mpiblast
Differences
This shows you the differences between two versions of the page.
Both sides previous revisionPrevious revision | Next revisionBoth sides next revision | ||
mpiblast [2010/01/29 09:39] – 172.26.0.166 | mpiblast [2010/01/29 09:41] – 172.26.0.166 | ||
---|---|---|---|
Line 41: | Line 41: | ||
MCA ras: gridengine (MCA v2.0, API v2.0, Component v1.3.2)</ | MCA ras: gridengine (MCA v2.0, API v2.0, Component v1.3.2)</ | ||
===== Benchmarks ===== | ===== Benchmarks ===== | ||
+ | |||
+ | ==== Standard BLAST ==== | ||
< | < | ||
| | ||
Line 47: | Line 49: | ||
sys | sys | ||
+ | ==== MPI Blast on 1 node ==== | ||
< | < | ||
Total Execution Time: 395.754 | Total Execution Time: 395.754 | ||
Line 54: | Line 57: | ||
sys | sys | ||
- | With 12 jobs, sge, mpiblast, 6 nodes did it in: | + | ==== MPI Blast with 12 jobs, 6 nodes ==== |
< | < | ||
Total Execution Time: 98.3068</ | Total Execution Time: 98.3068</ | ||
+ | ==== Paracel Blast ==== | ||
< | < | ||
Line 66: | Line 70: | ||
The number of processes for an MPI job should be +1 of the number of CPUs because one process is used as the master to control the other jobs. | The number of processes for an MPI job should be +1 of the number of CPUs because one process is used as the master to control the other jobs. | ||
+ | |||
===== Random Notes ===== | ===== Random Notes ===== | ||
Line 97: | Line 102: | ||
* wwwblast: http:// | * wwwblast: http:// | ||
* OpenMPI FAQ: http:// | * OpenMPI FAQ: http:// | ||
- |