Abstract | ||
---|---|---|
We reconsider the familiar problem of executing a perfectly parallel workload consisting of N independent tasks on a parallel computer with P << N processors. We show that there are memory-bound problems for which the runtime can be reduced by the forced parallelization of individual tasks across a small number of cores. Specific examples include solving differential equations, performing sparse matrix-vector multiplications, and sorting integer keys. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1007/978-3-642-55224-3_8 | PARALLEL PROCESSING AND APPLIED MATHEMATICS (PPAM 2013), PT I |
Keywords | DocType | Volume |
Perfectly parallel problem, Resource contention, Forced parallelization | Conference | 8384 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
1 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lars Karlsson | 1 | 51 | 5.16 |
Carl Christian Kjelgaard Mikkelsen | 2 | 11 | 3.57 |
Bo Kågström | 3 | 1045 | 189.17 |