2006 SPEC Benchmark Workshop

January 23, 2006

The SPEC benchmark workshop was held on January 23, 2006, in conjunction with the Annual Meeting of the Standard Performance Evaluation Corporation (SPEC). The workshop took place at the Joe C. Thompson Conference Center at the University of Texas, Austin and brought together benchmark developers and users in industry and academia. The program featured a series of talks on:

• available benchmark suites,
• the use of benchmarks in industry, academia, and government organizations and,
• benchmarking methodologies.

The papers and slides provided by our presenters have been made available below. Unless otherwise indicated, papers are in PDF format and slides are in Powerpoint format.

Schedule

8:15 – 8:30 Opening Remarks

8:30 – 9:15 Keynote: Jim Smith, University of Wisconsin - Benchmarking: Science? Art? Neither?
                 [Slides]

9:15 – 10:05   Session 1:

• BioPerf: An Open Benchmark Suite for Evaluating Computer Architecture on Bioinformatics and Life Science Applications
  • David Bader, Georgia Institute of Technology
    [Slides]
• Workload Characterization of SPECweb2005
  • Rema Hariharan and Ning Sun, Sun Microsystems
    [Slides]

10:05 – 10:30     Break

10:30 – 12:10     Session 2:

• HPC Benchmarking and Performance Evaluation With Realistic Applications
  • Brian Armstrong, Hansang Baeh, Rudolf Eigenmann, Faisal Saied, Mohamed Sayeed, Yili Zheng, Purdue University
    [Slides]
• SPEC HPG Benchmarks for HPC Systems
  • Kumaran Kalyanasundaram, SGI, Matthijs van Waveren, Fujitsu Systems Europe, Hideki Saito, Intel
    [Slides]
• Benchmarking using the Community Atmospheric Model
  • Patrick H. Worley, Oak Ridge National Laboratory
    [Slides]
• J2EE Performance and Scalability - From Measuring to Predicting
  • Samuel Kounev, Darmstadt University
    [Slides]

12:10 - 1:45     Lunch (on your own)

1:45 - 3:00    Session 3:

• Fun Size Your Data: Using Statistical Techniques to Efficiently Compress and Exploit Benchmarking Results
  • David J. Lilja, University of Minnesota
    [Slides]
• Overview of the HPCC Challenge Benchmark Suite
  • Jack Dongarra and Piotr Luszczek, Oak Ridge National Labs
    [Slides]
• Evaluating Whether the Training Data Provided for Profile Feedback is a Realistic Control Flow for the Real Workload
  • Darryl Gove and Lawrence Spracklen, Sun Microsystems
    [Slides]

3:00 - 3:20     Break

3:20 – 5:00     Session 4:

• Analyzing the Processor Bottlenecks in SPEC CPU2000
  • Joshua J. Yi, Freescale Semiconductor Inc., Resit Sendag, University of Rhode Island, Ajay Joshi, The University of Texas at Austin and David J. Lilja, University of Minnesota
    [Slides (PDF)]
• Multimedia Workloads versus SPEC CPU2000
  • Christopher Martinez, Mythri Pinnamaneni and Eugene B. John, The University of Texas at San Antonio
    [Slides]
• Performance Prediction using Program Similarity
  • Aashish Phansalkar and Lizy K. John, The University of Texas at Austin
    [Slides]
• The Memory Behavior of Data Structures in C - SPEC CPU2000 Benchmarks
  • Kartik K. Agaram, Stephen W. Keckler, Calvin Lin, Kathryn S. McKinley, The University of Texas at Austin
    [Slides]

5:00 End of Technical Program

Social Program

5:30 – 8:00     Social and Award