Migratable Objects + Active Messages + Adaptive Runtime = Productivity + Performance: A Submission to the 2012 HPC Class II Challenge
International Conference for High Performance Computing, Networking, Storage and Analysis (SC) 2012
Publication Type: Paper
Repository URL:
Abstract
Charm++ is an elegant, general-purpose parallel programming model backed by an adaptive runtime system [1]. This combination yields portable performance and a spectrum of real-world productivity benefits that have been demonstrated in production applications. Our submission to this year’s HPC Challenge (Class II) comprises six benchmarks that demonstrate these practical benefits available to application developers today. These include: (1) interoperability with MPI (2) automatic, dynamic load balancing (3) effortless checkpointing and restart on a different number of processors, and (4) application progress in the presence of failing processes. The submission also explains how over-decomposed, message-driven, migratable objects enhance the clarity of expression of parallel programs and also enable the runtime system to deliver portable performance. Our code size (line counts) and a summary of the performance results can be seen in Table 1.
TextRef
People
Research Areas