This talk will provide an overview of two parallel programming models, OpenSHMEM and SharP, to address the challenges of programming extreme-scale systems. OpenSHMEM is a well-established library based PGAS programming model for programming HPC systems. It is particularly popular for workloads that has irregular communication patterns. SharP uses distributed data-structure approach to abstract the memory and provide uniform interfaces for data abstractions, locality, sharing and resiliency across these memory systems. These two complementary programming models provide ability to program emerging architectures for Big-Compute and Big-Data applications. After the overview, we will present experimental results for a wide-variety of applications including QMCPack, Graph500, and Memcached demonstrating the programming model advantages.
Friday, April 20, 2018 at 11:15am to 12:15pm
Love Building (LOV), 353
1017 Academic Way, Tallahassee, FL
No recent activity