Performance profiling - Revision history

Robert-schade-e757@uni-paderborn.de at 11:31, 19 July 2024

2024-07-19T11:31:26Z

2019-09-04T06:30:53Z

2019-08-20T14:09:54Z

Oracle Sampling Collector and Performance Analyzer

2019-08-20T14:08:07Z

Oracle Sampling Collector and Performance Analyzer

2019-08-20T08:29:38Z

Score-P: added link to own Score-P page

2019-08-20T08:28:32Z

added link to Score-P page

2019-08-20T08:26:41Z

SCORE-P: refactored information regarding Score-P into own page

2019-08-19T16:10:23Z

Oracle Performance Analyzer

2019-08-19T15:48:02Z

Tools

2019-08-19T15:43:42Z

Measurement

← Older revision		Revision as of 11:31, 19 July 2024
Line 1:		Line 1:
	[[Category:HPC-Developer]]		[[Category:HPC-Developer]]
		+	[[Category:Benchmarking]]<nowiki />
		+
	In a performance engineering context performance profiling means to relate performance metric measurements to source code execution. Data sources are typically either operating system, execution environments or measurement facilities in the hardware. The following explanations focus on hardware performance monitoring (HPM) based metrics.		In a performance engineering context performance profiling means to relate performance metric measurements to source code execution. Data sources are typically either operating system, execution environments or measurement facilities in the hardware. The following explanations focus on hardware performance monitoring (HPM) based metrics.

← Older revision		Revision as of 06:30, 4 September 2019
Line 1:		Line 1:
		+	[[Category:HPC-Developer]]
	In a performance engineering context performance profiling means to relate performance metric measurements to source code execution. Data sources are typically either operating system, execution environments or measurement facilities in the hardware. The following explanations focus on hardware performance monitoring (HPM) based metrics.		In a performance engineering context performance profiling means to relate performance metric measurements to source code execution. Data sources are typically either operating system, execution environments or measurement facilities in the hardware. The following explanations focus on hardware performance monitoring (HPM) based metrics.

@@ Line 52: / Line 52: @@
 All recommended metrics can be measured using the MEM_DP/MEM_SP, BRANCH, DATA, L2 and L3 performance groups.
-=== [[Oracle Sampling Collector and Performance Analyzer]] ===
+=== Oracle Sampling Collector and Performance Analyzer ===
 The Oracle Sampling Collector and the Performance analyzer are a pair of tools that can be used to collect and analyze performance data for serial or parallel applications.

@@ Line 52: / Line 52: @@
 All recommended metrics can be measured using the MEM_DP/MEM_SP, BRANCH, DATA, L2 and L3 performance groups.
-=== Oracle Sampling Collector and Performance Analyzer ===
+=== [[Oracle Sampling Collector and Performance Analyzer]] ===
 The Oracle Sampling Collector and the Performance analyzer are a pair of tools that can be used to collect and analyze performance data for serial or parallel applications.
-==== The Oracle Sampling Collector ====
+Performance data including a hierarchy of function calls and hardware performance counters, for example, can be gathered by executing the program under control of the Sampling Collector:
+<syntaxhighlight lang="sh">
+$ collect <opt> a.out
-==== The Oracle performance Analyzer ====
+</syntaxhighlight>
 === Intel VTune Amplifier ===

@@ Line 85: / Line 85: @@
 Help on using `amplxe-cl` with MPI is found [https://software.intel.com/en-us/vtune-amplifier-help-mpi-code-analysis here].
-=== SCORE-P ===
+=== Score-P ===
-[[SCORE-P]] is an infrastructure supporting multiple other tools as backend. Targeted at large scale parallel measurements. More information can be found [https://www.vi-hps.org/projects/score-p/ here].
+[[Score-P]] is an infrastructure supporting multiple other tools as backend. Targeted at large scale parallel measurements. More information can be found [https://www.vi-hps.org/projects/score-p/ here].
 === TAU ===

@@ Line 87: / Line 87: @@
 === SCORE-P ===
-The Score-P measurement infrastructure is a tool for profiling, event tracing and online analysis targeted at large scale parallel measurements. The project website can be found [https://www.vi-hps.org/projects/score-p/ here].
+SCORE-P is an infrastructure supporting multiple other tools as backend. Targeted at large scale parallel measurements. More information can be found [https://www.vi-hps.org/projects/score-p/ here].
 === TAU ===

← Older revision		Revision as of 15:48, 19 August 2019
Line 51:		Line 51:

	All recommended metrics can be measured using the MEM_DP/MEM_SP, BRANCH, DATA, L2 and L3 performance groups.		All recommended metrics can be measured using the MEM_DP/MEM_SP, BRANCH, DATA, L2 and L3 performance groups.
		+
		+	=== Oracle Performance Analyzer ===

	=== Intel VTune Amplifier ===		=== Intel VTune Amplifier ===

@@ Line 103: / Line 103: @@
 * $SCOREP_METRIC_RUSAGE - resource usage metric names to measure
 Note that tracing is disabled by default because it can cause substantial additional overhead and may produce lots of data, which will ultimately perturb your application runtime behavior during measurement.
-More environment variables can be found in the [http://scorepci.pages.jsc.fz-juelich.de/scorep-pipelines/docs/scorep-6.0/pdf/scorep.pdf Score-P documentation (Appendix G - Score-P Measurement Configuration)] or using the command:
+More environment variables can be found in the [http://scorepci.pages.jsc.fz-juelich.de/scorep-pipelines/docs/scorep-6.0/pdf/scorep.pdf Score-P documentation] (Appendix G - Score-P Measurement Configuration) or using the command:
 <syntaxhighlight lang="bash">
 $ scorep-info config-vars --full