DASH: A C++ PGAS Library for Distributed Data Structures and Parallel Algorithms
Authors:
- Karl FuerlingerKFKarl Fuerlinger
- Tobias FuchsTFTobias Fuchs
- Roger KowalewskiRKRoger Kowalewski
- 1 December 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 983-990
Abstract
We present DASH, a C++ template library that offers distributed data structures and parallel algorithms and implements a compiler-free PGAS (partitioned global address space) approach. DASH offers many productivity and performance features such as global-view data structures, efficient support for the owner-computes model, flexible multidimensional data distribution schemes and interoperability with STL (standard template library) algorithms. DASH also features a flexible representation of the parallel target machine and allows the exploitation of several hierarchically organized levels of locality through a concept of Teams. We evaluate DASH on a number of benchmark applications and we port a scientific proxy application using the MPI two-sided model to DASH. We find that DASH offers excellent productivity and performance and demonstrate scalability up to 9800 cores.Keywords
This publication has 26 references indexed in Scilit:
- Notified Access: Extending Remote Memory Access Programming Models for Producer-Consumer Synchronization2015
- Porting scientific libraries to PGAS in XSEDE resources2015
- Kokkos: Enabling manycore performance portability through polymorphic memory access patternsJournal of Parallel and Distributed Computing, 2014
- UPC++: A PGAS Extension for C++2014
- Exascale Computing Trends: Adjusting to the "New Normal"' for Computer ArchitectureComputing in Science & Engineering, 2013
- Designing Scalable Graph500 Benchmark with Hybrid MPI+OpenSHMEM Programming Models2013
- Hierarchical Place Trees: A Portable Abstraction for Task Parallelism and Data Movement2010
- Parallel Programmability and the Chapel LanguageThe International Journal of High Performance Computing Applications, 2007
- ARMCI: A portable remote memory copy library for distributed array libraries and compiler run-time systems1999
- Co-array Fortran for parallel programmingACM SIGPLAN Fortran Forum, 1998