Re: [fluid-dev] parallel loading of soundfont samples

[Hamish Moffatt]

On 29/10/20 12:50 am, Marcus Weseloh wrote:
> Hi,
>
> Am Mi., 28. Okt. 2020 um 13:10 Uhr schrieb Ceresa Jean-Jacques
> <jean-jacques.ceresa@orange.fr>:
> > Now we should try the suggested test to run 2 fluidsynth console applications 
> > (a1, a2) at the same time (not sequencially) and measure the total time.
> That's a really good idea to quickly test if parallel loading has
> merit. A quick test on my machine (i5-3210M CPU @ 2.50GHz × 4) and the
> MuseScore_General.sf3 (ca. 40MB) Soundfont on SSD with the following
> test script:

Here are my results for on a 6 core i7-3930K (8 years old) on SSD, with 
one of the SF3 files from my application. Almost no change until we have 
used up all the cores.


time ./bench.sh 1
real    0m3.505s
user    0m3.287s
sys    0m0.116s

time ./bench.sh 2
real    0m3.537s
user    0m6.604s
sys    0m0.256s

time ./bench.sh 3
real    0m3.629s
user    0m10.148s
sys    0m0.408s

time ./bench.sh 4
real    0m3.716s
user    0m13.936s
sys    0m0.477s

time ./bench.sh 5
real    0m3.784s
user    0m17.682s
sys    0m0.652s

time ./bench.sh 6
real    0m3.890s
user    0m21.438s
sys    0m0.819s

time ./bench.sh 7
real    0m5.066s
user    0m27.390s
sys    0m0.994s


Now if I make two copies of this file and load both, in series

real    0m6.870s
user    0m6.566s
sys    0m0.200s

in parallel:

real    0m3.597s
user    0m6.727s
sys    0m0.240s


Hamish