Name
Abstract | ||
|---|---|---|
Software distributed shared memory (DSM) techniques, while effective on applications with coarse-grained sharing, yield poor performance for the fine-grained sharing encountered in applications increasingly relying on sophisticated adaptive and hierarchical algorithms. Such applications exhibit irregular communication patterns unsynchronized with computation, incurring large overheads for synchronous (request-reply) DSM protocols that require responsive processing of coherence messages. We describe a new DSM framework, View Caching, that addresses this problem by utilizing application knowledge of data access semantics to enable the construction of low-overhead, asynchronous coherence protocols. Experiments on the Cray T3D show that view caching enables efficient execution of fine-grained irregular applications, reducing both coherence overheads and idle time to improve performance by up to 35% over a weakly-consistent DSM implementation. |
Year | DOI | Venue |
|---|---|---|
1997 | 10.1109/IPPS.1997.580944 | IPPS |
Keywords | Field | DocType |
weakly-consistent dsm implementation,dsm protocol,applications exhibit irregular communication,fine-grained irregular application,coherence overhead,coherence message,dynamic computations,asynchronous coherence protocol,view caching,efficient software shared memory,coarse-grained sharing,new dsm framework,hardware,dynamic programming,coherence,robustness,shared memory,software performance,data access,application software,computer science | Interleaved memory,Uniform memory access,Shared memory,Computer science,Distributed memory,Data diffusion machine,Memory management,Memory map,Distributed shared memory,Distributed computing | Conference |
ISSN | ISBN | Citations |
1063-7133 | 0-8186-7792-9 | 3 |
PageRank | References | Authors |
0.41 | 13 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Vijay Karamcheti | 1 | 646 | 67.03 |
| Andrew A. Chien | 2 | 3696 | 405.97 |