NAS Parallel Benchmarks
The NAS Parallel Benchmarks (NPB) are a set of benchmarks targetting performance evaluation of highly parallel supercomputers. They are developed and maintained by the NASA Advanced Supercomputing Division (formerly the NASA Numerical Aerodynamic Simulation Program) based at the NASA Ames Research Center.
Development
Motivation
Traditional benckmarks that existed before the NPB, such as the Livermore loops, the LINPACK Benchmark and the NAS Kernel Benchmark Program, were usually specialized for vector computers. They generallly suffered from inadequacies including parallelism-impeding tuning restrictions and insufficient problem sizes, which rendered them inappropriate for highly parallel systems. Equally unsuitable were full-scale application benchmarks due to high porting cost and unavailability of automatic software parallelization tools.[1] As a result, the NPB were created in the early 1990s to address the ensuing lack of benchmarks applicable to highly parallel machines.
Guidelines
The specification of the NPB recognizes the following development guidelines:
- Use of new parallel-aware algorithmic and software methods
- Genericness and architecture neutrality
- Easy verifiability of correctness of results and performance figures
- Capability of accomodating new systems with increased power
- Ready distributability
In the light of these guidelines, it was deemed the only viable approach to use a set of "paper and pencil" benchmarks, i.e., specify a set of problems only algorithmically and leave most implementation details to the implementor's discretion under certain less restrictive limits.[1]
References
- ^ a b D. Bailey, E. Barscz, J. Barton, D. Browning, R. Carter, L. Dagum, R. Fatoohi, S. Fineberg, P. Frederickson, T. Lasinski, R. Schreiber, H. Simon, V. Venkatakrishnan, S. Weeratunga, The NAS Parallel Benchmarks, NAS Technical Report RNR-94-007, NASA Ames Research Center, Moffett Field, CA, 1994.
External links
 | This software article is a stub. You can help Wikipedia by expanding it. |