[FFmpeg-devel] Benchmarking
Michael Niedermayer
michaelni
Tue Dec 16 14:06:02 CET 2008
On Tue, Dec 16, 2008 at 09:10:20AM +0100, Diego Biurrun wrote:
> On Tue, Dec 16, 2008 at 12:24:02AM +0100, Michael Niedermayer wrote:
> >
> > Ive run some tests to determine how reliable benchmarks are and which
> > method is most reliable. The results are not really a surprise as they
> >
> > 3 samples:
> > len: 1280000 correct: avg: 78 min: 61 without outliers: 78 without max: 69 without 2max: 61
> >
> > 5 samples:
> > len: 1280000 correct: avg: 90 min: 61 without outliers: 91 without max: 78 without 2max: 62
> >
> > 15 samples:
> > len: 1280000 correct: avg: 87 min: 93 min2: 80 without outliers: 98 without max: 98 without 2max: 97
>
> Do you have an explanation for the anomaly at this value of len?
btw, with 20 samples:
len: 1250 correct: avg: 97 min: 100 min2: 100 without outliers: 100 without max: 100 without 2max: 100
len: 2500 correct: avg: 97 min: 100 min2: 100 without outliers: 100 without max: 100 without 2max: 100
len: 5000 correct: avg: 88 min: 100 min2: 100 without outliers: 100 without max: 100 without 2max: 100
len: 10000 correct: avg: 83 min: 100 min2: 100 without outliers: 100 without max: 100 without 2max: 100
len: 20000 correct: avg: 51 min: 100 min2: 100 without outliers: 97 without max: 97 without 2max: 100
len: 40000 correct: avg: 55 min: 100 min2: 100 without outliers: 93 without max: 93 without 2max: 100
len: 80000 correct: avg: 71 min: 100 min2: 100 without outliers: 80 without max: 80 without 2max: 100
len: 160000 correct: avg: 73 min: 100 min2: 100 without outliers: 68 without max: 70 without 2max: 84
len: 320000 correct: avg: 94 min: 100 min2: 100 without outliers: 92 without max: 93 without 2max: 91
len: 640000 correct: avg: 92 min: 100 min2: 100 without outliers: 96 without max: 97 without 2max: 96
len: 1280000 correct: avg: 90 min: 99 min2: 94 without outliers: 98 without max: 98 without 2max: 98
len: 2560000 correct: avg: 89 min: 100 min2: 99 without outliers: 98 without max: 100 without 2max: 98
len: 5120000 correct: avg: 87 min: 100 min2: 100 without outliers: 100 without max: 100 without 2max: 100
[...]
--
Michael GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB
it is not once nor twice but times without number that the same ideas make
their appearance in the world. -- Aristotle
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: Digital signature
URL: <http://lists.mplayerhq.hu/pipermail/ffmpeg-devel/attachments/20081216/4c2ad835/attachment.pgp>
More information about the ffmpeg-devel
mailing list