Remote Memory Access (RMA) programming enables direct access to low-level hardware features to achieve high performance for distributed-memory programs. However, the design of RMA programming schemes focuses on the memory access and less on the synchronization. For example, in contemporary RMA programming systems, the widely used producer-consumer pattern can only be implemented inefficiently, incurring in an overhead of an additional round-trip message. We propose Notified Access, a scheme where the target process of an access can receive a completion notification. This scheme enables direct and efficient synchronization with a minimum number of messages. We implement our scheme in an open source MPI-3 RMA library and demonstrate lower overheads (two cache misses) than other point-to-point synchronization mechanisms for each notification. We also evaluate our implementation on three real-world benchmarks, a stencil computation, a tree computation, and a Colicky factorization implemented with tasks. Our scheme always performs better than traditional message passing and other existing RMA synchronization schemes, providing up to 50% speedup on small messages. Our analysis shows that Notified Access is a valuable primitive for any RMA system. Furthermore, we provide guidance for the design of low-level network interfaces to support Notified Access efficiently.
|Original language||English (US)|
|Title of host publication||2015 IEEE International Parallel and Distributed Processing Symposium|
|Publisher||Institute of Electrical and Electronics Engineers (IEEE)|
|Number of pages||11|
|State||Published - May 2015|
Bibliographical noteKAUST Repository Item: Exported on 2020-10-01
Acknowledgements: We thank Hatem Ltaief (Kaust) for providing theCholesky example. We thank the GASPI team for inspir-ing discussions about RMA interfaces and Christian Sim-mendinger for numerous clarifications about the GASPIspecification. We thank James Dinan (Intel), Jeff Ham-mond (Intel), Kathy Yelick (LBNL), Edgar Solomonik, TimoSchneider, and Salvatore Di Girolamo for helpful discus-sions, Larry Kaplan (Cray) for help with uGNI, and theSwiss National Supercomputing Centre (CSCS) for accessto Piz Daint.
This publication acknowledges KAUST support, but has no KAUST affiliated authors.