- Infos im HLRS Wiki sind nicht rechtsverbindlich und ohne Gewähr -
- Information contained in the HLRS Wiki is not legally binding and HLRS is not responsible for any damages that might result from its use -
Scalasca: Difference between revisions
(Update Scalasca for latest scalasca release and HAWK system) |
(Add link to Score-P) |
||
| (4 intermediate revisions by the same user not shown) | |||
| Line 13: | Line 13: | ||
To use Scalasca start by loading the respective software modules: | To use Scalasca start by loading the respective software modules: | ||
{{Command|command = | {{Command|command = | ||
module load scalasca scorep cube # on | <nowiki /># on HAWK: | ||
module load performance/scalasca performance/scorep | module load scalasca scorep cube | ||
<nowiki /># on Vulcan | |||
module load performance/scalasca performance/scorep | |||
}} | }} | ||
Then, instrument your application using Score-P by prefixing all MPI compiler and linker commands with the ''scorep'' command: | Then, instrument your application using [[Score-P]] by prefixing all MPI compiler and linker commands with the ''scorep'' command: | ||
{{Command|command = | {{Command|command = | ||
scorep mpicc myapp.c -o myapp | scorep mpicc myapp.c -o myapp | ||
}} | }} | ||
Next analyze your application using the ''scalasca -analyze'' command with your usual ''mpirun'' command: | Next analyze your application using the ''scalasca -analyze'' command with your usual ''mpirun'' command: | ||
{{Command|command= | {{Command|command= | ||
| Line 41: | Line 45: | ||
=== Usage on Hawk === | === Usage on Hawk === | ||
{{Warning|text= | {{Warning|text= | ||
It is necessary to set {{command|command=export MPI_SHEPHERD=true}} for the | It is necessary to set {{command|command=export MPI_SHEPHERD=true}} for the ''scalasca -analyze'' command. | ||
}} | }} | ||
Latest revision as of 13:27, 29 April 2020
| Scalasca is an open-source toolset for the performance analyzes of parallel applications helping to identify optimization opportunities. It has been specifically designed for the use on large-scale systems including Cray XT/XE, but is also well-suited for small- and medium-scale HPC platforms. Scalasca supports an incremental performance-analysis procedure that integrates runtime summaries with in-depth studies of concurrent behavior via event tracing, adopting a strategy of successively refined measurement configurations. A distinctive feature is the ability to identify wait states that occur, for example, as a result of unevenly distributed workloads. |
| ||||||||||||
Usage
To use Scalasca start by loading the respective software modules:
module load scalasca scorep cube
# on Vulcan
module load performance/scalasca performance/scorep
Then, instrument your application using Score-P by prefixing all MPI compiler and linker commands with the scorep command:
Next analyze your application using the scalasca -analyze command with your usual mpirun command:
scalasca -analyze mpirun -n ${NP} myapp
After the run there will be a folder prefixed with "scorep_*" containing the messurment results.
The last step is to explore the generated reports by using the scalasca -examine command, with the previously created "scorep_*" folder as the experiment name:
This will open Cube with the generated report automatically if you have enabled X forwarding. You can also inspect the generated *.cubex report files, manually starting the Cube GUI:
Usage on Hawk