Using Hybrid Model OpenSHMEM + CUDA to Implement the SHOC Benchmark Suite

Conference · Thu Aug 04 00:00:00 EDT 2016

DOI:https://doi.org/10.1007/978-3-319-50995-2_14· OSTI ID:1567410

Grodowitz, Megan ^[1]; D’Azevedo, Eduardo ^[1]; Powers, Sarah ^[1]; Imam, Neena ^[1]

---

1. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

This work describes the process of porting the Scalable HeterOgeneous Computing (SHOC) benchmark suite from the hybrid MPI + CUDA implementation to OpenSHMEM + CUDA. SHOC includes a wide variety of benchmark kernels used to measure accelerator performance in both single node and cluster configurations. The hybrid model implementation attempts to place all major computation on accelerator devices, and uses MPI to synchronize and aggregate results. In some cases, MPI Groups are used to gradually reduce the number of accelerators used for computation as the problem size drops. Porting this behavior to OpenSHMEM required implementing several synchronizing collective operations, and using SHMEM teams to replace MPI Group functionality. Benchmark results on a Cray XK7 system with one GPU per compute node show that SHMEM performance is equal to MPI performance in these hybrid tasks. These results and porting experience show that using OpenSHMEM for accelerator devices benefits from adding functionality for synchronization and teams, and would further benefit from adding support for communication within accelerator kernels.

• Research Organization: Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility (OLCF)
• Sponsoring Organization: USDOE Office of Science (SC)
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 1567410
• Resource Relation: Conference: OpenSHMEM and Related Technologies. Enhancing OpenSHMEM for Hybrid Environments, Third Workshop, OpenSHMEM 2016, Baltimore, MD (United States), 2-4 Aug, 2016
• Country of Publication: United States
• Language: English

Related Subjects

97 MATHEMATICS AND COMPUTING
Computer Science