期刊
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
卷 31, 期 12, 页码 2968-2980出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPDS.2019.2905201
关键词
Field programmable gate arrays; Yarn; Resource management; Task analysis; Scheduling; Computer architecture; Processor scheduling; Heterogeneous system; heterogeneous FPGA architecture; FPGA-accelerated computing; data-intensive computing; YARN
资金
- National Key Research and Development Program of China [2016YFB0800402, 2016QY01W0202]
- National Natural Science Foundation of China [U1836204, 61572221, 61433006, U1401258, 61572222, 61502185]
- Major Projects of the National Social Science Foundation [16ZDA092]
- Guangxi High level innovation Team in Higher Education Institutions Innovation Team of ASEAN Digital Cloud Big Data Security and Mining Technology
In recent years, the heterogeneous distributed platform integrating with FPGAs to accelerate computation tasks has been widely studied to deal with the deluge of data. However, most of current works suffer from poor universality and low resource utilization that run specific algorithms with the highly customized structure. Moreover, there are still many challenges, such as data curation, task scheduling, and resource management, which further limit the scalability of a CPU-FPGA distributed platform. In this paper, we present HeteroYARN, an FPGA-accelerated heterogeneous architecture based on YARN platform, which provides resource management and programming support for computing-intensive applications using FPGAs. In particular, the HeteroYARN abstracts FPGA accelerators as general resources and provides programming APIs to utilize those accelerators easily. Our HeteroYARN simplifies the request and usage of FPGA resources to enhance the efficiency of the heterogeneous framework while maintaining previous workflow unchanged. Experimental results using two representative algorithms, K-means and Naive Bayes classifier, which are accelerated by FPGAs, demonstrate the usability of the HeteroYARN framework and show performance speedup improvement by 7.5x (K-means) and 2.3x (Naive Bayes) respectively compared to conventional CPU-only applications provided by Mahout.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据