multi core os x machines

[Satish Balay]

Actually the new intels are pretty similar to the AMDs these days.

There are 2 things here:
- multiple-cores per chip
- and multiple chips

For eg: one can buy 2-chip-dual-core = 4CPU machine.

[with AMD each chip has a separate memory bank. With intel, there is a
single controller with multiple banks. But when 1 chip is used - only
half the memory banks are accessed - or something like that]

So in both AMD and Intel, when both chips [each chip - a dual-core]
are used, MB available scales up - as compared to 1 chip usage.

However within a chip [i.e dual core] - the MB from main memory to
cpu/cache is same irrespective of both cores being used or only
one. So when both are used - the effective memory bandwith is not
scaling up.

So to get best parallel speedup - one should choose 'np' as
'no_of_memory banks' - not 'no_of_cpus'. So, on this 2x2 = 4CPU
machine, I suspect the best performance scaling can be seen only with
'-np 2'

Wrt MPICH on SMP, we were sugested to use the following MPICH
configure options:

--with-pm=gforker --device=ch3:nemesis --enable-fast

Satish

On Tue, 13 Nov 2007, Barry Smith wrote:

> 
>  It depends on how the memory is connected to the individual cores or CPUS;
> for example the AMD has a different approach than Intel. If the different
> processors/cores
> have SEPERATE paths to memory then you will not see this terrible effect.
> 
>   Barry
> 
> 
> 
> On Nov 13, 2007, at 10:23 AM, Gideon Simpson wrote:
> 
> > This is also true for a multi-processor machine, or its unique to multi-core
> > machines?
> > -gideon
> > 
> > On Nov 13, 2007, at 11:14 AM, Barry Smith wrote:
> > 
> > > 
> > >  Not possible. The problem is that with one process it uses all the memory
> > > bandwidth, when you change to use 2 processes (2 cores) each core
> > > now gets only half the memory bandwidth and hence essentially half
> > > the speed.
> > > 
> > >   Barry
> > > 
> > > 
> > >   Barry
> > > 
> > > On Nov 13, 2007, at 10:06 AM, Gideon Simpson wrote:
> > > 
> > > > Has anyone had any success in getting good performance on multi-core
> > > > intel os x machines with petsc?  What's the right way to get MPICH up
> > > > and running for such a thing?
> > > > 
> > > > -Gideon Simpson
> > > > Department of Applied Physics and Applied Mathematics
> > > > Columbia University
> > > > 
> > > > 
> > > 
> > 
>