D. Kuck
E. Davidson
P. Yew
ABSTRACT
In this paper, we give an overview of the Cedar multiprocessor and present recent performance results. These include the performance of some computational kernels and the Perfect Benchmarks. We also present a methodology for judging parallel system performance and apply this methodology to Cedar, Cray YMP-8, and Thinking Machines CM-5.
- Add1.CSRD Staff. Perfect Report 2: Addendum 1. Center for Supercomputing Research and Development, University of Illinois, 1991.Google Scholar
- AnGa93.J. Andrews and K. Gallivan. Analysis of a Cedar Implementation of TR.FD, CSRD Report in preparation, University of Illinois.Google Scholar
- BrBo91.l~. Bramley and j. Bordner. Sequentzal Oplzm~zation and Dala Dzstmbution for ARC2D on the Cedar Hierarchzcal Mult~processor, CSRD Report No. 1128, University of Illinois, 1991.Google Scholar
- EABM91.Emrath, P., et al. The Xylem Operating System. Procs. of ICPP'91, vol. 1, pg. 67- 70, 1991.Google Scholar
- EHJL91.Eigenmann, et al. Reslructurzng Fortran Programs for Cedar. Procs. ofICPP'91, vol. 1, pp. 57-66, 1991.Google Scholar
- EHJP92.Eigenmann, et al. The Cedar Forlran Project. CSRD Report No. 1262, University of Illinois, 1992.Google Scholar
- EHLP91.Eigenmann, et al. Experience in the automatic Parallelization of Four Perfect- Benchmark Programs. Proceedings of the Fourth Workshop on Languages and Compilers for Parallel Computing, pp. 65-83, 1991. Google ScholarDigital Library
- FWPS92.Ferng, W., et al. Bas'tc Sparse Matrix Computations on Massively Parallel Compulers. AHPCRC Preprint 92-084, University of Minnesota, July, 1992.Google Scholar
- GJTV91.K. Gallivan, et al. Preliminary Performance Analysis of the Cedar Multiprocessor Memory System. Proc. 1991 ICPP, Vol. I, pp. 71-75, 1991.Google Scholar
- GJWY93.K. Gallivan, et al. Comments on a Cedar Implemenlalion of FLO5~, CSRD Report in preparation, University of Illinois.Google Scholar
- GKLS83.Gajski, D., et al. CEDAR - a Large Scale Multiprocessor, Procs. 1983 ICPP, pp. 524- 529, 1983.Google Scholar
- GoGV90.Gornish, E., et al. Compiler-direcled Data Prefelching in Mulliprocessors wilh Memory Hierarchies. Procs. ICS'90, Amsterdam, The Netherlands, vol. 1, pp. 342-353, 1990. Google ScholarDigital Library
- Hoef91.Hoeflinger, J. Cedar Fortran Programmer's Handbook. Center for Supercornputing Research and Development, University of illinois, 1991.Google Scholar
- KDLS86.Kuck, D., et al. Parallel Supercomputing Today and the Cedar Approach, Science, vol. 231, pp. 96%974, Feb. 28, 1986.Google ScholarCross Ref
- KTVZ91.Konicek, J., et al. The Organizatzon of the Cedar System. Procs. ICPP'91, vol. 1, pg. 49-56, 1991.Google Scholar
- Lawr75.Lawrie, D., Access and Alignment of Data in an Array Processor. IEEE Trans. on Computers, vol. C-24, no. 12, pp. 1145- 1155, Dec. 1975.Google Scholar
- MaEG92.B. Marsolf, P. Emrath, and K. Gallivan. Investigation of lhe Page Fault Performance of Cedar, CSRD Report No. 1263, University of Illinois, 1992.Google Scholar
- Turn93.S. Turner. Performance Analysis of Interconnection Networks, PhD Thesis in preparation, 1993.Google Scholar
- YaGa93.U. M. Yang and K. Gallivan. Analysis of a Cedar Implemental,on Of DYFESM, CSRD Report No. 1284, University of Illinois, 1993.Google Scholar
- ZhYe87.Zhu, C-Q. and Yew, P-C., A Scheme to Enforce Data Dependence on Large Multiprocessor Systems. IEEE Transactions on Software Engineering, vol. SE-13, no. 6, pp. 726- 739, June 1987. Google ScholarDigital Library
Index Terms
- The cedar system and an initial performance study
Recommendations
The cedar system and an initial performance study
Special Issue: Proceedings of the 20th annual international symposium on Computer architecture (ISCA '93)In this paper, we give an overview of the Cedar multiprocessor and present recent performance results. These include the performance of some computational kernels and the Perfect Benchmarks. We also present a methodology for judging parallel system ...
Initial Performance Evaluation of the Cray SeaStar Interconnect
HOTI '05: Proceedings of the 13th Symposium on High Performance InterconnectsThe Cray SeaStar is a new network interface and router for the Cray Red Storm and XT3 supercomputer. The SeaStar was designed specifically to meet the performance and reliability needs of a large-scale, distributed-memory scientific computing platform. ...
Comparing the Performance of the DASH and Cedar Multiprocessors for Scientific Applications
ICPP '94: Proceedings of the 1994 International Conference on Parallel Processing - Volume 02Scalable shared-memory multiprocessors are attractive because they achieve large-scale parallel processing without surrendering much programmability. Several such machines have been built or are currently being built, for instance RP3, Cedar, KSR1, DASH,...
Comments