E. Smirni and E. Rosti. Modeling Speedup of SPMD Applications on the Intel Paragon: a Case Study. In HPCN'95 | High Performance Computing and Networking, LNCS 919, pp. 94-101, Milan, Italy, May 1995. Springer-Verlag. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Algorithm + Strategy = Parallelism - Trinder, Hammond, Loidl, Jones (1993) (1 citation) (Correct)
....and understanding and explicitly controlling it is hard. A major motivation for investigating our predominantly implicit approach is to address irregular parallelism. Two recent parallel programming models, Bulk Synchronous Processing (BSP) McColl, 1996) and Single Program Multiple Data (SPMD) (Smirni et al. 1995), have gone some way towards addressing this problem by providing a framework in which some irregularity can be supported in an otherwise regular program. In large applications, evaluation strategies are defined in three kinds of modules. Strategies over Prelude types such as lists, tuples and ....
Smirni, E., Merlo, A., Tessera, D., Haring, G., and Kotsis, G., "Modeling speedup of SPMD applications on the Intel Paragon: a case study", In B. Hertzberger, and G. Serazzi, editors, Proc. High Performance Computing and Networking (HPCN '95), Milan, Italy, May (1995), Springer-Verlag LNCS 919, pp. 94--101.
A Methodology for the Evaluation of Multiprocessor Non-Preemptive.. - Rosti (1998) Self-citation (Smirni Rosti) (Correct)
....of and 1 have been selected to characterize the execution rates and speedup curves (see Figure 2) of the workloads used in the following sections. They best represent the execution rates experimentally derived on an Intel Paragon for a matrix transposition kernel executed on 16 processors [SR95]. 0 2 4 6 8 10 12 14 16 0 2 4 6 8 10 12 14 16 Number of Processors SPEEDUP WK 1 WK 2 WK 3 WK 4 Figure 2: Speedup curves of the four representative workloads for a 16 processor system. Table 1 summarizes the workload functional forms and parameters (i.e. the maximum parallelism M , the average ....
Smirni E., Rosti E., "Modeling speedup of SPMD applications on the Intel Paragon: a case study," Proc. of High-Performance Computing and Networking 95 Europe, B. Hertzberger, G. Serazzi Eds., Lecture Notes in Computer Science 919, pp 94-101, Italy, May 1995.
Performance Evaluation of Parallel Systems - Cremonesi, Rosti, Serazzi, Smirni (1999) Self-citation (Smirni Rosti) (Correct)
....on the Paragon is deterministic [4] meaning that the route established by the header flit is fixed and independent of the network load. Since message routing does not adapt to changes in the network load [1] contention can degrade communication latency in networks with deterministic routing. In [29] the impact of interconnection network traffic on the scalability of Single Program Multiple Data (SPMD) applications is investigated using a queueing network model and results are then validated experimentally on a 512 node Paragon. Factors that affect performance and variance in workload ....
E. Smirni and E. Rosti. Modeling speedup of SPMD applications on the Intel Paragon: a case study. In Proceedings of the High-Performance Computing and Networking 95 Int'l Conference, volume 919 of Lecture Notes in Computer Science, pages 94--101, Milan, Italy, May 1995. Springer Verlag.
Engineering Parallel Symbolic Programs in GpH - Loidl, Trinder, Hammond.. (1999) (5 citations) (Correct)
No context found.
E. Smirni and E. Rosti. Modeling Speedup of SPMD Applications on the Intel Paragon: a Case Study. In HPCN'95 | High Performance Computing and Networking, LNCS 919, pp. 94-101, Milan, Italy, May 1995. Springer-Verlag.
Strategic SPMD - Hammond (1998) (1 citation) (Correct)
No context found.
Smirni, E., Merlo, A., Tessera, D., Haring, G., and Kotsis, G., "Modeling Speedup of SPMD Applications on the Intel Paragon: a Case Study", Proc. HPCN~'95 --- High Performance Computing and Networks, Milan, Italy, 1995.
GpH: An Architecture-independent Functional Language - Trinder, Barry, Jr.. (1998) (2 citations) (Correct)
No context found.
E. Smirni, A. Merlo, D. Tessera, G. Haring, and G. Kotsis, "Modeling Speedup of SPMD Applications on the Intel Paragon: a Case Study", Proc. HPCN '95 --- High Performance Computing and Networks, Milan, Italy, 1995, pp. 94--101.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC