derek@x-i.net schrieb:

i get these CPU jumps in a big way under Linux and Win both. i've been told it has a lot to do with signals which are very near zero, but not quite. johannes taelman told me the technical name for this, but i have forgotten it... "denormal numbers", maybe ....

That's right. The CPU switches to an 'extra accurate and very slow' (i.e. foating point) mode when it is asked to calculate very small values. A fix in terms of changing the source code it to add the following:

#define undenormalise(sample) if(((*(unsigned int*)&sample)&0x7f800000)==0) sample=0.0

and add

undenormalise(myfloatvalue);

wherever a calculation might have produced very small values (reüplaye 'myfloatvalue' with the variable that stores the float). There are many many places in the Pd sources (and in every external) where this happens. My freeverb~ (and also cverb~) just wouldn't work work without his since reverb tails tend to get weaker and weaker but (due to unaccurate calculation) probably never really get 0.0.

anyway, if there are any patches which can be applied to a Linux compile of PD which are bug fixes for this, can somebody let me know? otherwise, how do people usually handle this.

I once realised that this problem (on Win) is reduced when I compile with the intel compiler and optimisation for P4. Don't know if this would work for Linux as well. The compiler can be downloaded from Intel and has a 30-day trial time, maybe someone can give it a try. 'Fresh' P4-optimised binaries for Win can be downloaded from http://www.akustische-kunst.org/puredata/experimental/pd0.36-win-P4.zip (based on pd0.36-0 since pd0.37-test4 does not work with my Motu 828). Just unzip the files into Pd's bin directory.

thomas musil says he just pumps a very small signal that is over this threshold through the whole system. could you also "clip~" the signal streams, except to clip them on the low end?

The trick is to avoid signals of getting below a certain limit. The code above does this by setting them to 0.0, adding a signal does it by always keeping the signals above this threshold.

Olaf

I just always add a noise~ to critical sections. I think jMax actually detects these denormalized values in some way. This might probably help to find the missing problematic spots and handle it inplace with the PD_BADFLOAT macro.

Guenter

On Sat, 24 May 2003, Johannes Taelman wrote:

Hi Derek, list,

...

derek@x-i.net schrieb:

...

has a lot to do with signals which are very near zero, but not quite. johannes taelman told me the technical name for this, but i have forgotten it... "denormal numbers", maybe ....

Yup, that was what I was talking about at pdStaminee. I don't think it explains 100% of the cpu load variations. CPU cache management decisions may be another cause.

Here's an overview of denormal handling: http://www.musicdsp.org/files/denormal.pdf

and http://phonophunk.phreakin.com/p4denormal.html

mvg, j#|@

---

PD-list mailing list PD-list@iem.kug.ac.at http://iem.kug.ac.at/cgi-bin/mailman/listinfo/pd-list

anyone experience (and then solve) a prob with compiling pd under debian unstable.

keep getting (with gcc 3.3)

dereferencing type-punned pointer will break strict-aliasing rules.

taking away -Wall lets it compile, but makes me wonder.

-august.

On Sunday 25 May 2003 19:47, Tim Blechmann wrote:

but i even had some trouble to compile the linux kernel... so i downdated to gcc 3.2.3 ... i'll wait for the next update...

on #debian : /msg apt 2.4bug

apt < 2.4bug

i guess 2.4bug is look at http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=194287 as it says there, gcc-3.3 cannot compile 2.4 kernels, apt-get install gcc-3.2 or gcc-2.95 (preferred) then edit the top level Makefile before you make dep with: perl -pi.bak -e 's/gcc/gcc-2.95/' Makefile

otherwise, if you want to compile something with a special gcc, export CC=gcc-2.95 works well

cheers, paul.

Zitiere Tim Blechmann TimBlechmann@gmx.net:

and maybe someone can offer some webspace that i can put my optimized binaries online...

hi, you can put it onto the IEM-ftp server. there should be an incoming-folder that will allow you to put files on our server with an anonymous-access. i will then move it into ftp://iem.at/pd/LINUX/ by hand. Maybe we will find a better solution in the future (authenticated accounts)

mfg.ad.sr IOhannes

there should be an incoming-folder that will allow you to put files on our server with an anonymous-access.

i've uploaded my binaries to the incoming folder... i haven't uploaded any externals, yet... i'll have to check which ones are compiled with icc...

Tim mailto:TimBlechmann@gmx.net ICQ: 96771783 http://www.nyds-exp-discogs.tk -- The only people for me are the mad ones, the ones who are mad to live, mad to talk, mad to be saved, desirous of everything at the same time, the ones who never yawn or say a commonplace thing, but burn, burn, burn, like fabulous yellow roman candles exploding like spiders across the stars and in the middle you see the blue centerlight pop and everybody goes "Awww!" Jack Kerouac