Abstract:
GPGPU (general purpose computing on graphics processing units) is one of the economical methods of parallel programming. However, in order to obtain high performance, the programmers must write code in a low-level programming language such as C and pay attention to memory allocation. We propose Sanajeh, a Python DSL (domain-specific language) that compiles object-oriented programs into GPGPU code. It is a language which is based on the Single-Method Multiple-Objects (SMMO) model. Sanijeh compiles parallel Python code into C++/CUDA code and utilizes DynaSOAr for efficient GPU memory allocation.
Reference:
Sanajeh: A DSL for GPGPU Programming With Python Objects (Jizhe Chenxin, Hidehiko Masuhara, Matthias Springer and Youyou Cong), In Proceedings of the 37th Annual Conference of Japan Society for Software Science and Technology (Eijiro Sumii, ed.), 2020.
Bibtex Entry:
@inproceedings{chenxin2020jssst,
url = {https://jssst2020.wordpress.com/},
organization = {{J}apan Society for Software Science and Technology
({JSSST})},
month = sep,
address = {Online},
editor = {Eijiro Sumii},
year = 2020,
booktitle = {Proceedings of the 37th Annual Conference of {J}apan Society for Software Science and Technology},
author = {Jizhe Chenxin and Hidehiko Masuhara and Matthias Springer and Youyou Cong},
title = {{Sanajeh}: A {DSL} for {GPGPU} Programming With {Python} Objects},
abstract = {GPGPU (general purpose computing on graphics processing units) is one of the economical methods of parallel programming. However, in order to obtain high performance, the programmers must write code in a low-level programming language such as C and pay attention to memory allocation. We propose Sanajeh, a Python DSL (domain-specific language) that compiles object-oriented programs into GPGPU code. It is a language which is based on the Single-Method Multiple-Objects (SMMO) model. Sanijeh compiles parallel Python code into C++/CUDA code and utilizes DynaSOAr for efficient GPU memory allocation.},
pdf = {jssst2020.pdf}
}