The Community for Technology Leaders
Proceedings.International Conference on Parallel Architectures and Compilation Techniques (2002)
Charlottesville, Virginia
Sept. 22, 2002 to Sept. 25, 2002
ISSN: 1089-795X
ISBN: 0-7695-1620-3
pp: 179
Chris Gniady , Carnegie Mellon University
Babak Falsafi , Carnegie Mellon University
This paper proposes SC++lite, a sequentially-consistent system that relaxes memory order speculatively to bridge the performance gap among memory consistency models. Prior proposals to speculatively relax memory order require large custom on-chip storage to maintain a history of speculative processor and memory state while memory order is relaxed. SC++lite uses the memory hierarchy to store the speculative history, providing a scalable path for speculative SC systems across a wide range of applications and system latencies. We use cycle-accurate simulation of shared-memory multiprocessors to show that SC++lite can fully relax memory order while virtually obviating the need for custom on-chip storage. Moreover, while demand for storage increases significantly with larger memory latencies, SC++lite?s ability to relax memory order remains insensitive to memory latency. An SC++lite system can improve performance over a base SC system by 28% with only 2KB of custom storage in a system with 16 processors. In contrast, speculative SC systems with custom storage require 51KB of storage to improve performance by 31% over a base SC system.

C. Gniady and B. Falsafi, "Speculative Sequential Consistency with Little Custom Storage," Proceedings.International Conference on Parallel Architectures and Compilation Techniques(PACT), Charlottesville, Virginia, 2002, pp. 179.
92 ms
(Ver 3.3 (11022016))