Presentation is loading. Please wait.

Presentation is loading. Please wait.

TAU Performance DataBase Framework (PerfDBF)

Similar presentations


Presentation on theme: "TAU Performance DataBase Framework (PerfDBF)"— Presentation transcript:

1 TAU Performance DataBase Framework (PerfDBF)
Allen D. Malony Department of Computer and Information Science Computational Science Institute University of Oregon

2 Outline Motivation for performance databases TAU performance system
TAU Performanc DataBase Framework Architecture XML profile data representation Example Performance engineering in software engineering X-PARE (eXPeriment Alerting and Reporting) Concluding remarks The TAU Performance DataBase Framework

3 Why Performance Databases?
Focus on empirical performance optimization process Necessary for multi-results performance analysis Multiple experiments (codes, versions, platforms, …) Historical performance comparison Integral component of performance analysis framework Improved performance analysis architecture design More flexible and open tool interfaces Supports extensibility and foreign tool interaction Performance analysis collaboration Performance tool sharing Performance data sharing and knowledge base The TAU Performance DataBase Framework

4 Empirical-Based Performance Optimization
Process Experiment Schemas Experiment Trials characterization Performance Tuning Performance Diagnosis Experimentation Observation hypotheses properties ? observability requirements The TAU Performance DataBase Framework

5 TAU Performance System Framework
Tuning and Analysis Utilities (aka Tools Are Us) Performance system framework for scalable parallel and distributed high-performance computing Targets a general complex system computation model nodes / contexts / threads Multi-level: system / software / parallelism Measurement and analysis abstraction Integrated toolkit for performance instrumentation, measurement, analysis, and visualization Portable performance profiling/tracing facility Open software approach The TAU Performance DataBase Framework

6 TAU Performance System Architecture
Paraver EPILOG The TAU Performance DataBase Framework

7 TAU Performance Database Framework
Performance analysis programs Performance data description Raw performance data PerfDML translators Performance analysis and query toolkit . . . ORDB PostgreSQL PerfDB profile data only XML representation project / experiment / trial The TAU Performance DataBase Framework

8 PerfDBF Components Performance Data Meta Language (PerfDML)
Common performance data representation Performance meta-data description PerfDML translators to common data representation Performance DataBase (PerfDB) Standard database technology (SQL) Free, robust database software (PostgresSQL) Commonly available APIs Performance DataBase Toolkit (PerfDBT) Commonly used modules for query and analysis Facility analysis tool development The TAU Performance DataBase Framework

9 Common and Extensible Profile Data Format
Goals Capture data from profile tools in common representation Implement representation in a standard format Allow for extension of format for new profile data objects Base on XML (obvious choice) Leverage XML tools and APIs XML parsers, Sun’s Java SDK, … XML verification systems (DTD and schemas) Target for profile data translation tools eXtensibile Stylesheet Language Transformations (XSLT) Which performance profile data are of interest? Focus on TAU and consider other profiling tools The TAU Performance DataBase Framework

10 Performance Profiling
Performance data about program entities and behaviors Code regions: functions, loops, basic blocks Actions or states Statistics data Execution time, number of calls, number of FLOPS ... Characterization data Parallel profiles Captured per process and/or per thread Program-level summaries Profiling tools prof/gprof, ssrun, uprofile/dpci, cprof/vprof, … The TAU Performance DataBase Framework

11 TAU Parallel Performance Profiles
The TAU Performance DataBase Framework

12 PerfDBF Example NAS Parallel Benchmark LU
% configure -mpiinc=/usr/include -mpilib=/usr/lib64 -arch=sgi64 -fortran=sgi -SGITIMERS -useropt=-O2 NPB profiled With TAU Standard TAU Output Data TAU to XML Converter TAU XML Format Database Loader SQL Database Analysis Tool The TAU Performance DataBase Framework

13 Scalability Analysis Process
Scalability study on LU % suite.def # of procs -> 1, 2, 4, and 8 % mpirun -np 1 lu.W1 % mpirun -np 2 lu.W2 % mpirun -np 4 lu.W4 % mpirun -np 8 lu.W8 populateDatabase.sh run Java translator to translate profiles into XML run Java XML reader to write XML profiles to database Read times for routines and program from experiments Calculate scalability metrics The TAU Performance DataBase Framework

14 Raw TAU Profile Data Raw data output One processor: Four processors:
"applu ” GROUP="applu“ Four processors: "applu ” GROUP="applu“ "applu " GROUP="applu“ "applu " GROUP="applu" profile calls group name exclusive time inclusive time name calls subs The TAU Performance DataBase Framework

15 XML Profile Representation
One processor <instrumentedobj> <funcname> 'applu '</funcname> <funcID>8</funcID> <inclperc>100.0</inclperc> <inclutime> E8</inclutime> <exclperc>0.0</exclperc> <exclutime> </exclutime> <call>1</call> <subrs>15</subrs> <inclutimePcall> E8</inclutimePcall> </instrumentedobj> The TAU Performance DataBase Framework

16 XML Representation Four processor mean <meanfunction>
<funcname>'applu '</funcname> <funcID>12</funcID> <inclperc>100.0</inclperc> <inclutime> E7</inclutime> <exclperc>0.0</exclperc> <exclutime> </exclutime> <call>1</call> <subrs>14.25</subrs> <inclutimePcall> E7</inclutimePcall> </meanfunction> The TAU Performance DataBase Framework

17 Contents of Performance Database
The TAU Performance DataBase Framework

18 Scalability Analysis Results
Scalability of LU performance experiments Four trial runs Funname | processors | meanspeedup …. applu | 2 | applu | 4 | applu | 8 | exact | 2 | exact | 4 | exact | 8 | The TAU Performance DataBase Framework

19 Current Status and Future
PerfDBF prototype TAU profile to XML translator XML to PerfDB populator PostgresSQL database Java-based PostgresSQL query module Use as a layer to support performance analysis tools Make accessing the Performance Database quicker Continue development XML parallel profile representation Basic specification Opportunity for APART to define a common format The TAU Performance DataBase Framework

20 Performance Tracking and Reporting
Integrated performance measurement allows performance analysis throughout development lifetime Applied performance engineering in software design and development (software engineering) process Create “performance portfolio” from regular performance experimentation (couple with software testing) Use performance knowledge in making key software design decision, prior to major development stages Use performance benchmarking and regression testing to identify irregularities Support automatic reporting of “performance bugs” Enable cross-platform (cross-generation) evaluation The TAU Performance DataBase Framework

21 XPARE - eXPeriment Alerting and REporting
Experiment launcher automates measurement / analysis Configuration and compilation of performance tools Instrumentation control for Uintah experiment type Execution of multiple performance experiments Performance data collection, analysis, and storage Integrated in Uintah software testing harness Reporting system conducts performance regression tests Apply performance difference thresholds (alert ruleset) Alerts users via if thresholds have been exceeded Web alerting setup and full performance data reporting Historical performance data analysis The TAU Performance DataBase Framework

22 XPARE System Architecture
Experiment Launch Mail server Web server Performance Database Performance Reporter Alerting Setup Comparison Tool Regression Analyzer The TAU Performance DataBase Framework

23 Experiment Results Viewing Selection
The TAU Performance DataBase Framework

24 Web-Based Experiment Reporting
The TAU Performance DataBase Framework

25 Web-Based Experiment Reporting (continued)
The TAU Performance DataBase Framework

26 Alerting Setup The TAU Performance DataBase Framework

27 Other Performance Database Projects
HPM Toolkit (DeRose; IBM) PPerfDB (Karavanic; Portland State University) HPCView (Mellor-Crummey, Fowler; Rice) SCALEA (Fahringer, Truong; University of Vienna) EXPERT (Mohr, Wolf; Research Center Juelich) The TAU Performance DataBase Framework

28 Acknowledgements University of Oregon University of Utah
Li Li, Robert Bell, Sameer Shende University of Utah Alan Morris, Steve Parker, Dav St. Germain Department of Energy (DOE), ASCI Academic Strategic Alliances Program (ASAP) Computational Science Institute, ASCI/ASAP Level 3 projects with LLNL / LANL, University of Oregon Center for the Simulation of Accidental Fires and Explosions (C-SAFE), ASCI/ASAP Level 1 center, University of Utah The TAU Performance DataBase Framework


Download ppt "TAU Performance DataBase Framework (PerfDBF)"

Similar presentations


Ads by Google