On Jun 23, 2004, at 12:22 PM, Joe Landman wrote: > Ok. Which binary are you using? Did you build it yourself? Is it > one of the > precompiled ones (including the Scalable Informatics LLC version)? > Would you > mind sharing it? I'm using NCBI's precompiled binary -- the one from ftp://ftp.ncbi.nlm.nih.gov/blast/executables/LATEST-BLAST/blast-2.2.9- ia32-linux.tar.gz > What happens if you boot one of the units with a "mem=1024M" option, > which > forces Linux to use only 1 GB ram? There are some oddities that > happen at the 4 > GB region (really 3.8 GB or so depending upon which kernel you are > using). I tried this, and still get the failure. I've also run my test on 1Gb and 2Gb nodes with about the same failure rate as on the 4Gb nodes. > If I build a static binary of blastall, would you be willing to give > it a try? Yes, I'll definitely try it if you are willing to build a binary. >> I've also run Blast with the same db+query on an SGI Origin 3400 with >> no failures, using -a 2, -a 3, -a 4. > > I presume this is with the native MIPSpro compilers (very good > compilers BTW) > and not gcc? This is NCBI's precompiled binary: ftp://ftp.ncbi.nlm.nih.gov/blast/executables/LATEST-BLAST/blast-2.2.9- mips64-irix.tar.gz There is limited information about how they compile it, but I'm hoping NCBI will provide some answers when they respond to my email. Susan.