2015/01/01 by Huan Zhou, Kamran Idrees, José Gracia
Computer Science · #Benchmark (surveying) #Distributed systems and fault tolerance #Embedded Systems Design Techniques #Implementation #Overhead (engineering) #Parallel Computing and Optimization Techniques #Partitioned global address space #Runtime system #Semantics (computer science) #Stencil #cs.DC
paper · pdf · doi:10.1007/978-3-662-48096-0_29
12 papers, accepted for publication in EuroPar 2015
openalex publication_date 2015/01/01 · arxiv created 2016/03/07 · arxiv updated 2016/03/08 · openalex created_date 2016/06/24 · openalex updated_date 2026/08/05
The relaxed semantics and rich functionality of one-sided communication primitives of MPI-3 makes MPI an attractive candidate for the implementation of PGAS models. However, the performance of such implementation suffers from the fact, that current MPI RMA implementations typically have a large overhead when source and target of a communication request share a common, local physical memory. In this paper, we present an optimized PGAS-like runtime system which uses the new MPI-3 shared-memory extensions to serve intra-node communication requests and MPI-3 one-sided communication primitives to serve inter-node communication requests. The performance of our runtime system is evaluated on a Cray XC40 system through low-level communication benchmarks, a random-access benchmark and a stencil kernel. The results of the experiments demonstrate that the performance of our hybrid runtime system matches the performance of low-level RMA libraries for intra-node transfers, and that of MPI-3 for inter-node transfers.