Application benchmark codes that were used as part of several NERSC procurements are provided below along with a brief discussion of the NERSC Sustained System Performance (SSP) metric.
The intent of these benchmarks is to measure the execution performance and compiler capabilities of existing and future supercomputer systems and to provide an ongoing glimpse of a portion of the NERSC scientific computing workload. Each of the benchmark programs represents a particular subset and/or characteristic of the NERSC workload, which generally consists of solving complex scientific problems using a variety of state-of-the-art computational techniques. There is keen interest on the part of the NERSC Advanced Technologies group to have vendor and university researchers use these codes to help guide future system designs.
The NERSC SSP
Each benchmark has its own web page that includes an HTML README file and a link containing information on how to obtain the codes. Because of licensing issues not all of the codes are available directly from NERSC. The README files describe the code, how to build and run it, any timing or storage issues, some RFP rules, optimization restrictions, required run configurations, expected results, and the release and modification record.
- Benchmarks used in the NCSa Procurement
- - last updated September 25, 2006
- Benchmarks used in the NCSb Procurement
- - last updated May 30, 2006
- Benchmarks used in the NERSC-5 Procurement
- - last updated September 30, 2006
- Benchmarks used in the NERSC-6 Procurement
- - last updated September 10, 2008
- AMR Chombo benchmark
- - last updated October 17, 2007