[petsc-dev] A closer look at the Xeon Phi

[Tim Tautges]

On 02/12/2013 06:40 PM, Jed Brown wrote:
> On Tue, Feb 12, 2013 at 6:06 PM, Tim Tautges <tautges at mcs.anl.gov <mailto:tautges at mcs.anl.gov>> wrote:
>
>     I'm kind of surprised at the > 10k element crossover myself.  For the strong scaling cases, at high core counts,
>     that's not terribly far from the number of DOFS per processor, is it?  I guess CPUs will be slower than the Xeon in
>     most cases (BGx), or fewer (Titan), but still.
>
>
> Which crossover are you referring to? The CPU versus GTX285 at about 20k dofs, but with only very small gains for
> another order of magnitude?
>

Yeah, that's what I meant.  There seems to be little benefit to both Phis and true GPUs until you get well above 20k 
DOFs per core, but for strong scaling studies, I wonder how many applications are really that large.  Maybe they are on 
Titan-class machines (fewer CPU cores, more memory/core), but maybe those cores are faster than the Xeon 55xx (not sure 
about that assertion), but then the crossover would be at even larger DOF counts.  If you take into account the added 
complexity of building those codes and running those machines, I still don't see the payoff to those machines.

Anybody know whether that effect showed up in the INCITE proposals?  Since users get charged for the GPUs whether they 
use them or not, I'd expect to see requests skewed toward Mira.

- tim

> For 2D Laplace, we expect to see strong scaling peter out around a couple thousand dofs per core. It can go a little
> further on Blue Gene because the network is much faster and the cores are a bit slower.
>
> Titan has a lot of (premium price) GPUs that you have to use to utilize the machine well, but it's unclear whether the
> architecture is delivering a science/dollars advantage, even if you ignore development costs to port and re-tune codes
> and the environment costs (it's more complicated to build and run, so it takes people longer to get running). I think
> the main justification is speculation about what future hardware will look like, not cost-effectiveness today.

-- 
================================================================
"You will keep in perfect peace him whose mind is
   steadfast, because he trusts in you."               Isaiah 26:3

              Tim Tautges            Adjunct Professor, Engr. Physics
          (tautges at engr.wisc.edu)    University of Wisconsin-Madison
         gphone: (608) 354-1459      1500 Engineering Dr.
            fax: (608) 263-4499      Madison, WI 53706