Name
Abstract | ||
|---|---|---|
Many future shared-memory multiprocessor servers will both target commercial workloads and use highly-integrated "glueless" designs. Implementing low-latency cache coherence in these systems is difficult, because traditional approaches either add indirection for common cache-to-cache misses (directory protocols) or require a totally-ordered interconnect (traditional snooping protocols). Unfortunately, totally-ordered interconnects are difficult to implement in glueless designs. An ideal coherence protocol would avoid indirections and interconnect ordering; however, such an approach introduces numerous protocol races that are difficult to resolve.We propose a new coherence framework to enable such protocols by separating performance from correctness. A performance protocol can optimize for the common case (i.e., absence of races) and rely on the underlying correctness substrate to resolve races, provide safety, and prevent starvation. We call the combination Token Coherence, since it explicitly exchanges and counts tokens to control coherence permissions.This paper develops TokenB, a specific Token Coherence performance protocol that allows a glueless multiprocessor to both exploit a low-latency unordered interconnect (like directory protocols) and avoid indirection (like snooping protocols). Simulations using commercial workloads show that our new protocol can significantly outperform traditional snooping and directory protocols. |
Year | DOI | Venue |
|---|---|---|
2003 | 10.1145/871656.859640 | ACM Sigarch Computer Architecture News |
Keywords | Field | DocType |
low-latency cache coherence,new protocol,glueless design,decoupling performance,ideal coherence protocol,new coherence framework,coherence permission,performance protocol,token coherence,glueless multiprocessor,numerous protocol race,directory protocol,broadcasting,low latency,cache coherence,space technology,total order,protocols,switches,file servers,logic,bandwidth | File server,Indirection,Directory,Computer science,Server,Parallel computing,Correctness,Real-time computing,Coherence (physics),Security token,Cache coherence,Distributed computing | Conference |
Volume | Issue | ISSN |
31 | 2 | 0163-5964 |
ISBN | Citations | PageRank |
0-7695-1945-8 | 144 | 5.46 |
References | Authors | |
91 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Milo M. K. Martin | 1 | 2677 | 125.22 |
| Mark D. Hill | 2 | 7371 | 582.90 |
| David A. Wood | 3 | 6058 | 617.11 |