A methodology to characterize critical section bottlenecks in DSM multiprocessors?

Abstract. Understanding and optimizing the synchronization opera-tions of parallel programs in distributed shared memory multiprocessors (dsm), is one of the most important factors leading to significant reduc-tions in execution time. This paper introduces a new methodology for tuning performance of par-allel programs. We focus on the critical sections used to assure exclusive access to critical resources and data structures, proposing a specific dy-namic characterization of every critical section in order to a) measure the lock contention, b) measure the degree of data sharing in consec-utive executions, and c) break down the execution time, reflecting the different overheads that can appear. All the required measurements are taken using a multiprocessor simulator with a detailed timing model of the processor and memory system. We propose also a static classification of critical sections that takes into account how locks are associated with their protected data. The dynamic characterization and the static classification are correlated to identify key critical sections and infer code optimization opportunities (e.g. data lay-out), which when applied can lead to significant reductions in execution time (up to 33 % in the SPLASH-2 scientific benchmark suite). By using the simulator we can also evaluate whether the performance of the ap-plied code optimizations is sensitive to common hardware optimizations or not.