Abstract
The NHT-1 I/O (Input/Output) benchmarks are a benchmark suite developed at the Numerical Aerodynamic Simulation Facility (NAS) located at NASA Ames Research Center. These benchmarks are designed to test various aspects of the I/O performance of parallel supercomputers. One of these benchmarks, the Application I/O Benchmark, is designed to test the I/O performance of a system while executing a typical computational fluid dynamics application. In this paper the implementation of this benchmark on three parallel systems located at NAS and the results obtained from these implementations are reported. The machines used were an 8 processor Cray Y-MP, a 32768 processor CM-2, and a 128 processor iPSC/860. The results show that the Y-MP is the fastest machine and has relatively well balanced I/O performance. I/O adds 2--40% overhead, depending on the number of processors utilized. The CM-2 is the slowest machine, but it has I/O that is fast relative to its computational performance. This resulted in typical I/O overheads on the CM-2 of less than 4%. Finally, the iPSC/860, while not as computationally fast as the Y-MP, is considerably faster than the CM-2. However, the iPSCI860's I/O performance is quite poor and can add overhead of more than 70%.
- [BaB93] D. Bailey, J. Barton, T. Lasinski, and H. Simon, eds, The NAS Parallel Benchmarks, NASA Technical Memorandum 103863, NASA Ames Research Center, Moffett Field, CA, July 1993.Google Scholar
- [BaB92] D. H. Bailey, E. Barszcz, L. Dagum, and H. D. Simon, NAS Parallel Benchmark Results, NAS Technical Report RNR-92-002, NASA Ames Research Center, Moffett Field, CA, August 1992.Google ScholarCross Ref
- [CaC92] R. Carter, B. Ciotti, S. Fineberg, and B. Nitzberg, NHT-1 I/O Benchmarks, NAS Technical Report RND-92-016, NASA Ames Research Center, Moffett Field, CA, November 1992.Google Scholar
- [Cio92] B. Ciotti, "Session Reservable File Systems (SRFS)," Spring 1992 CRAY User Group Proceedings , Berlin, Germany, 1992.Google Scholar
- [Hil87] W. D. Hillis, "The connection machine," Scientific American, vol. 256, June 1987, pp. 108-115. Google ScholarDigital Library
- [Int91] Intel Supercomputing Systems Division, iPSC/2 and iPSC/860 User's Guide, Intel Corporation, Beaverton, OR, 1991.Google Scholar
- [Nit92] B. Nitzberg, Performance of the iPSC/860 Concurrent File System, NAS Technical Report RND-92-020, NASA Ames Research Center, Moffett Field, CA, December 1992.Google Scholar
- [Nug88] S. F. Nugent, "The iPSC/2 direct connect communications technology," Third Conference on Hypercube Concurrent Computers and Applications , January 1988, pp. 51-60. Google ScholarDigital Library
- [Wee92] S. Weeretunga, NAS Applied Research Department, personal communication, October 1992.Google Scholar
- [ZeL88] S.A. Zenios, R.A. Lasken, "The connection machines CM-1 and CM-2: solving nonlinear network problems," 1988 International Conference on Supercomputing, July 1988, pp. 648-658. Google ScholarDigital Library
Index Terms
- Implementing the NHT-1 application I/O benchmark
Recommendations
NAS Parallel Benchmark Results
Benchmark results for the Numerical Aerodynamic Simulation (NAS) Program at NASA Ames Research Center, which is dedicated to advancing the science of computational aerodynamics are presented. The benchmark performance results are for the Y-MP, Y-MO EL, ...
MPI Performance Evaluation and Characterization using a Compact Application Benchmark Code
MPIDC '96: Proceedings of the Second MPI Developers ConferenceIn this paper the parallel benchmark code PSTSWM is used to evaluate the performance of the vendor-supplied implementations of the MPI message-passing standard on the Intel Paragon, IBM SP2, and Cray Research T3D. This study is meant to complement the ...
Comments