diff options
| author | Ben Avison <bavison@riscosopen.org> | 2014-03-20 18:59:14 +0000 |
|---|---|---|
| committer | Michael Niedermayer <michaelni@gmx.at> | 2014-03-26 20:22:18 +0100 |
| commit | 87b128d5ef6aeb01cc8bba167c929c74cbf2e7c7 (patch) | |
| tree | 4536015fb8b2039d45e13a869046238815a6aa24 /libavcodec/mlpdsp.c | |
| parent | 3017239d3a6f1c4049394be49ae207cd4475ad53 (diff) | |
| download | ffmpeg-87b128d5ef6aeb01cc8bba167c929c74cbf2e7c7.tar.gz | |
truehd: add hand-scheduled ARM asm version of mlp_filter_channel.
Profiling results for overall audio decode and the mlp_filter_channel(_arm)
function in particular are as follows:
Before After
Mean StdDev Mean StdDev Confidence Change
6:2 total 380.4 22.0 370.8 17.0 87.4% +2.6% (insignificant)
6:2 function 60.7 7.2 36.6 8.1 100.0% +65.8%
8:2 total 357.0 17.5 343.2 19.0 97.8% +4.0% (insignificant)
8:2 function 60.3 8.8 37.3 3.8 100.0% +61.8%
6:6 total 717.2 23.2 658.4 15.7 100.0% +8.9%
6:6 function 140.4 12.9 81.5 9.2 100.0% +72.4%
8:8 total 981.9 16.2 896.2 24.5 100.0% +9.6%
8:8 function 193.4 15.0 103.3 11.5 100.0% +87.2%
Experiments with adding preload instructions to this function yielded no
useful benefit, so these have not been included.
The assembly version has also been tested with a fuzz tester to ensure that
any combinations of inputs not exercised by my available test streams still
generate mathematically identical results to the C version.
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
Diffstat (limited to 'libavcodec/mlpdsp.c')
| -rw-r--r-- | libavcodec/mlpdsp.c | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/libavcodec/mlpdsp.c b/libavcodec/mlpdsp.c index b413e86db5..4b403b8e82 100644 --- a/libavcodec/mlpdsp.c +++ b/libavcodec/mlpdsp.c @@ -60,6 +60,8 @@ static void mlp_filter_channel(int32_t *state, const int32_t *coeff, av_cold void ff_mlpdsp_init(MLPDSPContext *c) { c->mlp_filter_channel = mlp_filter_channel; + if (ARCH_ARM) + ff_mlpdsp_init_arm(c); if (ARCH_X86) ff_mlpdsp_init_x86(c); } |