@inproceedings{187644ae40324b4fa59a8ffcac7a4874,
title = "VersaPipe: A versatile programming framework for pipelined computing on GPU",
abstract = "mostly for data-level parallel executions, lacks an efficient mechanism to support pipeline programming and executions. This paper provides a systematic examination of various existing pipeline execution models on GPU, and analyzes their strengths andweaknesses. To address their shortcomings, this paper then proposes three new execution models equipped with much improved controllability, including a hybrid model that is capable of getting the strengths of all. These insights ultimately lead to the development of a software programming framework named VersaPipe. With VersaPipe, users only need to write the operations for each pipeline stage. VersaPipe will then automatically assemble the stages into a hybrid execution model and configure it to achieve the best performance. Experiments on a set of pipeline benchmarks and a real-world face detection application show that VersaPipe produces up to 6.90× (2.88× on average) speedups over the original manual implementations.",
keywords = "GPU, Pipelined computing",
author = "Zhen Zheng and Chanyoung Oh and Jidong Zhai and Xipeng Shen and Youngmin Yi and Wenguang Chen",
note = "Publisher Copyright: {\textcopyright} 2017 Association for Computing Machinery.; 50th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2017 ; Conference date: 14-10-2017 Through 18-10-2017",
year = "2017",
month = oct,
day = "14",
doi = "10.1145/3123939.3123978",
language = "English",
series = "Proceedings of the Annual International Symposium on Microarchitecture, MICRO",
publisher = "IEEE Computer Society",
pages = "587--599",
booktitle = "MICRO 2017 - 50th Annual IEEE/ACM International Symposium on Microarchitecture Proceedings",
address = "United States",
}