|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
| ASCII Text | x | ||
| R. Nelson, D. Towsley, A.N. Tantawi, "Performance Analysis of Parallel Processing Systems," IEEE Transactions on Software Engineering, vol. 14, no. 4, pp. 532-540, April, 1988. | |||
| BibTex | x | ||
| @article{ 10.1109/32.4676, author = {R. Nelson and D. Towsley and A.N. Tantawi}, title = {Performance Analysis of Parallel Processing Systems}, journal ={IEEE Transactions on Software Engineering}, volume = {14}, number = {4}, issn = {0098-5589}, year = {1988}, pages = {532-540}, doi = {http://doi.ieeecomputersociety.org/10.1109/32.4676}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - JOUR JO - IEEE Transactions on Software Engineering TI - Performance Analysis of Parallel Processing Systems IS - 4 SN - 0098-5589 SP532 EP540 EPD - 532-540 A1 - R. Nelson, A1 - D. Towsley, A1 - A.N. Tantawi, PY - 1988 KW - Bulk arrival queues KW - fork/join queues KW - job splitting KW - modeling and analysis KW - parallel processing KW - synchronization delay. VL - 14 JA - IEEE Transactions on Software Engineering ER - | |||
A bulk arrival M^x/M/c queueing system is used to model a centralized parallel processing system with job splitting. In such a system, jobs wait in a central queue, which is accessible by all the processors, and are split into independent tasks that can be executed on separate processors. The job response time consists of three components: queueing delay, service time, and synchronization delay. An expression for the mean job response time is obtained for this centralized parallel processing system. Centralized and distributed parallel processing systems (with and without job splitting) are considered and their performances compared. Furthermore, the effects of parallelism and overheads due to job splitting are investigated.
[1] F. Baccelli and A. M. Makowski, "Simple computable bounds for the fork-join queue," presented at the Johns Hopkins Conf. Inform. Sci., Johns Hopkins Univ., 1985.
[2] M. L. Chaudhry and J. G. C. Templeton, AFirst Course in BulkQueues. New York: Wiley, 1983.
[3] L. Flatto, "Two parallel queues created by arrivals with two demands II,"SIAM J. Appl. Math., vol. 45, pp. 861-878, Oct. 1985.
[4] L. Flatto and S. Hahn, "Two parallel queues created by arrivals and with two demands I,"SIAM J. Appl. Math., vol. 44, pp. 1041-1053, Oct. 1984.
[5] R. Nelson and A. N. Tantawi, "Approximate analysis of fork/join synchronization in parallel queues," IBM Res. Rep. RC11481, Oct. 1985; alsoIEEE Trans. Comput., to be published.
[6] P. P. Spies and W. J. Geilenkeuser, "Queueing systems serving task families," inPerformnnce'83, A. K. Agrawala and S. K. Tripathi, Eds., 1983, pp. 187-201.
[7] D. D. Yao, "Some results for the queuesMx/M/candGIx/G/c," Oper. Res. Lett., vol. 4, pp. 79-83, July 1985.
[8] D. D. Yao, "Refining the diffusion approximation for the M/G/m queue,"Oper. Res., vol. 33, pp. 1266-1277, Nov. 1985.