Abstract | ||
---|---|---|
In the solution of large-scale numerical problems, pamllel computing is becoming simultaneously more important and more difictilt. The complex organization of today's multi- processors with several memory hierarchies has forced the sci- entiific progmmmer to make a choice between simple but unscal- able code and scalable but extremely complex code that does not port to other architectures. This paper describes how the SMARTS runtime system and the POOMA C++ class library for high-performance scientijk computing work together to exploit data parallelism in scientific applications while hiding the details of managing parallelism and data locality from the user. We present innovative algo- n'thms, based on the macro-dataflow model, for detecting data pamllelism and eficiently executing data-parallel statements on shared-memory multiprocessors. We also describe how these al- |
Year | DOI | Venue |
---|---|---|
1999 | 10.1145/305138.305207 | International Conference on Supercomputing 2006 |
Keywords | Field | DocType |
temporal locality,vertical execution,programming models,barrier synchronization,data locality,cache reuse,data-parallel languages,dependence-driven execution,run-time systems,macro-dataflow,object-oriented,data-parallelism,object-parallelism,scientific computation,loop scheduling,data parallelism,parallel programming model,object oriented,scientific computing | Instruction-level parallelism,Locality of reference,Programming paradigm,Computer science,Task parallelism,Parallel computing,Data parallelism,Loop scheduling,Runtime system,Scalability | Conference |
ISBN | Citations | PageRank |
1-58113-164-X | 15 | 2.37 |
References | Authors | |
21 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Suvas Vajracharya | 1 | 34 | 10.76 |
Steve Karmesin | 2 | 111 | 17.80 |
Peter Beckman | 3 | 218 | 35.20 |
James Crotinger | 4 | 52 | 8.38 |
Allen Malony | 5 | 94 | 8.29 |
Sameer Shende | 6 | 1351 | 116.40 |
Rod Oldehoeft | 7 | 15 | 3.05 |
Stephen Smith | 8 | 15 | 2.37 |