Lazy release consistency for software distributed shared memory
Peter J. Keleher, Alan L. Cox, Willy Zwaenepoel Y · Proceedings - International Symposium on Computer Architecture/Proceedings · 1992
Relaxed memory consistency models, such as release consistency, were introduced in order to reduce the impact of remote memory access latency in both software and hardware distributed shared memory (DSM). However, in a software DSM, it is also important to reduce the number of messages and the amount of data exchanged for remote memory access. Lazy release consistency is a new algorithm for implementing release consistency that lazily pulls modifications across the interconnect only when necessary. Trace-driven simulation using the SPLASH benchmarks indicates that lazy release consistency reduces both the number of messages and the amount of data transferred between processors. These reductions are especially significant for programs that exhibit false sharing and make extensive use of locks.
Cited by 564 works. doi:10.1145/139669.139676
Authors
References
- How to Make a Multiprocessor Computer That Correctly Executes Multiprocess Programs
- SPLASH
- Memory coherence in shared virtual memory systems
- The directory-based cache coherence protocol for the DASH multiprocessor
- Memory consistency and event ordering in scalable shared-memory multiprocessors
- Implementation and performance of Munin
- Weak ordering—a new definition
- Cache Consistency and Sequential Consistency
- Analysis of cache invalidation patterns in multiprocessors
- Memory access dependencies in shared-memory multiprocessors