This Article 
 Bibliographic References 
 Add to: 
Performance Considerations of Shared Virtual Memory Machines
November 1995 (vol. 6 no. 11)
pp. 1185-1194

Abstract—Generalized speedup is defined as parallel speed over sequential speed. In this paper the generalized speedup and its relation with other existing performance metrics, such as traditional speedup, efficiency, scalability, etc., are carefully studied. In terms of the introduced asymptotic speed, we show that the difference between the generalized speedup and the traditional speedup lies in the definition of the efficiency of uniprocessor processing, which is a very important issue in shared virtual memory machines. A scientific application has been implemented on a KSR-1 parallel computer. Experimental and theoretical results show that the generalized speedup is distinct from the traditional speedup and provides a more reasonable measurement. In the study of different speedups, an interesting relation between fixed-time and memory-bounded speedup is revealed. Various causes of superlinear speedup are also presented.

[1] X.-H. Sun and J. Gustafson,“Toward a better parallel performance metric,” Parallel Computing, vol. 17, pp. 1,093-1,109, Dec. 1991.
[2] K. Hwang, Advanced Computer Architecture: Parallelism, Scalability, Programmability. McGraw-Hill, 1993.
[3] J. Ortega and R. Voigt,“Solution of partial differential equations on vector and parallel computers,” SIAM Rev., pp. 149-240, June 1985.
[4] G. Amdahl,“Validity of the single-processor approach to achieving largescale computing capabilities,” Proc. AFIPS Conf., pp. 483-485, 1967.
[5] J. L. Gustafson,“Reevaluating Amdahl's law,”Commun. ACM, vol. 31, no. 5, pp. 532–533, 1988.
[6] X.-H. Sun and L. Ni,“Scalable problems and memory-bounded speedup,” J. Parallel and Distributed Computing, vol. 19, pp. 27-37, Sept. 1993.
[7] D. Helmbold and C. McDowell,“Modeling speedup(n) greater than n,” IEEE Trans. Parallel and Distributed Systems, pp. 250-256, Apr. 1990.
[8] D. Parkinson, "Parallel Efficiency can be Greater than Unity," Parallel Computing, vol. 3, pp. 261-262, 1986.
[9] D. Nicol,“Inflated speedups in parallel simulations via malloc(),” Int’l J. Simulation, vol. 2, pp. 413-426, Dec. 1992.
[10] X.-H. Sun and J. Zhu,“Performance prediction of scalable computing: A case study,” Proc. 28th Hawaii Int’l Conf. of Systems Sciences, pp. 456-465, Jan. 1995.
[11] J. Gustafson,D. Rover,S. Elbert,, and M. Carter,“The design of a scalable, fixed-time computer benchmark,” J. Parallel and Distributed Computing, vol. 12, no. 4, pp. 388-401, 1991.
[12] X.-H. Sun and D. Rover, “Scalability of Parallel Algorithm-Machine Combinations,” IEEE Trans. Parallel and Distributed Systems, vol. 5, no. 6, pp. 599-613, June 1994.
[13] A. Grama, A. Gupta, and V. Kumar, “Isoefficiency Function: A Scalability Metric for Parallel Algorithms and Architectures,” IEEE Trans. Parallel and Distributed Technology, vol. 1, no. 3, pp. 12-21, 1993.
[14] Kendall Square Research, “KSR parallel programming,”Waltham, Mass., 1991.
[15] C.E. Leiserson, "Fat-Trees: Universal Networks for Hardware Efficient Supercomputing," IEEE Trans. Computers, vol. C-34, no. 10, Oct. 1985, pp. 892-901.
[16] Kendall Square Research, “KSR technical summary,”Waltham, Mass., 1991.
[17] A.N. Tikhnov and V. Arsenin,Solution of Ill-Posed Problems. John Wiley and Sons, 1977.
[18] Y.M. Chen,J.P. Zhu,W.H. Chen,, and M.L. Wasserman,“GPST inversion algorithms for history matching in 3D 2-phase simulators,” IMACS Trans. Scientific Computing I, pp. 369-374, 1989.
[19] J. Dongarra,I.S. Duff,C.D. Sorensen,, and H.A. van der Vorst,Solving Linear Systems on Vector and Shared Memory Computers.Philadelphia: SIAM, 1991.
[20] A. Pothen and P. Raghavan,“Distributed orthogonal factorization: Givens and Householder algorithms,” SIAM J. Science and Statistical Computing, vol. 10, pp. 1,113-1,135, 1989.
[21] J. Gustafson,G. Montry,, and R. Benner,“Development of parallel methods for a 1,024-processor hypercube,” SIAM J. Science and Statistical Computing, vol. 9, pp. 609-638, July 1988.

Index Terms:
High performance computing, parallel processing, performance evaluation, performance metrics, scalability, speedup, shared virtual memory.
Xian-He Sun, Jianping Zhu, "Performance Considerations of Shared Virtual Memory Machines," IEEE Transactions on Parallel and Distributed Systems, vol. 6, no. 11, pp. 1185-1194, Nov. 1995, doi:10.1109/71.476190
Usage of this product signifies your acceptance of the Terms of Use.