Name
Abstract | ||
|---|---|---|
In the push to achieve exascale performance, systems will grow to over 100,000 sockets, as growing cores-per-socket and improved single-core performance provide only part of the speedup needed. These systems will need affordable interconnect structures that scale to this level. To meet the need, we consider an extension of the hypercube and flattened butterfly topologies, the HyperX, and give an adaptive routing algorithm, DAL. HyperX takes advantage of high-radix switch components that integrated photonics will make available. Our main contributions include a formal descriptive framework, enabling a search method that finds optimal HyperX configurations; DAL; and a low cost packaging strategy for an exascale HyperX. Simulations show that HyperX can provide performance as good as a folded Clos, with fewer switches. We also describe a HyperX packaging scheme that reduces system cost. Our analysis of efficiency, performance, and packaging demonstrates that the HyperX is a strong competitor for exascale networks. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1145/1654059.1654101 | SC |
Keywords | Field | DocType |
hyperx packaging scheme,system cost reduction,network routing,butterfly topology,multistage interconnection networks,system cost,exascale performance,exascale hyperx,adaptive routing algorithm,folded clos,network packaging,optimal hyperx configuration,network topology,interconnect structures,improved single-core performance,low cost packaging strategy,optimal hyperx configurations,exascale network,efficient large-scale network,single-core performance,digital arithmetic,search problems,high-radix switch components,flattened butterfly topology,integrated photonics,large-scale networks,formal descriptive framework,dal,hypercube,exascale networks,cores-per-socket,search method,hypercube networks,sparse matrices,affinity propagation,adaptive routing,kernel methods | Adaptive routing algorithm,Affinity propagation,Clos network,Computer science,Parallel computing,Network topology,Interconnection,Hypercube,Sparse matrix,Speedup,Distributed computing | Conference |
Citations | PageRank | References |
89 | 4.94 | 11 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jung Ho Ahn | 1 | 2657 | 122.11 |
| Nathan Binkert | 2 | 1129 | 38.76 |
| Al Davis | 3 | 986 | 54.47 |
| Moray McLaren | 4 | 481 | 33.08 |
| Robert Schreiber | 5 | 211 | 20.38 |