@inproceedings{springer2017array,
  author = {Matthias Springer and Wauligmann, Peter and Hidehiko Masuhara},
  pdf = {array2017.pdf},
  title = {Modular Array-based {GPU} Computing in a Dynamically-typed Language},
  booktitle = {Proceedings of the 4th ACM SIGPLAN International Workshop on Libraries, Languages, and Compilers for Array Programming (ARRAY2017)},
  month = jun,
  series = {ARRAY 2017},
  year = {2017},
  isbn = {978-1-4503-5069-3},
  location = {Barcelona, Spain},
  pages = {48--55},
  numpages = {8},
  url = {http://doi.acm.org/10.1145/3091966.3091974},
  doi = {10.1145/3091966.3091974},
  acmid = {3091974},
  publisher = {ACM},
  address = {New York, NY, USA},
  keywords = {CUDA, GPGPU, Ruby, kernel fusion, Ikra},
  date = {2017-06-18},
  abstract = {Nowadays, GPU accelerators are widely used in areas with large data-parallel computations such as scientific computations or neural networks. Programmers can either write code in low-level CUDA/OpenCL code or use a GPU extension for a high-level programming language for better productivity. Most extensions focus on statically-typed languages, but many programmers prefer dynamically-typed languages due to their simplicity and flexibility.

This paper shows how programmers can write high-level modular code in Ikra, a Ruby extension for array-based GPU computing. Programmers can compose GPU programs of multiple reusable parallel sections, which are subsequently fused into a small number of GPU kernels. We propose a seamless syntax for separating code regions that extensively use dynamic language features from those that are compiled for efficient execution. Moreover, we propose symbolic execution and a program analysis for kernel fusion to achieve performance that is close to hand-written CUDA code.}
}