Abstract:
Experimental data validating some of the proposed parallel computation models on the Intel Paragon is presented. This architecture is characterized by a large bandwidth and a relatively large startup cost of a message transmission, which makes it extremely important to employ bulk transfers. The models considered are the BSP model, in which it is assumed that all messages have a fixed short size, and the BPRAM, in which block transfers are rewarded. 1.
Citations
|
970
|
A bridging model for parallel computation
– Valiant
- 1997
|
|
434
|
LogP: Towards a Realistic Model of Parallel Computation
– Culler, al
- 1993
|
|
83
|
BSPlib: The BSP programming library
– Hill, McColl, et al.
- 1997
|
|
61
|
On communication latency in PRAM computations
– Agarwal, Chandra, et al.
- 1989
|
|
57
|
auf der Heide. Truly efficient parallel algorithms: c-optimal multisearch for an extension of the BSP model
– Baumker, Dittrich, et al.
- 1995
|
|
50
|
A quantitative comparison of parallel computation models
– Juurlink, Wijshoff
- 1996
|
|
42
|
The input/output complexity of transitive closure
– Ullman, Yannakakis
- 1991
|
|
39
|
SUNMOS for the Intel Paragon: A brief user’s guide
– Maccabe, McCurley, et al.
- 1994
|
|
38
|
Towards efficiency and portability: Programming with the BSP model
– Goudreau, Lang, et al.
- 1996
|
|
33
|
Fast parallel sorting under LogP: From theory to practice
– Culler, Dusseau, et al.
- 1993
|
|
28
|
Evaluation of the Intel Paragon on Active Message Communication
– Liu, Culler
- 1995
|
|
20
|
The NX message passing interface
– Pierce
- 1994
|
|
15
|
Practical Parallel List Ranking
– Sibeyn, Guillaume, et al.
- 1999
|
|
12
|
The E-BSP model: Incorporating unbalanced communication and general locality into the BSP model
– Juurlink, Wijshoff
- 1996
|
|
7
|
Experimental validation of models of parallel computation
– Snyder
- 1995
|
|
3
|
Technology advances in the Intel Paragon system
– Brandenburg
- 1993
|