- 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 -

Performance Analysis Tools: Difference between revisions

From HLRS Platforms
Jump to navigationJump to search
No edit summary
No edit summary
 
(11 intermediate revisions by 2 users not shown)
Line 1: Line 1:
Note: This page is in progress.
{{Note|text=This page is in progress. You might want to look at the corresponding category page for additional tools not listed here, yet: https://kb.hlrs.de/platforms/index.php/Category:Performance_Analyzer }}


There are several tools to analyse the performance of your application. Some are pre-installed on our systems and ready to use. Please see the documentation to get more details of every tool.
There are several tools to analyse the performance of your application. Some are pre-installed on our systems and ready to use. Please see the documentation to get more details of every tool.
{{Warning|text=Please make sure to always set ''MPI_SHEPHERD=true'' when using performance analysis tools with MPT MPI. Otherwise you might crash the nodes you are working on.}}


{| class="wikitable"
{| class="wikitable"
Line 8: Line 10:
! Purpose
! Purpose
! Available on
! Available on
|-
| [[Advisor|Advisor]]
| threading assistant
| [[HPE Hawk|Hawk]]
|-
|-
| [[Darshan|Darshan]]
| [[Darshan|Darshan]]
| tracing IO performance of mpi programms
| tracing IO performance of mpi programms
| [[HPE Hawk|Hawk]]
| [[HPE Hawk|Hawk]]
|-
| [[Extrae|Extrae]]
| record MPI communication events
| [[HPE Hawk|Hawk]]
|-
| [[Kojak|Kojak]]
|
|
|-
| [[LIKWID|LIKWID]]
|
|
|-
| [[MpiP|MpiP]]
| simple MPI profiling
| [[HPE Hawk|Hawk]]
|-
| [[OPT|OPT]]
|
|
|-
| [[Paraver|Paraver]]
|
|
|-
| [[Scalasca|Scalasca]]
|
|
|-
|-
| [[Score-P|Score-P]]
| [[Score-P|Score-P]]
| tracing and sampling of MPI and Open MP parallel applications
| tracing and sampling of MPI and Open MP parallel applications
| [[HPE Hawk|Hawk]], [[Vulcan|Vulcan]]
| [[HPE Hawk|Hawk]], [[Vulcan|Vulcan]]
|-
| [[Threadspotter|Threadspotter]]
|
|
|-
| [[Trace Analyzer and Collector|Trace_Analyzer_and_Collector]]
|
|
|-
| [[Vampir|Vampir]]
|
|
|-
| [[VTune|VTune]]
|
|
|-
|-
|}
|}

Latest revision as of 14:27, 20 April 2023

Note: This page is in progress. You might want to look at the corresponding category page for additional tools not listed here, yet: https://kb.hlrs.de/platforms/index.php/Category:Performance_Analyzer


There are several tools to analyse the performance of your application. Some are pre-installed on our systems and ready to use. Please see the documentation to get more details of every tool.

Warning: Please make sure to always set MPI_SHEPHERD=true when using performance analysis tools with MPT MPI. Otherwise you might crash the nodes you are working on.


Tool Purpose Available on
Advisor threading assistant Hawk
Darshan tracing IO performance of mpi programms Hawk
Extrae record MPI communication events Hawk
Kojak
LIKWID
MpiP simple MPI profiling Hawk
OPT
Paraver
Scalasca
Score-P tracing and sampling of MPI and Open MP parallel applications Hawk, Vulcan
Threadspotter
Trace_Analyzer_and_Collector
Vampir
VTune