C. H. Papadimitriu and M. Yannakakis. Towards an Architecture Independent Analysis pf Parallel Algorithms. In Proceedings of the 20th Annual Symposium on Theory of Computing, pages 510--513, 1988. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Communication Performance of Wormhole Interconnection Networks - Petrini (1997) (Correct)
....the unit memory cost idealization. The BPRAM [4] augmented this by charging l units for the first message from global memory and a variable cost, b, for each memory access in a contiguous block, thus modeling a fixed overhead plus a transfer rate typical of block communication. The Delay Model [115] considers the communication latency, realizing that there is a delay between the time some information is produced at a processor and the time it can by used by another processor. Another example of a PRAM variant which assumes two classes of memory and includes a mechanism for assigning a ....
C. H. Papadimitriu and M. Yannakakis. Towards an Architecture Independent Analysis pf Parallel Algorithms. In Proceedings of the 20th Annual Symposium on Theory of Computing, pages 510--513, 1988.
Latency and Bandwidth Requirements of Massively Parallel.. - Petrini (1999) (Correct)
....is simple and useful for a gross classi cation of algorithms, but it does not reveal important performance bottlenecks in the interconnection network. As a consequence, a variety of alternative models have been developed, each capturing di erent aspects of real parallel machines. The Delay Model [30] considers the communication latency, realizing that there is a delay between the time some information is produced at a processor and the time it can by used by another processor. Another model that addresses communication latency is the BPRAM [1] in which block transfers are allowed. A model ....
C. H. Papadimitriu and M. Yannakakis. Towards an Architecture Independent Analysis pf Parallel Algorithms. In Proceedings of the 20th Annual Symposium on Theory of Computing, pages 510-513, 1988.
Latency and Bandwidth Requirements of Massively Parallel.. - Petrini, Vanneschi (1999) (Correct)
....simple and useful for a gross classification of algorithms, but it does not reveal important performance bottlenecks in the interconnection network. As a consequence, a variety of alternative models have been developed, each capturing different aspects of real parallel machines. The Delay Model [PY88] considers the communication latency, realizing that there is a delay between the time some information is produced at a processor and the time it can by used by another processor. Another model that addresses communication latency is the BPRAM [ACS89] in which block transfers are allowed. A ....
C. H. Papadimitriu and M. Yannakakis. Towards an Architecture Independent Analysis pf Parallel Algorithms. In Proceedings of the 20th Annual Symposium on Theory of Computing, pages 510--513, 1988.
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