diff options
author | Janne Grunau <janne-libav@jannau.net> | 2015-12-03 16:17:32 +0100 |
---|---|---|
committer | Janne Grunau <janne-libav@jannau.net> | 2015-12-14 16:45:02 +0100 |
commit | 90b1b9350c0a97c4065ae9054b83e57f48a0de1f (patch) | |
tree | 96a67450ae3b647de6c9da7de87f9724d8b834b3 /libavcodec/dfa.c | |
parent | a0fc780a2093784e8664f88205ee1b215e109cee (diff) | |
download | ffmpeg-90b1b9350c0a97c4065ae9054b83e57f48a0de1f.tar.gz |
arm: add ff_int32_to_float_fmul_array8_neon
Quite a bit faster than int32_to_float_fmul_array8_c calling
ff_int32_to_float_fmul_scalar_neon through FmtConvertContext.
Number of cycles per int32_to_float_fmul_array8 call while decoding
padded.dts on exynos5422:
before after change
cortex-a7: 1270 951 -25%
cortex-a15: 434 285 -34%
checkasm --bench cycle counts: cortex-a15 cortex-a7
int32_to_float_fmul_array8_c: 1730.4 4384.5
int32_to_float_fmul_array8_neon_c: 571.5 1694.3
int32_to_float_fmul_array8_neon: 374.0 1448.8
Interesting are the differences between
int32_to_float_fmul_array8_neon_c and int32_to_float_fmul_array8_neon.
The former is current behaviour of calling
ff_int32_to_float_fmul_scalar_neon repeatedly from the c function,
The raw numbers differ since checkasm uses different lengths than the
dca decoder.
Diffstat (limited to 'libavcodec/dfa.c')
0 files changed, 0 insertions, 0 deletions