Technical Report 2017-008

Scope-Aware Classification: Taking the Hierarchical Private/Shared Data Classification to the Next Level

Mahdad Davari, Erik Hagersten, and Stefanos Kaxiras

April 2017


Hierarchical techniques are commonplace in ameliorating the bottlenecks, such as cache coherence, in the design of scalable multi/manycores. Furthermore, there have been proposals to simplify the coherence based on the data-race-free semantics of the software and private/shared data classification, where cores self-invalidate their shared data upon synchronizations. However, naive private/shared data classification in the hierarchies nullifies such optimizations by increasing the amount of data misclassified as shared and therefore being needlessly self-invalidated.

We introduce a private/shared data classification approach for hierarchical clusters, where a datum is concurrently classified as private and shared with respect to different classification scopes. Such scope-aware classification eliminates the needless self-invalidation of the valid data at synchronizations, resulting in a coherence scheme that reduces the average network traffic and execution time by 30% and 5%, respectively.

Available as PDF (340 kB, no cover)

Download BibTeX entry.