Document Actions

Performance Tools for Extreme Scale Computing

by John Mellor-Crummey last modified 2011-08-06 17:24

August 1-4, 2011, Granlibakken Resort and Conference Center, Tahoe City, CA, USA



Petascale computer systems are now available to the DOE science community; multipetaflop systems for open science are scheduled to be installed at Argonne National Laboratory and Oak Ridge National Laboratory. Compared to systems of the past, these machines represent a dramatic increase in scale and complexity. Making effective use of systems at this scale will require performance tools that help application developers by pinpointing and explaining application performance bottlenecks. Two performance challenges for applications are to make effective use of processor nodes, and to keep parallelization overhead low enough so that extreme-scale parallelism is practical.

Providing tools that make it possible to address these problems is requiring increasingly sophisticated methods for instrumentation, measurement, analysis and modeling of application performance. Meeting these challenges will require tools with unprecedented capabilities.

Today, research and development in the area of performance tools for parallel systems is fragmented. Individual groups have developed tools and components with unique capabilities. Working together to capitalize these capabilities into shared community infrastructure would reduce duplication of effort, accelerate development of effective tools with increasing sophistication, and simplify the process of developing tools for new systems as they emerge.

The goal of this workshop is to bring together tools researchers to discuss challenges of performance analysis and debugging on emerging petascale systems, review ongoing research, and work together to tackle the challenges of performance analysis on petascale systems together as a community. Attendees at the workshop will be tools developers in the areas of tools infrastructure, debugging, performance instrumentation, measurement, analysis, and visualization. We expect that about a third of the workshop will consist of opportunities to work together in smaller groups to make progress on tackling problems of mutual interest.

Specific aims of the workshop include

  • Identifying performance tool capabilities needed to analyze the spectrum of issues that arise with emerging extreme scale systems.
  • Discussing emerging capabilities of research and commercial tools in this space.
  • Identifying common needs, functionality, and opportunities for sharing infrastructure.
  • Discussing design aspects of sharable components.
  • Developing standardized interfaces to facilitate sharing.

Tentative Agenda

Sunday, July 31, 2011
Social hour at 6:30pm; Dinner served at 7:00pm, Cedar House, main building
Monday, August 1, 2011
7:30 AM Breakfast buffet, main building
Workshop technical sessions will be held in Mountain Conference Room, main building
9:00 AM The Deconstruction of Dyninst: Lessons Learned and Best Practices, Bill Williams, Madhavi Krishnan, Drew Bernat, Barton Miller (University of Wisconsin) Slides
9:45 AM An Update on the Cray Tools Activities for Extreme Scale Computing, Luiz DeRose and Heidi Poxon (Cray Inc.) Slides
10:15 AM Describing Performance and Resource Needs of DOE Office of Science Workloads, David Skinner (LBNL) Slides
10:45 AM Morning Break
11:15 AM Menage a Trois: Performance Visualization, Integrated Profiling, and Kernel Measurement, Allen Malony (University of Oregon) Slides
11:45 AM An Overview and Status of Component Based Tool Framework and First User Experiences Building Tools using the CBTF Infrastructure , Jim Galarowicz (Krell Labs), David Montoya (LANL) Slides
12:15 PM Lunch buffet
1:45 PM HPCToolkit: New Capabilities, Ongoing Work, and Challenges Ahead, John Mellor-Crummey, Nathan Tallent, Xu Liu (Rice University) Slides
2:30 PM Are there Components in Auto-tuning?, Jeffrey Hollingsworth (University of Maryland) Slides
3:00 PM PAVE: More Intuitive Performance Analysis, Martin Schulz (LLNL) Slides
3:30 PM Afternoon Break
4:00 PM Improving the Scalability of the TotalView Debugger using TBON-FS and proc++, Michael Brim (University of Wisconsin) Abstract Slides
4:30 PM LIBI Status Update and Future Directions, Dorian Arnold (University of New Mexico) Slides
5:00 PM Efforts on Programming Environment and Tools in China's High-tech R&D Program, Depei Qian (Beihang University) Slides
5:30 PM Extrapolation of and Code Generation from Communication Traces Program, Frank Mueller (North Carolina State University) Slides
7:00 PM Social hour @ 7pm, Dinner @ 7:30pm
Tuesday, August 2, 2011
7:30 AM Breakfast buffet provided
9:00 AM Demand-Driven Software Race Detection using Hardware Performance Counters, Ramesh Peri (Intel) Abstract Slides
9:30 AM Cycle Accounting and the GOODA Analyzer, David Levinthal (Google) Slides
10:00 AM Adaptive Threading Using Counter-based Performance Introspection , Robert Fowler (RENCI) Slides
10:30 AM Morning Break
11:00 AM Recent Performance Analysis with Memphis, Collin McCurdy (ORNL) Slides
11:30 AM Porting PAPI to the Cloud (and Other Places), Dan Terpstra (University of Tennessee) Slides
12:00 AM perf_event Progress Report, Stephane Eranian (Google) Slides
12:30 PM Lunch buffet provided
2:00 PM Recent Scalasca Research , Felix Wolf (University of Aachen) Slides
2:30 PM Performance Diagnosis for Hybrid GPU/CPU Applications, Karen Karavanic (Portland State) Slides
3:00 PM HPC Programming Environment for Accelerator-based Development , Richard Graham (ORNL) Slides
3:30 PM Afternoon Break
4:00 PM An Overview of the Blackcomb Simulator, Gabriel Marin (ORNL) Slides
4:30 PM Towards Rapid Development of Component Tools at LLNL , Todd Gamblin (LLNL) Slides
5:00 PM Scalasca Tool Integrations, Bernd Mohr (Juelich Supercomputer Center) Slides
5:30 PM The Other HPC -- Profiling Enterprise Applications , Marty Itzkowitz (Oracle) Abstract, Slides
7:00 PM Dinner - Social hour at 7:00pm, dinner served at 7:30pm
Wednesday, August 3, 2011
7:30 AM Breakfast buffet provided
9:00 AM Working Groups - Planning and Initial Meetings
10:30 AM Morning Break
11:00 AM Working Groups Meet
12:30 PM Lunch buffet provided
2:00 PM Small Working Group Activities
7:00 PM Dinner - Social hour at 7:00pm, dinner served at 7:30pm
Thursday, August 4, 2011
7:30 AM Breakfast buffet provided
9:00 AM Working Groups meet
10:30 AM Morning Break
11:00 AM Working Groups meet
12:30 PM Lunch buffet provided
2:00 PM Working Groups meet
3:30 PM Afternoon Break
4:00 PM Working Group Presentations
Hardware Performance Monitoring Unit Working Group Outbrief
GPU Performance Working Group Outbrief
Wrappers Working Group Outbrief
Build Systems Working Group Outbrief
7:00 PM Dinner - Social hour at 7:00pm, dinner served at 7:30pm
Friday, August 5, 2011
7:30 AM Breakfast buffet provided
Box lunch provided upon request


This workshop is sponsored by the Center for Scalable Application Development Software, with funding from the Scientific Discovery through Advanced Computing (SciDAC) program.

« April 2018 »
Su Mo Tu We Th Fr Sa

Powered by Plone

CScADS Collaborators include:

Rice University ANL UCB UTK WISC