Title | ||
---|---|---|
Programming many-core architectures - a case study: dense matrix computations on the Intel single-chip cloud computer processor |
Abstract | ||
---|---|---|
A message passing, distributed-memory parallel computer on a chip is one possible design for future, many-core architectures. We discuss initial experiences with the Intel Single-chip Cloud Computer research processor, which is a prototype architecture that incorporates 48 cores on a single die that can communicate via a small, shared, on-die buffer. The experiment is to port a state-of-the-art, distributed-memory, dense matrix library, Elemental, to this architecture and gain insight from the experience. We show that programmability addressed by this library, especially the proper abstraction for collective communication, greatly aids the porting effort. This enables us to support a wide range of functionality with limited changes to the library code. Copyright © 2011 John Wiley & Sons, Ltd. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1002/cpe.1832 | Concurrency and Computation: Practice and Experience |
Keywords | DocType | Volume |
dense matrix computation,initial experience,Intel single-chip cloud computer,many-core architecture,case study,distributed-memory parallel computer,dense matrix library,Programming many-core architecture,Intel Single-chip Cloud Computer,gain insight,prototype architecture,collective communication,library code,John Wiley | Journal | 24 |
Issue | ISSN | Citations |
12 | 1532-0626 | 6 |
PageRank | References | Authors |
0.61 | 17 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bryan Marker | 1 | 178 | 11.58 |
Ernie Chan | 2 | 393 | 21.90 |
Jack Poulson | 3 | 138 | 8.85 |
Rob F. Van der Wijngaart | 4 | 374 | 45.61 |
Rob F. Van der Wijngaart | 5 | 374 | 45.61 |
Timothy G. Mattson | 6 | 408 | 33.63 |
Theodore E. Kubaska | 7 | 6 | 0.61 |