Token Coherence: decoupling performance and correctness

By Milo M. K. Martin, Mark D. Hill, David A. Wood. 30th Annual International Symposium on Computer Architecture, 2003. Proceedings., 2003

312 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Electrical and Electronic Engineering, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/e5796735c62625e990178c35e2b6206a415303a7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

1. T. Harris
2. J. Larus
3. Ravi Rajwar
4. Jichuan Chang
5. G. Sohi
6. David A. Wood
7. Tushar Krishna
8. Jayneel Gandhi

In Electrical and Electronic Engineering

1. T. Harris
2. Jichuan Chang
3. J. Larus
4. G. Sohi
5. Tushar Krishna
6. Ravi Rajwar
7. Håkan Grahn

In Hardware and Architecture

1. T. Harris
2. J. Larus
3. Jichuan Chang
4. G. Sohi
5. Ravi Rajwar
6. David A. Wood
7. Tushar Krishna
8. Jayneel Gandhi

Citations in the corpus

• Transactional Memory, 2nd edition (2010, background): “TokenTM does this by introducing the notion of transactional tokens captured in per-memory block metadata, inspired by the idea of token-based coherence mechanisms [213].”
• The gem5 Simulator: Version 20.0+ (2020, background): “In mainline gem5, there are now 12 unique protocols including GPU-specific protocols, region-coherence protocols [58], research protocols like token coherence [49], and teaching protocols [52].”
• Cooperative Caching for Chip Multiprocessors (2006, methodology): “Token coherence [23] and its application to multiple-CMP systems [24] simplifies the protocol design by decoupling the protocol’s correctness substrate and performance policy.”