Difference between revisions of "Intel Trace Analyzer and Collector"
Jump to navigation
Jump to search
import>Cen1001 |
import>Cen1001 |
||
| Line 2: | Line 2: | ||
mpicc -trace -o foo foo.c |
mpicc -trace -o foo foo.c |
||
| − | mpicc -tcollect -o foo foo.c |
+ | mpicc -tcollect -o foo foo.c # not sure what the difference is |
| − | itcpin -- foo |
+ | itcpin -- foo |
mpiexec foo |
mpiexec foo |
||
| + | |||
| + | The output is voluminous and rapidly causes the nodes to swap. You can filter it. |
||
| + | |||
| + | [cen1001@zero tracing]$ cat itac.conf |
||
| + | MEM-FLUSHBLOCKS 256 # flush to disk once you have 16Mb of data |
||
| + | MEM-MAXBLOCKS 1024 # stop and flush if you have more than 64Mb |
||
| + | FLUSH-PREFIX /scratch/cen1001 # where to flush to |
||
| + | STOPFILE-NAME /home/cen1001/STOP # this doesn't work unless you use the failsafe libs |
||
| + | |||
| + | echo $VT_CONFIG |
||
| + | /home/cen1001/src/NMM-MPI/tracing/itac.conf |
||
| + | |||
| + | qsub -v PATH,LD_LIBRARY_PATH,VT_CONFIG run.sh |
||
| + | |||
| + | traceanalyse |
||
Revision as of 16:06, 25 June 2008
This is a thing that came as part of the Intel cluster toolkit on zero but I am still figuring out how to use it, sp these are rough notes.
mpicc -trace -o foo foo.c mpicc -tcollect -o foo foo.c # not sure what the difference is itcpin -- foo mpiexec foo
The output is voluminous and rapidly causes the nodes to swap. You can filter it.
[cen1001@zero tracing]$ cat itac.conf MEM-FLUSHBLOCKS 256 # flush to disk once you have 16Mb of data MEM-MAXBLOCKS 1024 # stop and flush if you have more than 64Mb FLUSH-PREFIX /scratch/cen1001 # where to flush to STOPFILE-NAME /home/cen1001/STOP # this doesn't work unless you use the failsafe libs echo $VT_CONFIG /home/cen1001/src/NMM-MPI/tracing/itac.conf qsub -v PATH,LD_LIBRARY_PATH,VT_CONFIG run.sh
traceanalyse