[Bioclusters] blast on opteron

[Andrew Shewmaker]

Joe Landman wrote:

<snip>
> Option 1 works today, it simply requires some process adjustment.  If
> this is possible you should be in good shape.  Option 2 may be possible,
> but I had some issues with quality of the opteron OSes I played with. 
> The compiler and library issues on these machines are annoying right
> now, but they should be resolved with AMD's help.  There are lots of
> distro's that "run" on the opteron, though I am not sure if they really
> support large memory directly, or if they use the PAE hack.  If it is
> the latter (the same way to support large memory on Xeon's), it is worth
> avoiding.  

I have tested an opteron's memory with a non-bio code.  It is a nuclear
model that in one particular problem allocated around 6GB RAM for a 
single process that ran for 2 days.  This model will not run when
compiled as a 32-bit executable on any platform, and PAE wouldn't change 
that.

This was with SuSE and I didn't experience any problems with the beta 
version of the Portland Group compiler on this code.  I'm looking 
forward to getting my own opteron's in the near future.

Andrew

-- 
Andrew Shewmaker, Associate Engineer
Phone: 1-208-526-1276
Idaho National Eng. and Environmental Lab.
P.0. Box 1625, M.S. 3605
Idaho Falls, Idaho 83415-3605