2018 ACM/IEEE International Workshop on System Level Interconnect Prediction (SLIP)最新文献

A Study of Optimal Cost-Skew Tradeoff and Remaining Suboptimality in Interconnect Tree Constructions 互连树结构中最优成本-偏态权衡与剩余次优性研究

2018 ACM/IEEE International Workshop on System Level Interconnect Prediction (SLIP) Pub Date : 2018-06-23 DOI: 10.1145/3225209.3225215

Kwangsoo Han, A. Kahng, C. Moyes, A. Zelikovsky

引用次数: 3

Resource and Data Optimization for Hardware Implementation of Deep Neural Networks Targeting FPGA-based Edge Devices 基于fpga边缘设备的深度神经网络硬件实现的资源和数据优化

2018 ACM/IEEE International Workshop on System Level Interconnect Prediction (SLIP) Pub Date : 2018-06-23 DOI: 10.1145/3225209.3225214

Xinheng Liu, Dae-Hee Kim, Chang Wu, Deming Chen

{"title":"Resource and Data Optimization for Hardware Implementation of Deep Neural Networks Targeting FPGA-based Edge Devices","authors":"Xinheng Liu, Dae-Hee Kim, Chang Wu, Deming Chen","doi":"10.1145/3225209.3225214","DOIUrl":"https://doi.org/10.1145/3225209.3225214","url":null,"abstract":"Recently, as machine learning algorithms have become more practical, there has been much effort to implement them on edge devices that can be used in our daily lives. However, unlike server-scale devices, edge devices are relatively small and thus have much more limited resources. Therefore, control of resource usage and hardware optimization play an important role when we implement machine learning algorithms on an edge device. In this paper, we target convolutional neural networks (CNN) and explore various optimization and design techniques to realize them on FPGA devices. The key idea explored in this paper is Backward Pipeline Scheduling together with Latency Balancing which optimize the pipeline between CNN layers in order to significantly reduce the overall latency for processing a single image. We also develop a batch processing design to improve the throughput of the FPGA solution. We have achieved latency of 175.7µs for classifying one image in the MNIST data set using LeNet and 653.4µs for classifying one image in Cifar-10 data set using CifarNet. Without retraining, we are still able to maintain high accuracy of 97.6% for MNIST data set and 83.6% for the Cifar-10 data set. Our achieved single- image latency is 5.2x faster for LeNet and 1.95x faster for CifarNet compared to the NVIDIA Jetson TX1 solution.","PeriodicalId":185773,"journal":{"name":"2018 ACM/IEEE International Workshop on System Level Interconnect Prediction (SLIP)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125128996","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 11

Exploiting PDN Noise to Thwart Correlation Power Analysis Attacks in 3D ICs 利用PDN噪声阻止3D集成电路中的相关功率分析攻击

2018 ACM/IEEE International Workshop on System Level Interconnect Prediction (SLIP) Pub Date : 2018-06-23 DOI: 10.1145/3225209.3225212

Jaya Dofe, Qiaoyan Yu

引用次数: 11

A Design Framework for Processing-In-Memory Accelerator 内存处理加速器的设计框架

2018 ACM/IEEE International Workshop on System Level Interconnect Prediction (SLIP) Pub Date : 2018-06-23 DOI: 10.1145/3225209.3225213

Di Gao, Tianhao Shen, Cheng Zhuo

引用次数: 6

Fast and Precise Routability Analysis with Conditional Design Rules 基于条件设计规则的快速精确可达性分析

2018 ACM/IEEE International Workshop on System Level Interconnect Prediction (SLIP) Pub Date : 2018-06-23 DOI: 10.1145/3225209.3225210

Ilgweon Kang, Dongwon Park, C. Han, Chung-Kuan Cheng

引用次数: 14

Adaptive Sensitivity Analysis with Nonlinear Power Load Modeling 非线性电力负荷模型的自适应灵敏度分析

2018 ACM/IEEE International Workshop on System Level Interconnect Prediction (SLIP) Pub Date : 2018-06-23 DOI: 10.1145/3225209.3225211

Po-Ya Hsu, Chun-Han Yao, Yuwei Wang, Chung-Kuan Cheng

引用次数: 0