Horatio B. Bogbindero
wyy at cersa.admu.edu.ph
Wed Sep 13 02:36:59 PDT 2000
> > Below are our results. The machines is 8 Athlon 550MHz and one 1Ghz Athlon.
> > 512 Mb memory each. and Myrinet.
> > WALL 6000 9 1 9 116.80 0.41 1229.04 0.001097 PASSED
> > WALL 6000 9 9 1 200.79 3.65 704.66 0.001926 PASSED
hi geof, i am running a 8-node athlon cluster w/ 128MB a piece. my grid
sizes are (2*4) and (4*2) and the matrix size is 6000x6000.
> it seems that you are far from what you can get from your cluster
> * First, 9 nodes is not a good idea, the (1*9) or (9*1) grids are
> bad. you should use only 8 nodes and try (2*4) and (4*2) grids,
> much better.
> * Then 6000 is not a big matrix. If you have 512 MB per node, you
> should go up to 20000. It will run longuer but you will be closest
> to the peak.
> * Which Blas do you use ? Atlas gives a DGEMM peak at 600 MFlops
> per Athlon, so you can hope about 4 GFlops on your cluster.
i use the atlas generated optimized blas. i compiled it to my system.
> * Which MPI do you use ? if it's MPICH-GM, do you use the
> -gm-can-register-memory flag ?
i use mpich from argonne v.1.2.0 w/ mpe.
> I strongly advice you to use the new High Performance Linpack
> (HPL) benchmark form Antoine Petitet
> (http://www.netlib.org/benchmark/index.html), it's faster than the
> old Linpack and much easier to install.
okay. i will check this out.
william.s.yu at ieee.org
I bought some used paint. It was in the shape of a house.
-- Steven Wright
More information about the Beowulf