Deconstructing redundant memory synchronization

In multiprocessor systems with weakly consistent shared memory, memory fence (also know as barrier) instructions are necessary to establish memory consistency at synchro-nization points in a parallel program. Programs that fol-low an acquire-release synchronization protocol (e.g., Java) make frequent use of such fence instructions and hence the thrifty use and efficient implementation of such instruc-tions is an important performance aspect. Perhaps sur-prisingly, this paper demonstrates on the example of multi-threaded Java benchmarks that most fences occurring in a program execution are- ex post- unnecessary according to the rules of memory consistency demanded by the software (max. 99.9%, avg.> 98%). We conclude that the model for memory synchronization offered by current multiproces-sor systems is not well aligned with the requirements of the widely used acquire-release software synchronization proto-col. 1