Tango: A Deep Neural Network Benchmark Suite for Various Accelerators
Computer Engineering Department, San Jose State University, San Jose, CA, USA
arXiv:1901.04987 [cs.DC], (14 Jan 2019)
@article{karki2019tango,
title={Tango: A Deep Neural Network Benchmark Suite for Various Accelerators},
author={Karki, Aajna and Keshava, Chethan Palangotu and Shivakumar, Spoorthi Mysore and Skow, Joshua and Hegde, Goutam Madhukeshwar and Jeon, Hyeran},
year={2019},
month={jan},
archivePrefix={"arXiv"},
primaryClass={cs.DC}
}
Deep neural networks (DNNs) have been proving the effectiveness in various computing fields. To provide more efficient computing platforms for DNN applications, it is essential to have evaluation environments that include assorted benchmark workloads. Though a few DNN benchmark suites have been recently released, most of them require to install proprietary DNN libraries or resource-intensive DNN frameworks, which are hard to run on resource-limited mobile platforms or architecture simulators. To provide a more scalable evaluation environment, we propose a new DNN benchmark suite that can run on any platform that supports CUDA and OpenCL. The proposed benchmark suite includes the most widely used five convolution neural networks and two recurrent neural networks. We provide in-depth architectural statistics of these networks while running them on an architecture simulator, a server- and a mobile-GPU, and a mobile FPGA.
January 20, 2019 by hgpu
