[Omp] Noob question about processors

[Klaas Vantournhout]

Hi Christian, thanks for your response

>> I just started with using OpenMP on the gcc4.2
>> compiler.
> I assume you are aware that the gcc 4.2 OpenMP implementation is still
> in some kind of beta state?

Yes I am.  Currently the development of the gcc4.2 compiler is in stage3
which means that only bugs are fixed and ports added that do not change
other parts of the compiler.  I think it is worth testing with it.

> Scheduling depends on the OpenMP runtime library and the operating
> system.
> AFAIK the combination gcc/linux does not provide reliable mechanisms to
> bind threads to processors. You can expect that if your program is the
> only one running on that node only one thread at a time will run on
> given processor, but you will probably experience your threads changing
> the processors very often. This situation is different on Solaris (for
> example) where you can do explicit thread binding.

So if I understand correctly, you mean that gcc/linux is not able to
spread the tasks over 2 real cpu's and only puts the threads on one of
those.  This would explain why I only obtain a speed up of 2 instead of 4.

> Make sure you know about the OMP_DYNAMIC environment variable.
I will look into that.

Thanks
Klaas



-- 
"Several billion trillion tons of superhot
exploding hydrogen nuclei rose slowly above
the horizon and managed to look small, cold
and slightly damp."
	Douglas Adams - The Hitch Hickers
		Guide to the Galaxy