Difference between revisions of "Milestones"

From Point
Jump to: navigation, search
(New page: {| !UO |- Add routine-level and message passing AI |- Develop experimentation framework and user frontend |- Develop comparative analysis modules |- Update PerfDMF for regression analysis...)
 
(→‎PHASE 2)
 
(10 intermediate revisions by 2 users not shown)
Line 1: Line 1:
−
{|
+
''Goals that emphasize interaction between institutions are marked in bold.''
−
!UO  
+
 
−
|- Add routine-level and message passing AI
+
==UO==
−
|- Develop experimentation framework and user frontend
+
====PHASE 1====
−
|- Develop comparative analysis modules
+
* Add routine-level and message passing AI
−
|- Update PerfDMF for regression analysis
+
* Develop experimentation framework and user frontend
−
|- '''OTF format updates for EPILOG'''
+
* Develop comparative analysis modules
−
|- '''Evaluate sample-based and direct measurement integration'''
+
* Update PerfDMF for regression analysis
−
|
+
* '''OTF format updates for EPILOG'''
−
!UTK
+
* '''Evaluate sample-based and direct measurement integration'''
−
|- Define common multi-core events
+
 
−
|- Port KOJAK distributed trace file analysis to cluster environment
+
====PHASE 2====
−
|- Develop additional KOJAK patterns for hardware counter profile data
+
* Develop controller for parametric experiments
−
|- '''Automate use of TAU call-path profiles for selective EPILOG tracing'''
+
* Develop user-interface for ACA power tool
−
|}
+
* Build PRA prototype, link with software test harness
 +
* '''Implement joint measurement support'''
 +
* '''Update PerfDMF for PerfSuite data'''
 +
* '''Incorporate PAPI features for multi-core'''
 +
 
 +
====PHASE 3====
 +
* Port AI on HPC systems and test
 +
* Complete AE framework and release
 +
* Integrate ACA with experimentation system
 +
* Complete ACA framework and release
 +
* Integrate PRA with application groups
 +
* '''Merge automatic profile analysis with KOJAK'''
 +
 
 +
==UTK==
 +
====PHASE 1====
 +
* Define common multi-core events
 +
* Port Scalasca distributed trace file analysis to cluster environment
 +
* Develop additional Scalasca patterns for hardware counter profile data
 +
* '''Automate use of TAU call-path profiles for selective EPILOG tracing'''
 +
 
 +
====PHASE 2====
 +
* Implement additional PAPI network components
 +
* Test distributed trace file analysis on production applications
 +
* Migrate contextual hardware counter information to PAPI standard
 +
* '''Incorporate PerfSuite and TAU profiles into Scalasca analysis'''
 +
 
 +
====PHASE 3====
 +
* Continue to develop and deploy component PAPI
 +
* Incorporate events from PAPI components into Scalasca analysis
 +
* Extend distributed trace analysis to more parallel paradigms
 +
* '''Integrate low-overhead statistical hardware counter profiling with TAU and PerfSuite'''
 +
 
 +
==NCSA==
 +
====PHASE 1====
 +
* Update core library for current processors/OS
 +
* Incorporate Perfmon2 in hardware counter library
 +
* Develop user-oriented reference manual
 +
* Java API design and development (XML access)
 +
* '''Begin integration with PerfDMF'''
 +
* '''Install project software suite at NCSA'''
 +
* PerfSuite v1.0
 +
 
 +
====PHASE 2====
 +
* Update core library for current processors/OS
 +
* Java XML API developed and released
 +
* Java hardware counter API underway
 +
* Develop engineering guide
 +
* '''Integrate PerfDMF access with PerfSuite tools'''
 +
 
 +
====PHASE 3====
 +
* Update core library for current processors/OS
 +
* '''Integration with PerfDMF completed'''
 +
* '''Joint TAU/PerfSuite automatic analysis tools completed'''
 +
 
 +
==PSC==
 +
====PHASE 1====
 +
* Install current project perrformance toolset at PSC
 +
* Train consultants in the tools' new, advanced analysis modes
 +
* Assess performance improvement opportunities of NEMO3D, ENZO, and NAMD groups
 +
* Coordinate AG Performance Engineering seminars: Best Practices
 +
 
 +
====PHASE 2====
 +
* Support performance engineering by NEMO3D, ENZO, NAMD, Cactus groups
 +
* Apply updated tool features, tracking performance gains
 +
* Coordinate AG Performance Engineering seminars: Tools for multicore
 +
 
 +
====PHASE 3====
 +
* Inject performance engineering into additional applications
 +
* Apply updated tool features, tracking performance gains
 +
* Coordinate AG Performance Engineering seminars: Advanced Tools

Latest revision as of 20:13, 14 July 2009

Goals that emphasize interaction between institutions are marked in bold.

UO

PHASE 1

  • Add routine-level and message passing AI
  • Develop experimentation framework and user frontend
  • Develop comparative analysis modules
  • Update PerfDMF for regression analysis
  • OTF format updates for EPILOG
  • Evaluate sample-based and direct measurement integration

PHASE 2

  • Develop controller for parametric experiments
  • Develop user-interface for ACA power tool
  • Build PRA prototype, link with software test harness
  • Implement joint measurement support
  • Update PerfDMF for PerfSuite data
  • Incorporate PAPI features for multi-core

PHASE 3

  • Port AI on HPC systems and test
  • Complete AE framework and release
  • Integrate ACA with experimentation system
  • Complete ACA framework and release
  • Integrate PRA with application groups
  • Merge automatic profile analysis with KOJAK

UTK

PHASE 1

  • Define common multi-core events
  • Port Scalasca distributed trace file analysis to cluster environment
  • Develop additional Scalasca patterns for hardware counter profile data
  • Automate use of TAU call-path profiles for selective EPILOG tracing

PHASE 2

  • Implement additional PAPI network components
  • Test distributed trace file analysis on production applications
  • Migrate contextual hardware counter information to PAPI standard
  • Incorporate PerfSuite and TAU profiles into Scalasca analysis

PHASE 3

  • Continue to develop and deploy component PAPI
  • Incorporate events from PAPI components into Scalasca analysis
  • Extend distributed trace analysis to more parallel paradigms
  • Integrate low-overhead statistical hardware counter profiling with TAU and PerfSuite

NCSA

PHASE 1

  • Update core library for current processors/OS
  • Incorporate Perfmon2 in hardware counter library
  • Develop user-oriented reference manual
  • Java API design and development (XML access)
  • Begin integration with PerfDMF
  • Install project software suite at NCSA
  • PerfSuite v1.0

PHASE 2

  • Update core library for current processors/OS
  • Java XML API developed and released
  • Java hardware counter API underway
  • Develop engineering guide
  • Integrate PerfDMF access with PerfSuite tools

PHASE 3

  • Update core library for current processors/OS
  • Integration with PerfDMF completed
  • Joint TAU/PerfSuite automatic analysis tools completed

PSC

PHASE 1

  • Install current project perrformance toolset at PSC
  • Train consultants in the tools' new, advanced analysis modes
  • Assess performance improvement opportunities of NEMO3D, ENZO, and NAMD groups
  • Coordinate AG Performance Engineering seminars: Best Practices

PHASE 2

  • Support performance engineering by NEMO3D, ENZO, NAMD, Cactus groups
  • Apply updated tool features, tracking performance gains
  • Coordinate AG Performance Engineering seminars: Tools for multicore

PHASE 3

  • Inject performance engineering into additional applications
  • Apply updated tool features, tracking performance gains
  • Coordinate AG Performance Engineering seminars: Advanced Tools
Retrieved from "http://www.nic.uoregon.edu/mediawiki-point/index.php?title=Milestones&oldid=194"