Re: Octave 3.6.0 on Windows XP plot fails.

[Martin Helm]

Am Mittwoch, 29. Februar 2012, 16:17:36 schrieb Michael Goffioul:
> On Wed, Feb 29, 2012 at 3:09 PM, Martin Helm <address@hidden> wrote:
> >> No, I think it's because of the principle of hyperthreading. HT does
> >> not mean you magically have 4 independent cores out of 2. You still
> >> have only 2 physical cores, but some parts of each core are duplicated
> >> such that they can appear as 4 instead of 2 at the OS level. However,
> >> the processing unit is not duplicated: so within a single physical
> >> core, each logical CPU will have to wait its turn on the processing
> >> unit.
> >> 
> >> So roughly, if you have 4 operations that you can perform in parallel,
> >> only 2 will be done really simultaneously.
> >> 
> >> HT can increase performances when you have 2 threads, one of which is
> >> stuck for some reason (waiting for data for instance). Then the other
> >> thread can use the processing unit while the first one is waiting. But
> >> if the 2 threads need the processing unit at the same time, you won't
> >> gain anything.
> >> 
> >> So I think that what  Xianyi Zhang means is that matrix multiplication
> >> is this kind of operations that cannot really benefit from HT. For the
> >> record, I've tried a 2-threaded ATLAS on a P4-HT (1 physical CPU, 2
> >> logical CPUs) and the performances were lower than a single-threaded
> >> one.
> >> 
> >> Michael.
> > 
> > Performing now my previous trivial example on my atom netbook (dual core
> > atom with hyperthreading, htop shows 4 threads are used) ATLAS gives me
> > a speedup by a factor 2.4 (so more than double!) when using multi vs
> > single threaded atlas.
> 
> You're actually confirming my explanation. Indeed 2.4 is better than
> 2, but way lower than 4. In various cases, HT will improve
> performances, because some threads are actually stuck waiting for
> data. But that's not always the case.
> 
> Michael.

I do not claim that a hyperthreaded bunch of threads scales as well as a bunch 
od threads running on different physical cpu's (if you read that that was not 
what i want to say).
Your comment just sounded to me a bit like you never get more than the 
physical core number as speedup which simply contradicts my experience, sorry 
if I misinterpreted what you wrote.
And of course you will also never get a speedup by a factor n when using n 
physical cores as well since overhead is involved.