Speculative Optimizations for Parallel Programs on Multicores

13 years 9 months ago

Download homepages.inf.ed.ac.uk

The advent of multicores presents a promising opportunity for exploiting ﬁne grained parallelism present in programs. Programs parallelized in the above fashion, typically involve threads that communicate via shared memory, and synchronize with each other frequently to ensure that shared memory dependences between diﬀerent threads are correctly enforced. Such frequent synchronization operations, although required, can greatly aﬀect program performance. In addition to forcing threads to wait for other threads and do no useful work, they also force the compiler to make conservative assumptions in generating code. We analyzed a set of parallel programs with ﬁne grained barrier synchronizations, and observed that the synchronizations used by these programs enforce interprocessor dependences which arise relatively infrequently. Motivated by this observation, our approach consists of creating two versions of the section of code between consecutive synchronization operations; one vers...

Vijay Nagarajan, Rajiv Gupta

Real-time Traffic