[Bioclusters] new on using clusters: problem running mpiblast (2)

[Joe Landman]

Zhiliang Hu wrote:
> I did more trials on fixing possible problems with "mpiblast" 
> installations.
> 
> Now I have compiled
> 
>  mpiblast-1.4.0 along with ncbi tool kit (June 2005), with
>  mpicc --version
>    gcc (GCC) 4.1.1 20070105 (Red Hat 4.1.1-52)
> 
> and run it with
> 
>   mpirun (Open MPI) 1.2.3,
> 
> as following, and have errors:
> 
>> /opt/openmpi.gcc/bin/mpirun -np 14 -machinefile 
>> /home/zhu/tests/new/machines /home/local/bin/mpiblast -p blastp -i 
> ./bait.fasta -d ecoli.aa > blastoutput.txt

Please try a simple hello world test to verify that openmpi is working.

Grab

	http://downloads.scalableinformatics.com/downloads/MPI/Makefile.hello

and

http://downloads.scalableinformatics.com/downloads/MPI/hello.c

Modify the Makefile to verify that it works for you

[landman at crunch-r.scalableinformatics.com:~/test1] 
         9 >make -f Makefile.hello
/apps/openmpi123/pgi/bin/mpicc -c -g  hello.c
/apps/openmpi123/pgi/bin/mpicc -g   -g -o hello.exe hello.o -lm

and run it

[landman at crunch-r.scalableinformatics.com:~/test1] 
         10 >/apps/openmpi123/pgi/bin/mpirun -v -np 2 ./hello.exe
I am the master thread and I have a tid of 0
I am a worker thread, number 1 out of 2 total

If this does not work, it is not likely that mpiblast will work.

Joe

-- 

Joseph Landman, Ph.D
Founder and CEO
Scalable Informatics LLC,
email: landman at scalableinformatics.com
web  : http://www.scalableinformatics.com
        http://jackrabbit.scalableinformatics.com
phone: +1 734 786 8423
fax  : +1 866 888 3112
cell : +1 734 612 4615