APL on GPUs: A TAIL from the Past, Scribbled in Futhark
HIPERFIT, Department of Computer Science, University of Copenhagen (DIKU), Denmark
5th ACM SIGPLAN workshop on Functional High-Performance Computing (FHPC’16), 2016
@inproceedings{henriksen2016apl,
title={APL on GPUs: A TAIL from the Past, Scribbled in Futhark},
author={Henriksen, Troels and Dybdal, Martin and Urms, Henrik and Kiehn, Anna Sofie and Gavin, Daniel and Abelskov, Hjalte and Elsman, Martin and Oancea, Cosmin},
booktitle={Proceedings of the 5th International Workshop on Functional High-Performance Computing},
pages={38–43},
year={2016},
organization={ACM}
}
This paper demonstrates translation schemes by which programs written in a functional subset of APL can be compiled to code that is run efficiently on general purpose graphical processing units (GPGPUs). Furthermore, the generated programs can be straightforwardly interoperated with mainstream programming environments, such as Python, for example for purposes of visualization and user interaction. Finally, empirical evaluation shows that the GPGPU translation achieves speedups up to hundreds of times faster than sequential C compiled code.
October 4, 2016 by hgpu
