Charm++ for Productivity and Performance: A Submission to the 2011 HPC Class II Challenge

We present our implementation of the HPC Challenge Class II (productivity) benchmarks in the Charm++ programming paradigm. Our submission focuses on explaining 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 submission includes implementations of three required benchmarks: Dense LU Factorization, FFT, and Random Access. We also include two additional benchmarks that represent relevant scientific computing algorithms of some complexity: Molecular Dynamics and Barnes-Hut. We believe our implementations demonstrate that a high-level productivity oriented model can also deliver portable performance via an intelligent runtime.

@techreport{hpcChallenge:2011,
  author        = {Laxmikant Kale and Anshu Arya and Abhinav Bhatele and Abhishek Gupta and Nikhil Jain and Pritish Jetley and Jonathan Lifflander and Phil Miller and Yanhua Sun and Ramprasad Venkataraman and Lukasz Wesolowski and Gengbin Zheng},
  title         = {Charm++ for Productivity and Performance: A Submission to the 2011 {HPC} Class {II} Challenge},
  year          = {2011},
  month         = {November},
  number        = "11-49",
  institution   = "Parallel Programming Laboratory",
}