arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.04861cs.LGcs.AIcs.AR
收藏

基于流水线矩阵乘法加速设计和非均匀Quantization的深度学习推理方案

A Deep Learning Inference Scheme Based on Pipelined Matrix Multiplication Acceleration Design and Non-uniform Quantization

Tsinghua University(清华大学)

Yuyang Zhang, Dik Hin Leung, Min Guo, Yijia Xiao, Haoyue Liu, Yunfei Li, Jiyuan Zhang, Guan Wang, Zhen Chen

摘要:

矩阵乘法是深度学习推理应用的基础。当涉及到边缘计算设备上的硬件加速时,矩阵乘法通常会占用大部分时间。为了在边缘计算中实现更好的性能,我们引入了一种基于流水线矩阵乘法方案和非均匀量化方法的低功耗多层感知器(MLP)加速器。该实现在现场可编程门阵列(FPGA)器件上运行,并在手写数字分类和Q学习任务上测试了其性能。结果表明,我们的方法可以实现更好的性能与更少的功耗。

英文摘要:

Matrix multiplication is the bedrock in Deep Learning inference application. When it comes to hardware acceleration on edge computing devices, matrix multiplication often takes up a great majority of the time. To achieve better performance in edge computing, we introduce a low-power Multi-layer Perceptron (MLP) accelerator based on a pipelined matrix multiplication scheme and a nonuniform quantization methodology. The implementation is running on Field-programmable Gate Array (FPGA) devices and tested its performance on handwritten digit classification and Q-learning tasks. Results show that our method can achieve better performance with fewer power consumption.

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。

↑