arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.02386cs.LGcs.NEstat.ML
收藏

Cheetah:边缘DNN的混合低精度硬件和软件协同设计框架

Cheetah: Mixed Low-Precision Hardware & Software Co-Design Framework for DNNs on the Edge

Rochester Institute of Technology(罗切斯特理工学院)

Hamed F. Langroudi, Zachariah Carmichael, David Pastuch, Dhireesha Kudithipudi

摘要:

低精度DNN已被广泛研究,以减少边缘设备的DNN模型的大小。最近,DNN数值格式已经显示出对DNN数据表示和超低精度计算的承诺[5]。8]位。然而,以前的研究仅限于DNN推理的研究。在本文中,我们提出了Cheetah框架,它支持DNN训练和使用posits的推理,以及其他常用格式。此外,该框架适用于不同的量化方法,并支持混合精度浮点和定点数值格式。Cheetah在三个数据集上进行评估:MNIST,Fashion MNIST和CIFAR-10。结果表明,在DNN训练中,16位定位优于16位浮点。此外,使用[5. 8]-位假设改善了性能和能量延迟积之间的权衡[5.. 8]-位浮点和定点。

英文摘要:

Low-precision DNNs have been extensively explored in order to reduce the size of DNN models for edge devices. Recently, the posit numerical format has shown promise for DNN data representation and compute with ultra-low precision in [5..8]-bits. However, previous studies were limited to studying posit for DNN inference only. In this paper, we propose the Cheetah framework, which supports both DNN training and inference using posits, as well as other commonly used formats. Additionally, the framework is amenable for different quantization approaches and supports mixed-precision floating point and fixed-point numerical formats. Cheetah is evaluated on three datasets: MNIST, Fashion MNIST, and CIFAR-10. Results indicate that 16-bit posits outperform 16-bit floating point in DNN training. Furthermore, performing inference with [5..8]-bit posits improves the trade-off between performance and energy-delay-product over both [5..8]-bit float and fixed-point.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑