Csound Csound-dev Csound-tekno Search About

Re: [Cs-dev] More OSX 10.3 benchmarks

Date2005-06-11 17:52
FromVictor Lazzarini
SubjectRe: [Cs-dev] More OSX 10.3 benchmarks
Altivec might have made a little difference:

this is compiled with altivec option, stock (uncommented)
code,
writing to disk

Elapsed time at end of performance: real: 54.744s, CPU:
43.510s

and not writing to disk

Elapsed time at end of performance: real: 43.822s, CPU:
35.000s

I did some comparisons with csound 4.23f12 using time
and performance seems comparable (although time is
not the best for benchmarking I suppose)

I have been using trapped as in CVS.

Victor
>
> Victor Lazzarini wrote:
>
> > >csound examples/trapped.csd -n
> >
> > Elapsed time at end of performance: real: 38.795s, CPU:
> > 29.340s
>
> This is now getting better. Did you disable messages with
> -d -m128 -H0, and did you use --expression-opt ?
>
> > Commenting out that bit does make a difference, but not
> > crucial; does it make a difference to have that bit of
> code ?
>
> It is needed for error handling. However, you may try
> replacing the call to csoundPerformKsmps with
> csoundPerformBuffer in frontends/csound/csound_main.c
> (assuming that you use the standard command line
> frontend): this way, setjmp() will be called only once per
> -b samples and not every ksmps samples. Of course for this
> to make difference, -b needs to be higher than ksmps.
>
> > Writing to disk seems to take a good chunk of processing
> > time though.
> > Can this be improved (again, not crucial for RT)?
>
> If you did not already try to set higher buffer sizes,
> then something like -b 1024 (or even higher, the default
> is 256) may improve disk rendering.
>
>
> -------------------------------------------------------
> This SF.Net email is sponsored by: NEC IT Guy Games.  How
> far can you shotput a projector? How fast can you ride
> your desk chair down the office luge track? If you want to
> score the big prize, get to know the little guy.   Play to
> win an NEC 61" plasma display:
> http://www.necitguy.com/?r=20
> _______________________________________________
> Csound-devel mailing list
> Csound-devel@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/csound-devel


-------------------------------------------------------
This SF.Net email is sponsored by: NEC IT Guy Games.  How far can you shotput
a projector? How fast can you ride your desk chair down the office luge track?
If you want to score the big prize, get to know the little guy.  
Play to win an NEC 61" plasma display: http://www.necitguy.com/?r=20
_______________________________________________
Csound-devel mailing list
Csound-devel@lists.sourceforge.net

Date2005-06-11 18:24
FromIstvan Varga
SubjectRe: [Cs-dev] More OSX 10.3 benchmarks
One thing that may possibly improve performance is building
with useLrint=1. At least on x86 without using SSE this does
result in reduced CPU usage. It may or may not be useful on a Mac.


-------------------------------------------------------
This SF.Net email is sponsored by: NEC IT Guy Games.  How far can you shotput
a projector? How fast can you ride your desk chair down the office luge track?
If you want to score the big prize, get to know the little guy.  
Play to win an NEC 61" plasma display: http://www.necitguy.com/?r=20
_______________________________________________
Csound-devel mailing list
Csound-devel@lists.sourceforge.net