Name
Abstract | ||
|---|---|---|
In this paper we analyze the Communication and Cache Conscious Radix sort algorithm, C3-Radix, using the distributed and the shared memory parallel programming models.C3-Radix was originally proposed based on the idea of the classic Radix sort to exploit the memory hierarchy locality and reduce the amount of communication for distributed memory computers. Here, we implement C3-Radix on the SGI Origin 2000 NUMA multiprocessor and make use of the Message Passing Interface (MPI) and the native shared memory directives of that computer to implement the two programming models that we want to analyze.We give results for up to 16 processors and 64M 32bit keys. The results show that for data sets that are small compared to the number of processors, the MPI implementation is faster while for data sets that are large, the shared memory implementation is faster. In the paper, we explain the reasons for the different behaviors depending on the size of the data sets. |
Year | DOI | Venue |
|---|---|---|
1999 | 10.1109/SCCC.1999.810190 | Talca |
Keywords | Field | DocType |
application program interfaces,cache storage,distributed memory systems,message passing,parallel machines,parallel programming,shared memory systems,software performance evaluation,sorting,32-bit keys,C3-Radix sorting algorithm,Communication and Cache-Conscious Radix algorithm,MPI implementation,Message Passing Interface,NUMA multiprocessor,SGI Origin 2000,communication reduction,data set size,distributed memory computers,memory hierarchy locality,native shared memory directives,parallel programming,processor number,shared memory computers | SPMD,Memory hierarchy,Uniform memory access,Shared memory,Computer science,Parallel computing,Distributed memory,Message Passing Interface,Distributed shared memory,Sorting algorithm | Conference |
ISSN | ISBN | Citations |
1522-4902 | 0-7695-0296-2 | 0 |
PageRank | References | Authors |
0.34 | 9 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jimenez-Gonzalez, D. | 1 | 0 | 0.34 |
| Guinovart, E. | 2 | 0 | 0.34 |
| Larriba-Pey, J.L. | 3 | 19 | 2.61 |
| Juan J. Navarro | 4 | 323 | 42.90 |