Eager combining: a coherency protocol for increasing effective network and memory bandwidth in shared-memory multiprocessors

An excessive number of remote accesses or a non-uniform distribution of remote accesses can cause even well-designed multiprocessors to exhibit severe memory and network contention. Producer/consumer data generates a particularly common sharing pattern that results in a non-uniform distribution of references. In this paper we quantify the performance impact of producer/consumer sharing as a function of memory and network bandwidth, and argue that the contention caused by this form of sharing severely impacts performance on large-scale machines. We propose a new coherency protocol, called eager combining, which is designed to alleviate this contention. We use execution-driven simulation of parallel programs on a large-scale multiprocessor to show that eager combining can improve the performance of programs with pro-ducer/consumer data by a factor of 4 or more.