Clovertown HPL scores

[Brent_Clements at Dell.com]

Kilian,
 
Actually 78% efficiency is pretty darn good. Look at the top 500 list and see that on average the efficiencies are between 75 and 80 percent. Your going to get worse efficiency as you scale up though.
 
Brent C.

________________________________

From: linux-poweredge-bounces at dell.com on behalf of Kilian CAVALOTTI
Sent: Tue 3/27/2007 4:20 PM
To: Robin Humble; linux-poweredge-Lists
Subject: Re: Clovertown HPL scores



On Monday 26 March 2007 08:30:08 pm you wrote:
> I'd say 70-80% is the best you could expect.
> on a single core you can expect close to 90%, but not on all 8.

Well, I tried on a single core, with P = Q = 1 and 'mpirun -np 1', and I
only get 78% efficiency, which is not exactly impressive.

> I see 75.7% on 1.6 GHz pe1950 dual quad-core Clovertowns with 4g ram.

That's almost 10% better that what I can get for 8 jobs. Do you think the
MPI implementation/compiler is at fault?

> these Woodcrests and Clovertown chips seem to lack memory bandwidth
> when trying to feed 4 flops/cycle, and also probably suffer bus
> contention due to the fairly pathetic Intel shared memory bus
> architecture. large caches only get you so far...
>
> having said that, you might get a better result with the threaded
> GotoBLAS - it generally performs better on a single node (but sometimes
> not for a large number of nodes). also NB of 192 or 256. the rest of
> your settings look fine.

Thanks for the info, I'll continue to try to find better parameters.

Cheers,
--
Kilian

_______________________________________________
Linux-PowerEdge mailing list
Linux-PowerEdge at dell.com
http://lists.us.dell.com/mailman/listinfo/linux-poweredge
Please read the FAQ at http://lists.us.dell.com/faq