Title :
C++ EDSL for parallel code generation
Author_Institution :
GPU Lab, Institute for Particle and Nuclear Physics, Wigner RCP, P.O. Box 49, Budapest 1525, Hungary
Abstract :
Code generation is ubiquitous for modern highperformance computing (HPC) to provide efficient but highly parametrizable program development. Many times functional dependencies should be made available for the user to manipulate, and such arbitrary functions should be efficiently parallelized over multiple levels. We propose an embedded domain specific language inside C++ for manipulating abstract syntax trees (ASTs) that can represent arbitrary computation, and that such language can be extended with constructs for parallelism and functional programming.
Keywords :
"Parallel processing","Syntactics","Hardware","Graphics processing units","Computer languages","Functional programming","Runtime"
Conference_Titel :
Grid, Cloud & High Performance Computing in Science (ROLCG), 2015 Conference
DOI :
10.1109/ROLCG.2015.7367231