This book constitutes the proceedings of the Third OpenSHMEM Workshop, held in Baltimore, MD, USA, in August 2016. The 14 full papers and 3 short papers presented were carefully reviewed and selected from 25 submissions. The papers discuss a variety of ideas of extending the OpenSHMEM specification and making it efficient for current and next generation systems. This included active messages, non-blocking APIs, fault tolerance capabitlities, exploring implementation of OpenSHMEM using communication layers such as OFI and UCX and implementing OpenSHMEM for heterogeneous architectures.

This includes new research for communication contexts in OpenSHMEM, different optimizations for OpenSHMEM on shared memory machines, exploring the implementation of OpenSHMEM and its memory model on Intel's KNL architecture, and implementing new applications and benchmarks with OpenSHMEM.