发布求助
文献互助 智能选刊 最新文献

2020 57th ACM/IEEE Design Automation Conference (DAC)最新文献

筛选
英文 中文
FTDL: A Tailored FPGA-Overlay for Deep Learning with High Scalability FTDL:一种适合深度学习的高扩展性fpga覆盖
2020 57th ACM/IEEE Design Automation Conference (DAC) Pub Date : 2020-07-01 DOI: 10.1109/DAC18072.2020.9218581
Runbin Shi, Yuhao Ding, Xuechao Wei, He Li, Hang Liu, Hayden Kwok-Hay So, Caiwen Ding
{"title":"FTDL: A Tailored FPGA-Overlay for Deep Learning with High Scalability","authors":"Runbin Shi, Yuhao Ding, Xuechao Wei, He Li, Hang Liu, Hayden Kwok-Hay So, Caiwen Ding","doi":"10.1109/DAC18072.2020.9218581","DOIUrl":"https://doi.org/10.1109/DAC18072.2020.9218581","url":null,"abstract":"Fast inference is of paramount value to a wide range of deep learning applications. This work presents FTDL, a highly-scalable FPGA overlay framework for deep learning applications, to address the architecture and hardware mismatch faced by traditional efforts. The FTDL overlay is specifically optimized for the tiled structure of FPGAs, thereby achieving post-place-and-route operating frequencies exceeding 88 % of the theoretical maximum across different devices and design scales. A flexible compilation framework efficiently schedules matrix multiply and convolution operations of large neural network inference on the overlay and achieved over 80 % hardware efficiency on average. Taking advantage of both high operating frequency and hardware efficiency, FTDL achieves 402.6 and 151.2 FPS with GoogLeNet and ResNet50 on ImageNet, respectively, while operating at a power efficiency of 27.6 GOPS/W, making it up to 7.7 × higher performance and 1.9× more power-efficient than the state-of-the-art.","PeriodicalId":428807,"journal":{"name":"2020 57th ACM/IEEE Design Automation Conference (DAC)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124098955","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: 9
ReTriple: Reduction of Redundant Rendering on Android Devices for Performance and Energy Optimizations 重复:减少冗余渲染在Android设备的性能和能源优化
2020 57th ACM/IEEE Design Automation Conference (DAC) Pub Date : 2020-07-01 DOI: 10.1109/DAC18072.2020.9218517
Xianfeng Li, Gengchao Li, Xiaole Cui
{"title":"ReTriple: Reduction of Redundant Rendering on Android Devices for Performance and Energy Optimizations","authors":"Xianfeng Li, Gengchao Li, Xiaole Cui","doi":"10.1109/DAC18072.2020.9218517","DOIUrl":"https://doi.org/10.1109/DAC18072.2020.9218517","url":null,"abstract":"Graphics rendering is a compute-intensive work and a major source of energy consumption on battery-driven mobile devices. Unlike the existing works that degrade user experience or reuse rendering results coarsely, we propose ReTriple, a fine-grained scheme to reduce rendering workload by reusing the past rendering results at the UI element level. This fine-grained reuse mechanism can explore more opportunities to reduce the workload of the rendering process and save energy. The experiments tested with popular apps show that ReTriple achieves an average speedup of 2.6x and per-frame energy saving of 32.3% for the rendering process while improving user experience.","PeriodicalId":428807,"journal":{"name":"2020 57th ACM/IEEE Design Automation Conference (DAC)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123485192","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: 3
Wafer Map Defect Patterns Classification using Deep Selective Learning 基于深度选择学习的晶圆图缺陷模式分类
2020 57th ACM/IEEE Design Automation Conference (DAC) Pub Date : 2020-07-01 DOI: 10.1109/DAC18072.2020.9218580
M. Alawieh, D. Boning, D. Pan
{"title":"Wafer Map Defect Patterns Classification using Deep Selective Learning","authors":"M. Alawieh, D. Boning, D. Pan","doi":"10.1109/DAC18072.2020.9218580","DOIUrl":"https://doi.org/10.1109/DAC18072.2020.9218580","url":null,"abstract":"With the continuous drive toward integrated circuits scaling, efficient yield analysis is becoming more crucial yet more challenging. In this paper, we propose a novel methodology for wafer map defect pattern classification using deep selective learning. Our proposed approach features an integrated reject option where the model chooses to abstain from predicting a class label when misclassification risk is high. Thus, providing a trade-off between prediction coverage and misclassification risk. This selective learning scheme allows for new defect class detection, concept shift detection, and resource allocation. Besides, and to address the class imbalance problem in the wafer map classification, we propose a data augmentation framework built around a convolutional auto-encoder model for synthetic sample generation. The efficacy of our proposed approach is demonstrated on the WM-811k industrial dataset where it achieves 94% accuracy under full coverage and 99% with selective learning while successfully detecting new defect types.","PeriodicalId":428807,"journal":{"name":"2020 57th ACM/IEEE Design Automation Conference (DAC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121896576","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: 25
Late Breaking Results: Pole-aware Analog Placement Considering Monotonic Current Flow and Crossing-Wire Minimization 迟断结果:考虑单调电流和交叉线最小化的极感知模拟放置
2020 57th ACM/IEEE Design Automation Conference (DAC) Pub Date : 2020-07-01 DOI: 10.1109/DAC18072.2020.9218634
Abhishek Patyal, Hung-Ming Chen, Mark Po-Hung Lin
{"title":"Late Breaking Results: Pole-aware Analog Placement Considering Monotonic Current Flow and Crossing-Wire Minimization","authors":"Abhishek Patyal, Hung-Ming Chen, Mark Po-Hung Lin","doi":"10.1109/DAC18072.2020.9218634","DOIUrl":"https://doi.org/10.1109/DAC18072.2020.9218634","url":null,"abstract":"This paper presents a new paradigm for analog placement, which further incorporates poles in addition to the considerations of symmetry-island and monotonic current flow while minimizing wire crossings. The nodes along the signal path in an analog circuit contribute to the poles, and the parasitics on these dominant poles can significantly limit the circuit performance. Although the monotonic placements introduced in the previous works can generate simpler routing topologies, the unawareness of poles, especially both dominant pole and the first non-dominant pole, and wire crossing among critical nets may result in the increase wire-load and performance degradation. Experimental results show that the proposed pole-aware analog placement method considering symmetry-island, monotonic current flow, and crossing-wire minimization results in much better solution quality in terms of circuit performance.","PeriodicalId":428807,"journal":{"name":"2020 57th ACM/IEEE Design Automation Conference (DAC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123531456","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: 1
Towards Purposeful Design Space Exploration of Heterogeneous CGRAs: Clock Frequency Estimation 面向异构CGRAs有目的的设计空间探索:时钟频率估计
2020 57th ACM/IEEE Design Automation Conference (DAC) Pub Date : 2020-07-01 DOI: 10.1109/DAC18072.2020.9218649
D. Wolf, Christoph Spang, C. Hochberger
{"title":"Towards Purposeful Design Space Exploration of Heterogeneous CGRAs: Clock Frequency Estimation","authors":"D. Wolf, Christoph Spang, C. Hochberger","doi":"10.1109/DAC18072.2020.9218649","DOIUrl":"https://doi.org/10.1109/DAC18072.2020.9218649","url":null,"abstract":"Coarse Grained Reconfigurable Arrays become increasingly popular. Besides research on scheduling algorithms and microarchitecture concepts, the use of heterogeneous structures can be a key approach to exploit their full potential. Unfortunately, a purposeful design space exploration of CGRAs is not trivial, since one needs to know the clock frequency of the resulting hardware implementation. This paper discusses challenges and a statistical approach to maximum clock frequency estimation of heterogeneous CGRAs with an irregular interconnect on FPGAs. The presented approach allows estimation with a maximum error of 8.8 - 17.4% and a mean error of only 1.9 - 4.6%.","PeriodicalId":428807,"journal":{"name":"2020 57th ACM/IEEE Design Automation Conference (DAC)","volume":"87 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131692258","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: 2
Deep Learning Multi-Channel Fusion Attack Against Side-Channel Protected Hardware 针对侧信道保护硬件的深度学习多信道融合攻击
2020 57th ACM/IEEE Design Automation Conference (DAC) Pub Date : 2020-07-01 DOI: 10.1109/DAC18072.2020.9218705
Benjamin Hettwer, Daniel Fennes, S. Leger, Jan Richter-Brockmann, Stefan Gehrer, T. Güneysu
{"title":"Deep Learning Multi-Channel Fusion Attack Against Side-Channel Protected Hardware","authors":"Benjamin Hettwer, Daniel Fennes, S. Leger, Jan Richter-Brockmann, Stefan Gehrer, T. Güneysu","doi":"10.1109/DAC18072.2020.9218705","DOIUrl":"https://doi.org/10.1109/DAC18072.2020.9218705","url":null,"abstract":"State-of-the-art hardware masking approaches like threshold implementations and domain-oriented masking provide a guaranteed level of security even in the presence of glitches. Although provable secure in theory, recent work showed that the effective security order of a masked hardware implementation can be lowered by applying a multi-probe attack or exploiting externally amplified coupling effects. However, the proposed attacks are based on an unrealistic adversary model (i.e. knowledge of masks values during profiling) or require complex measurement setup manipulations.In this work, we propose a novel attack vector that exploits location dependent leakage from several decoupling capacitors of a modern System-on-Chip (SoC) with 16 nm fabrication technology. We combine the leakage from different sources using a deep learning-based information fusion approach. The results show a remarkable advantage regarding the number of required traces for a successful key recovery compared to state-of-the-art profiled side-channel attacks. All evaluations are performed under realistic conditions, resulting in a real-world attack scenario that is not limited to academic environments.","PeriodicalId":428807,"journal":{"name":"2020 57th ACM/IEEE Design Automation Conference (DAC)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116505418","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: 3
FlexReduce: Flexible All-reduce for Distributed Deep Learning on Asymmetric Network Topology FlexReduce:用于非对称网络拓扑上分布式深度学习的灵活全约简
2020 57th ACM/IEEE Design Automation Conference (DAC) Pub Date : 2020-07-01 DOI: 10.1109/DAC18072.2020.9218538
Jinho Lee, Inseok Hwang, Soham Shah, Minsik Cho
{"title":"FlexReduce: Flexible All-reduce for Distributed Deep Learning on Asymmetric Network Topology","authors":"Jinho Lee, Inseok Hwang, Soham Shah, Minsik Cho","doi":"10.1109/DAC18072.2020.9218538","DOIUrl":"https://doi.org/10.1109/DAC18072.2020.9218538","url":null,"abstract":"We propose FlexReduce, an efficient and flexible all-reduce algorithm for distributed deep learning under irregular network hierarchies. With ever-growing deep neural networks, distributed learning over multiple nodes is becoming imperative for expedited training. There are several approaches leveraging the symmetric network structure to optimize the performance over different hierarchy levels of the network. However, the assumption of symmetric network does not always hold, especially in shared cloud environments. By allocating an uneven portion of gradients to each learner (GPU), FlexReduce outperforms conventional algorithms on asymmetric network structures, and still performs even or better on symmetric networks.","PeriodicalId":428807,"journal":{"name":"2020 57th ACM/IEEE Design Automation Conference (DAC)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129545680","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: 6
KFR: Optimal Cache Management with K-Framed Reclamation for Drive-Managed SMR Disks 基于k帧回收的驱动管理SMR磁盘的最优缓存管理
2020 57th ACM/IEEE Design Automation Conference (DAC) Pub Date : 2020-07-01 DOI: 10.1109/DAC18072.2020.9218636
Chenlin Ma, Yi Wang, Zhaoyan Shen, Z. Shao
{"title":"KFR: Optimal Cache Management with K-Framed Reclamation for Drive-Managed SMR Disks","authors":"Chenlin Ma, Yi Wang, Zhaoyan Shen, Z. Shao","doi":"10.1109/DAC18072.2020.9218636","DOIUrl":"https://doi.org/10.1109/DAC18072.2020.9218636","url":null,"abstract":"Shingled Magnetic Recording (SMR) disks have been proposed as a promising solution to satisfy the increasing capacity need in the big data era. Drive-Managed SMR (DM-SMR) disk which acts as a traditional block device is favored for providing high compatibility. However, DM-SMR disks suffer from high performance recovery time (PRT) due to the \"SMR space reclamation\" issue. This paper proposes an optimal cache management named K-Framed Reclamation (KFR) to minimize PRT within the DM-SMR disk. The effectiveness of our proposed design was evaluated with realistic and intensive I/O workloads and the results are encouraging.","PeriodicalId":428807,"journal":{"name":"2020 57th ACM/IEEE Design Automation Conference (DAC)","volume":"34 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131653368","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: 1
Hardware-assisted Service Live Migration in Resource-limited Edge Computing Systems 资源有限边缘计算系统中硬件辅助服务实时迁移
2020 57th ACM/IEEE Design Automation Conference (DAC) Pub Date : 2020-07-01 DOI: 10.1109/DAC18072.2020.9218677
Zhe Zhou, Xintong Li, Xiaoyang Wang, Zheng Liang, Guangyu Sun, Guojie Luo
{"title":"Hardware-assisted Service Live Migration in Resource-limited Edge Computing Systems","authors":"Zhe Zhou, Xintong Li, Xiaoyang Wang, Zheng Liang, Guangyu Sun, Guojie Luo","doi":"10.1109/DAC18072.2020.9218677","DOIUrl":"https://doi.org/10.1109/DAC18072.2020.9218677","url":null,"abstract":"Service live migration means migrating the running services from one machine to another with negligible service downtime. It has been considered as a powerful mechanism to facilitate service management. However, conventional live migration methods always come with expensive cost of data transmission, and thus can hardly be applied to a real-world edge computing system directly due to the limited network bandwidth. To tackle this problem, some recent works present various techniques to reduce the data transmission.However, these techniques for data transmission reduction always introduce extra computational costs, which have a great impact on the quality of service (QoS), especially in edge systems containing lots of nodes with insufficient computational resources. To alleviate this issue, we propose an insight to offload data reduction computations to a specific hardware accelerator, thus reducing the burden of CPU cores. To this end, we present a novel hardware accelerator design to speed up the data transmission reduction computations to accelerate the service live migration. For evaluation, we implement a prototype on an FPGA platform. Compared to the normal CPU-based approaches, our specialized accelerator is 3.1× faster, 2.9× more-energy efficient, and can reduce 29%∼47% of total migrating time and 24%∼40% of service downtime in our cases. Furthermore, our architecture has great scalability and is easy-configurable to achieve a balance between cost and performance.","PeriodicalId":428807,"journal":{"name":"2020 57th ACM/IEEE Design Automation Conference (DAC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130736899","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: 3
A Robust Exponential Integrator Method for Generic Nonlinear Circuit Simulation 一般非线性电路仿真的鲁棒指数积分法
2020 57th ACM/IEEE Design Automation Conference (DAC) Pub Date : 2020-07-01 DOI: 10.1109/DAC18072.2020.9218556
Quan Chen
{"title":"A Robust Exponential Integrator Method for Generic Nonlinear Circuit Simulation","authors":"Quan Chen","doi":"10.1109/DAC18072.2020.9218556","DOIUrl":"https://doi.org/10.1109/DAC18072.2020.9218556","url":null,"abstract":"In this paper, we aim to address two long-lasting issues in large scale transient circuit simulation using the exponential integrator (EI) method. First is the numerical instability caused by the singularity in the differential-algebraic equation system. Our proposed solution is a systematic, algebraic and sparsity preserving regularization technique to eliminate the unstable modes in the system to be solved. Next, we devise a generic scheme to apply Newton-Raphson iterations in the EI framework for enhanced nonlinearity handling capability. With the two techniques, we wish to elevate the robustness and performance of EI and make it a competitive alternative to the existing SPICE-type simulators in practical usage.","PeriodicalId":428807,"journal":{"name":"2020 57th ACM/IEEE Design Automation Conference (DAC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134423917","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: 3
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信