Score-P - Revision history

Simon-schwitanski-3f90@rwth-aachen.de at 17:37, 9 September 2023

2023-09-09T17:37:53Z

Marc-andre-hermanns-bc32@rwth-aachen.de: Adding focus element to infobox

2022-03-03T16:40:13Z

Adding focus element to infobox

Marc-andre-hermanns-bc32@rwth-aachen.de: Fix unnecessary newline at top of page

2022-03-03T14:36:02Z

Fix unnecessary newline at top of page

Marc-andre-hermanns-bc32@rwth-aachen.de: Added Software Infobox

2022-03-03T14:35:03Z

Added Software Infobox

Marc-andre-hermanns-bc32@rwth-aachen.de: Tweak wording and improve inter-page linkeage

2020-10-02T13:51:33Z

Tweak wording and improve inter-page linkeage

Robert-dietrich-26ef@tu-dresden.de: /* RWTH */

2019-10-07T08:50:26Z

RWTH

Daniel-schurhoff-de23@rwth-aachen.de at 08:29, 5 September 2019

2019-09-05T08:29:27Z

Fabian-orland-a681@rwth-aachen.de: added RWTH site-specific information

2019-08-22T15:34:42Z

added RWTH site-specific information

Fabian-orland-a681@rwth-aachen.de: /* Instrumentation */

2019-08-20T08:22:31Z

Instrumentation

Fabian-orland-a681@rwth-aachen.de at 08:19, 20 August 2019

2019-08-20T08:19:47Z

@@ Line 72: / Line 72: @@
 === RWTH ===
 In order to use Score-P on the RWTH cluster you need to load the corresponding module.
 <syntaxhighlight lang="sh">
-$ module load DEV-TOOLS
+$ module load Score-P
 </syntaxhighlight>
 Depending on your currently loaded compiler and MPI implementation this will automatically load the correct version of Score-P for you.
 However, if you want to have an overview about all the available Score-P versions use the following command:
 <syntaxhighlight lang="sh">
-$ module avail scorep
+$ module avail Score-P
 </syntaxhighlight>

@@ Line 2: / Line 2: @@
 {{Infobox Software
 | name = Score-P
 | provider = Score-P Development Team
 | homepage = https://score-p.org

@@ Line 1: / Line 1: @@
-[[Category:HPC-Developer]]
+[[Category:HPC-Developer]]<nowiki />
 {{Infobox Software
 | name = Score-P
@@ Line 9: / Line 9: @@
 | lang = C, C++, Fortran, Python
 | license = Open Source, BSD-like
-}}
+}}<nowiki />
 Score-P is a performance measurement infrastructure for profiling, event tracing and online analysis of (parallel) HPC applications.
 It allows users to instrument and record the behavior of sequential, multi-process ([[MPI]], [[SHMEM]]), thread-parallel ([[OpenMP]], [[Pthreads]]) and accelerator-based ([[CUDA]], [[OpenCL]]) applications as well as hybrid parallel applications.

@@ Line 1: / Line 1: @@
 [[Category:HPC-Developer]]
 Score-P is a performance measurement infrastructure for profiling, event tracing and online analysis of (parallel) HPC applications.
 It allows users to instrument and record the behavior of sequential, multi-process ([[MPI]], [[SHMEM]]), thread-parallel ([[OpenMP]], [[Pthreads]]) and accelerator-based ([[CUDA]], [[OpenCL]]) applications as well as hybrid parallel applications.

@@ Line 1: / Line 1: @@
 [[Category:HPC-Developer]]
 Score-P is a performance measurement infrastructure for profiling, event tracing and online analysis of (parallel) HPC applications.
-It allows users to instrument and record the behavior of sequential, multi-process (MPI, SHMEM), thread-parallel (OpenMP, Pthreads) and accelerator-based (CUDA, OpenCL) applications as well as hybrid parallel applications.
+It allows users to instrument and record the behavior of sequential, multi-process ([[MPI]], [[SHMEM]]), thread-parallel ([[OpenMP]], [[Pthreads]]) and accelerator-based ([[CUDA]], [[OpenCL]]) applications as well as hybrid parallel applications.
 == General ==
@@ Line 8: / Line 8: @@
 * Periscope
-* Scalasca
+* [[Scalasca]]
 * [[Vampir]]
-* Tau
+* [[TAU]]
-It comes with the new Open Trace Format Version 2, the Cube4 profiling format and the Opari2 instrumenter and is available under the New BSD Open Source license.
+It uses the [[OTF2|Open Trace Format Version 2]] for event traces and the [[Cube|Cube4]] profiling format for runtime summaries.
 == Instrumentation ==
@@ Line 48: / Line 50: @@
 Score-P produces experiment results in different commonly used formats.
-Call-path profiles are stored in the CUBE4 format and can be viewed using the [https://www.scalasca.org/scalasca/software/cube-4.x/download.html Cube] tool.
+Call-path profiles are stored in the [[Cube|CUBE4]] format and can be viewed using the [https://www.scalasca.org/scalasca/software/cube-4.x/download.html Cube] tool.
-Event traces are stored in the [https://silc.zih.tu-dresden.de/otf2-current/html/index.html Open Trace Format 2] and can be visualized using tools like [https://vampir.eu/ Vampir] or [https://www.scalasca.org/ Scalasca].
+Event traces are stored in the [https://silc.zih.tu-dresden.de/otf2-current/html/index.html Open Trace Format 2] and can be visualized using tools such as [https://vampir.eu/ Vampir] or automatically analyzed with tools such as [https://www.scalasca.org/ Scalasca].
 == Score-P Plugins ==

← Older revision		Revision as of 08:29, 5 September 2019
Line 1:		Line 1:
		+	[[Category:HPC-Developer]]
	Score-P is a performance measurement infrastructure for profiling, event tracing and online analysis of (parallel) HPC applications.		Score-P is a performance measurement infrastructure for profiling, event tracing and online analysis of (parallel) HPC applications.
	It allows users to instrument and record the behavior of sequential, multi-process (MPI, SHMEM), thread-parallel (OpenMP, Pthreads) and accelerator-based (CUDA, OpenCL) applications as well as hybrid parallel applications.		It allows users to instrument and record the behavior of sequential, multi-process (MPI, SHMEM), thread-parallel (OpenMP, Pthreads) and accelerator-based (CUDA, OpenCL) applications as well as hybrid parallel applications.

@@ Line 54: / Line 54: @@
 Score-P provides two plugin interfaces: metrics, which allows integrating new metric sources, and substrates, which allows adding new event consumers besides profiling and tracing. You can also write your own plugins.
 == References ==
 [https://www.vi-hps.org/projects/score-p/ Score-P website].

@@ Line 16: / Line 16: @@
 Performing automatic instrumentation can simply be done by replacing your compiler command with the appropriate Score-P wrapper.
-The following example uses the Intel C compiler:
+The following example assumes your C compiler is given by the variable $CC:
 <syntaxhighlight lang="bash">
-$ scorep icc <compile_flags>
+$ scorep $CC <compile_flags>
 </syntaxhighlight>
-Score-P also supports MPI applications. Again the corresponding MPI-compiler-wrapper for Score-P needs to be used to ensure correct linking of the MPI libraries. Using the Intel MPI C compiler this looks like:
+Score-P also supports MPI applications. Again the corresponding MPI-compiler-wrapper for Score-P needs to be used to ensure correct linking of the MPI libraries. Assuming the MPI C compiler is referenced by the variable $MPICC this looks like:
 <syntaxhighlight lang="bash">
-$ scorep mpicc <compile_flags>
+$ scorep $MPICC <compile_flags>
 </syntaxhighlight>