Publikationsansicht

Epoch 3 (2007)

Abstract
Thread-Level Data Speculation (TLDS) is a technique which enables the optimistic parallelization of applications despite ambiguous data dependences between the resulting threads. Although TLDS is mostly managed by software, hardware provides two key pieces of functionality: (i) detecting dependence violations, and (ii) buffering speculative side-effects until they can be safely committed to memory. To provide this functionality we present an extension to invalidation-based cache coherence which is both scalable and has a minimal impact on hardware complexity. We explore the design space in depth and find that our baseline architecture is sufficient to exploit speculative parallelism.

Details der Publikation
Download http://citeseerx.ist.psu.edu/viewdoc/summary?doi=?doi=10.1.1.30.7771
Quelle http://reports-archive.adm.cs.cmu.edu/anon/1998/CMU-CS-98-171.ps
Mitarbeiter CiteSeerX
Archiv CiteSeerX - Scientific Literature Digital Library and Search Engine (United States)
Keywords Redo Processor1 Processor2 Processor3 Processor4
Typ text
Sprache Englisch
Verknüpfungen 10.1.1.42.7329, 10.1.1.134.208, 10.1.1.136.951, 10.1.1.33.9954, 10.1.1.119.8529, 10.1.1.20.7353, 10.1.1.18.7505, 10.1.1.114.2587, 10.1.1.48.7426