Session: High Performance Computing System Performance Modeling
  Title: High Performance Computing System Performance Modeling
  Chair: Larry Davis (DoD High Performance Computing Modernization Program)
  Time: Thursday, November 20, 3:30PM - 5:00PM
  Rm #: 42-43
  Speaker(s)/Author(s):  
  Chair: Larry Davis (DoD High Performance Computing Modernization Program); Panelists: Allan Snavely (SDSC), Jack Dongarra (University of Tennessee), Walt Brooks (NASA Ames), Adolfy Hoisie (DOE), Henry Newman (Instrumental), John McCalpin (IBM)
   
  Description:
  This panel consists of government and government-sponsored researchers in the area of high performance computing system performance modeling. Benchmarks are structured to address a range of target configurations. They provide the High Performance Computing Modernization Program (HPCMP) with accurate performance information on available high performance computing (HPC) capabilities. The intent is to provide a set of program source code listings, makefiles, runtime scripts, input files, and validated results files which represents the type of computational work performed on HPC resources. Questions addressed by the panelists include:

1. Describe how and why benchmarks are used in your organization.
2. Describe a minimal spanning set of HPC system attributes that can accurately model the performance of HPC systems on a broad class of applications.
3. What is the potential for the use of synthetic benchmarks to accurately model the performance of a broad class of applications, both now and in the future?
4. For procurement related decisions, do you allow vendors to optimize the benchmarks for their particular architecture? Why or why not?
  Link: --