur <hum@semihalf.com>
Signed-off-by: Martin Storsjö <martin@martin.st>
Diffstat (limited to 'libswscale/aarch64/swscale.c')
| -rw-r--r-- | libswscale/aarch64/swscale.c | 13 |
1 files changed, 9 insertions, 4 deletions
diff --git a/libswscale/aarch64/swscale.c b/libswscale/aarch64/swscale.c index d1312c6658..171fb51329 100644 --- a/libswscale/aarch64/swscale.c +++ b/libswscale/aarch64/swscale.c @@ -29,7 +29,8 @@ void ff_hscale ## from_bpc ## to ## to_bpc ## _ ## filter_n ## _ ## opt( \ const int16_t *filter, \ const int32_t *filterPos, int filterSize) #define SCALE_FUNCS(filter_n, opt) \ - SCALE_FUNC(filter_n, 8, 15, opt); + SCALE_FUNC(filter_n, 8, 15, opt); \ + SCALE_FUNC(filter_n, 8, 19, opt); #define ALL_SCALE_FUNCS(opt) \ SCALE_FUNCS(4, opt); \ SCALE_FUNCS(X8, opt); \ @@ -48,9 +49,13 @@ void ff_yuv2plane1_8_neon( int offset); #define ASSIGN_SCALE_FUNC2(hscalefn, filtersize, opt) do { \ - if (c->srcBpc == 8 && c->dstBpc <= 14) { \ - hscalefn = \ - ff_hscale8to15_ ## filtersize ## _ ## opt; \ + if (c->srcBpc == 8) { \ + if(c->dstBpc <= 14) { \ + hscalefn = \ + ff_hscale8to15_ ## filtersize ## _ ## opt; \ + } else \ + hscalefn = \ + ff_hscale8to19_ ## filtersize ## _ ## opt; \ } \ } while (0) |