Abstract
Massively parallel processors have begun using commodity operating systems that support demand-paged virtual memory. To evaluate the utility of virtual memory, we measured the behavior of seven shared-memory parallel application programs on a simulated distributed-shared-memory machine. Our results (1) confirm the importance of gang CPU scheduling, (2) show that a page-faulting processor should spin rather than invoke a parallel context switch, (3) show that our parallel programs frequently touch most of their data, and (4) indicate that memory, not just CPUs, must be “gang scheduled.” Overall, our experiments demonstrate that demand paging has limited value on current parallel machines because of the applications' synchronization and memory reference patterns and the machines' high page-fault and parallel context-switch overheads.
Similar content being viewed by others
References
A. Agarwal, R. Simoni, M. Horowitz, and J. Hennessy. An evaluation of directory schemes for cache coherence. In Proceedings of the 15th Annual International Symposium on Computer Architecture, pp. 280–289, 1988.
T. Anderson. NOW: Distributed supercomputing on a network of workstations. Presentation at 1993 Fall ARPA HPC Software PI's meeting, September 1993.
T. Anderson, D. Culler, and D. Patterson. A case for networks of workstations: NOW.IEEE Micro, Feb. 1995.
D. Bailey, J. Barton, T. Lasinski, and H. Simon. The NAS parallel benchmarks. Technical Report RNR-91-002 Revision 2, NASA Ames Research Center, Aug. 1991.
F. J. Corbato. A paging experiment with the Multics system. Technical Report MAC-M-384, MIT, May 1968.
P. J. Denning. The working set model of program behavior.Communications of the ACM, 11: 323–333, May 1968.
J. Dongarra, G. A. Geist, R. Manchek, and V. S. Sunderam. Integrated PVM framework supports heterogeneous network computing.Computers in Physics, 7: 166–174, March-April 1993.
D. L. Eager, J. Zahorjan, and E. D. Lazowska. Speedup versus efficiency in parallel systems.IEEE Transactions on Computers, 38: 408–423, March 1989.
D. G. Feitelson and L. Rudolph. Gang scheduling performance benefits for fine-grained synchronization.Journal of Parallel and Distributed Computing, 16: 306–318, December 1992.
L. Iftode, K. Li, and K. Petersen. Memory servers for multicomputers. In Proceedings of 1993 Spring CompCon, pp. 538–547, February 1993.
S. T. Leutenegger. Issues in multiprogrammed multiprocessor scheduling. Ph.D. thesis, University of Wisconsin-Madison, August 1990.
S. T. Leutenegger and X.-H. Sun. Distributed computing feasibility in a non-dedicated homogenous distributed system. In Proceedings of ACM Supercomputing '93, 1993.
J. K. Ousterhout, D. A. Scelza, and P. S. Sindhu. Medusa: An experiment in distributed operating system structure.Communications of the ACM, 23: 92–105, February 1980.
S. K. Reinhardt, M. D. Hill, J. R. Larus, A. R. Lebeck, J. C. Lewis, and D. A. Wood. The Wisconsin Wind Tunnel: Virtual prototyping of parallel computers. In Proceedings of the 1993 ACM Sigmetrics Conference on Measurement and Modeling of Computer Systems, pp. 48–60, May 1993.
E. Sharakan. Personal communication, April 1994.
J. P. Singh, W.-D. Weber, and A. Gupta. SPLASH: Stanford parallel applications for shared memory.Computer Architecture News, 20: 5–44, March 1992.
F. Traenkle. Parallel programming models and boundary integral equation methods for microstructure electrostatics. Master's thesis, University of Wisconsin-Madison, 1993.
D. Thiebaut and H. Stone. Footprints in the cache.ACM Transactions on Computer Systems, 5: 305–329, November 1987.
S. Zhou, J. Wang, X. Zheng, and P. Delisle. Utopia: A load sharing system for large, heterogeneous distributed computer systems. CSRI Technical Report 257, Computer Systems Research Institute, University of Toronto, April 1992.
Author information
Authors and Affiliations
Additional information
This work is supported in part by NSF Presidential Young Investigator Award CCR-9157366; NSF Grants MIP-9225097, CCR-9100968, and CDA-9024618; Office of Naval Research Grant N00014-89-J-1222; Department of Energy Grant DE-FG02-93ER25176; and donations from Thinking Machines Corporation, Xerox Corporation, and Digital Equipment Corporation.
Rights and permissions
About this article
Cite this article
Burger, D.C., Hyder, R.S., Miller, B.P. et al. Paging tradeoffs in distributed-shared-memory multiprocessors. J Supercomput 10, 87–104 (1996). https://doi.org/10.1007/BF00128100
Issue Date:
DOI: https://doi.org/10.1007/BF00128100