@inproceedings{sen2017rosa,
author = {Sen, Rathijit and Zhu, Jianqiao and Patel, Jignesh M. and Jha, Somesh},
title = {ROSA: R Optimizations with Static Analysis},
booktitle = {RIOT 2017},
year = {2017},
month = {July},
abstract = {R is a popular language and programming environment for data scientists. It is increasingly co-packaged with both relational and Hadoop-based data platforms and can often be the most dominant computational component in data analytics pipelines. Recent work has highlighted inefficiencies in executing R programs, both in terms of execution time and memory requirements, which in practice limit the size of data that can be analyzed by R. This paper presents ROSA, a static analysis framework to improve the performance and space efficiency of R programs. ROSA analyzes input programs to determine program properties such as reaching definitions, live variables, aliased variables, and types of variables. These inferred properties enable program transformations such as C++ code translation, strength reduction, vectorization, code motion, in addition to interpretive optimizations such as avoiding redundant object copies and performing in-place evaluations. An empirical evaluation shows substantial reductions by ROSA in execution time and memory consumption over both CRAN R and Microsoft R Open.},
publisher = {arXiv},
url = {http://approjects.co.za/?big=en-us/research/publication/rosa-r-optimizations-with-static-analysis/},
}