HPC Challenge
HPC Challenge is a collection of benchmarks for measuring various aspects of system performance, such as flop/s, sustainable memory bandwidth, memory read/write rates, network bandwidth, and latency for parallel machines. It is designed for supercomputers, but will run on any computer with MPI-1 (Message Passing Interface) implementation and BLAS (Basic Linear Algebra Subprograms).
| Tags | Scientific/Engineering Benchmark |
|---|---|
| Licenses | BSD Original |
| Operating Systems | BeOS Mac OS X Windows Windows Windows Windows POSIX Unix |
| Implementation | C |
Recent releases
- 27 Jun 2007 08:52
Changes: This version contains many bugfixes, major features, and minor enhancements, many of which were contributed by users. The major focus of this release was to improve accuracy of the reported performance results and ensure scalability of the code on the largest supercomputer installations with hundreds of thousands of computational cores.
- 19 Jun 2005 19:23
Changes: The following features were added: simplified and/or automatic configuration, OpenMP support added to FFT and RandomAccess, time-bound in MPI-RandomAccess, parallel verification in MPI-RandomAccess, and enhanced and improved reporting of results.
- 10 Nov 2004 17:39
No changes have been submitted for this release.
