Universal constructions for large objects

Abstract

We present lock-free and wait-free universal constructions for implementing large shared objects. Most previous universal constructions require processes to copy the entire object state, which is impractical for large objects. Previous attempts to address this problem require programmers to explicitly fragment large objects into smaller, more manageable pieces, paying particular attention to how such pieces are copied. In contrast, our constructions are designed to largely shield programmers from this fragmentation. Furthermore, for many objects, our constructions result in lower copying overhead than previous ones.

Fragmentation is achieved in our constructions through the use of load-linked, store-conditional, and validate operations on a “large” multi-word shared variable. Before presenting our constructions, we show that these operations can be efficiently implemented from similar one-word primitives.

Work supported, in part, by NSF contract CCR 9216421, and by a Young Investigator Award from the U.S. Army Research Office, grant number DAAHO4-95-1-0323.