Designing a High Performance OpenSHMEM Implementation using Universal Common Communication Substrate as a Communication Middleware

Conference · Tue Dec 31 23:00:00 EST 2013

OSTI ID:1127396

Welch, Donald A ^[1]; Shamis, Pavel ^[1]; Gorentla Venkata, Manjunath ^[1]; Poole, Stephen W ^[1]; Tony, Curtis ^[2]

---

1. ORNL
2. University of Houston, Houston

OpenSHMEM is an effort to standardize the well-known SHMEM parallel programming library. The project aims to produce an open-source and portable SHMEM API and is led by ORNL and UH. In this paper, we optimize the current OpenSHMEM reference implementa- tion, based on GASNet, to achieve higher performance characteristics. To achieve these desired performance characteristics, we have redesigned an important component of the OpenSHMEM implementation, the network layer, to leverage a low-level communication library designed for imple- menting parallel programming models called UCCS. In particular, UCCS provides an interface and semantics such as native atomic operations and remote memory operations to better support PGAS programming models, including OpenSHMEM. Through the use of microbenchmarks, we evaluate this new OpenSHMEM implementation on various network metrics, including the latency of point-to-point and collective operations. Furthermore, we compare the performance of our OpenSHMEM imple- mentation with the state-of-the-art SGI SHMEM. Our results show that the atomic operations of our OpenSHMEM implementation outperform SGI s SHMEM implementation by 3%. Its RMA operations outperform both SGI s SHMEM and the original OpenSHMEM reference implemen- tation by as much as 18% and 12% for gets, and as much as 83% and 53% for puts.

• Research Organization: Oak Ridge National Laboratory (ORNL)
• Sponsoring Organization: ORNL work for others
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 1127396
• Country of Publication: United States
• Language: English