2018 Ninth International Green and Sustainable Computing Conference (IGSC)最新文献_第3页

Towards Design Decisions for Genetic Algorithms in Clock Tree Synthesis 为时钟树合成中的遗传算法制定设计决策

2018 Ninth International Green and Sustainable Computing Conference (IGSC) Pub Date : 2018-10-01 DOI: 10.1109/IGCC.2018.8752170

Scott Lerner, B. Taskin

引用次数: 0

DiRP: Distributed Intelligent Rendezvous Point for Multicast Control Plane DiRP:多播控制平面分布式智能集合点

2018 Ninth International Green and Sustainable Computing Conference (IGSC) Pub Date : 2018-10-01 DOI: 10.1109/IGCC.2018.8752124

Ammar Latif, Roshini Paul, Rishi Chhibber, Anand Singh, Rahul Parameswaran, Abdallah Khreishah, Y. Jararweh

{"title":"DiRP: Distributed Intelligent Rendezvous Point for Multicast Control Plane","authors":"Ammar Latif, Roshini Paul, Rishi Chhibber, Anand Singh, Rahul Parameswaran, Abdallah Khreishah, Y. Jararweh","doi":"10.1109/IGCC.2018.8752124","DOIUrl":"https://doi.org/10.1109/IGCC.2018.8752124","url":null,"abstract":"Multicast is widely deployed in data centers for point-to-multi-point communications. It has an established set of control protocols such as IGMP and PIM that has limitations around the lack of bandwidth awareness when establishing the multicast trees. This could lead to over-subscription of network links and packet loss impacting user quality of experience. Other existing multicast issues are related to path setup time as delay translates to deterioration of user experience. In this paper, we present and implement the DiRP algorithm utilizing distributed decision making architecture to optimize multicast tree formation while maintaining low path setup time. The system is implemented using off-the-shelve commercially available switches. the proposed DiRP algorithm maintains the creation and removal of source trees based on bandwidth requirements. We test the algorithm using Cisco’s Nexus commercially available switches. Testing results confirm that the DiRP Algorithm is able to setup multicast tree paths based on available bandwidth while maintaining distributed decision making in the fabric to lower path setup time. The system offers substantially lower path setup time compared to centralized systems while maintaining bandwidth awareness when setting up the fabric.","PeriodicalId":388554,"journal":{"name":"2018 Ninth International Green and Sustainable Computing Conference (IGSC)","volume":"234 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115752603","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: 0

IGSC 2018 PhD Workshop on Power/Energy Management at Extreme Scale IGSC 2018极端规模下的电力/能源管理博士研讨会

2018 Ninth International Green and Sustainable Computing Conference (IGSC) Pub Date : 2018-10-01 DOI: 10.1109/igcc.2018.8752166

引用次数: 0

GreenWeb: Hosting High-Load Websites Using Low-Power Servers GreenWeb:使用低功耗服务器托管高负载网站

2018 Ninth International Green and Sustainable Computing Conference (IGSC) Pub Date : 2018-10-01 DOI: 10.1109/IGCC.2018.8752138

Brad Everman, Ziliang Zong

引用次数: 1

Dark Silicon Considered Harmful: A Case for Truly Green Computing 被认为有害的暗硅:一个真正绿色计算的案例

2018 Ninth International Green and Sustainable Computing Conference (IGSC) Pub Date : 2018-10-01 DOI: 10.1109/IGCC.2018.8752110

E. Brunvand, Donald Kline, A. Jones

{"title":"Dark Silicon Considered Harmful: A Case for Truly Green Computing","authors":"E. Brunvand, Donald Kline, A. Jones","doi":"10.1109/IGCC.2018.8752110","DOIUrl":"https://doi.org/10.1109/IGCC.2018.8752110","url":null,"abstract":"As individuals and researchers approach the challenge of green computing it is natural to consider the energy consumption of computational devices and their supporting systems during their use phase (i.e., after they are deployed into service). However, for computing to be truly green, all phases of the system life-cycle, from manufacturing to disposal, must be considered. In particular there is limited awareness to the considerable fraction of the total life-cycle environmental impacts of computing systems that result from the fabrication of the integrated circuits (ICs) that are used in those devices. Ironically, the trend toward dark silicon accelerators, often targeted at improving operational energy efficiency, may be counterproductive for holistic energy reduction of computing systems. The increased chip area that results from a large percentage of dark silicon may exacerbate the fabrication impacts to the point that overall sustainability is actually decreased. In this paper, we explore some properties of manufacturing and operational energy efficiency and make a case that truly green computing must carefully consider the tradeoffs involved.","PeriodicalId":388554,"journal":{"name":"2018 Ninth International Green and Sustainable Computing Conference (IGSC)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122465794","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: 12

A Case Study of Complementary-multiply-with-carry Method on OpenCL FPGA 基于OpenCL FPGA的补乘进位方法实例研究

2018 Ninth International Green and Sustainable Computing Conference (IGSC) Pub Date : 2018-10-01 DOI: 10.1109/IGCC.2018.8752144

Zheming Jin, H. Finkel

引用次数: 0

Holistic Approaches to HPC Power and Workflow Management* HPC电源和工作流管理的整体方法*

2018 Ninth International Green and Sustainable Computing Conference (IGSC) Pub Date : 2018-10-01 DOI: 10.1109/IGCC.2018.8752150

A. Purkayastha, S. Hammond, Ramkumar Nagappan, M. Alt

引用次数: 1

IGSC 2018 PhD Forum IGSC 2018博士论坛

2018 Ninth International Green and Sustainable Computing Conference (IGSC) Pub Date : 2018-10-01 DOI: 10.1109/igcc.2018.8752118

引用次数: 0

PowerCoord: A Coordinated Power Capping Controller for Multi-CPU/GPU Servers PowerCoord:用于多cpu /GPU服务器的协调功率封顶控制器

2018 Ninth International Green and Sustainable Computing Conference (IGSC) Pub Date : 2018-10-01 DOI: 10.1109/IGCC.2018.8752132

R. Azimi, Chao Jing, S. Reda

{"title":"PowerCoord: A Coordinated Power Capping Controller for Multi-CPU/GPU Servers","authors":"R. Azimi, Chao Jing, S. Reda","doi":"10.1109/IGCC.2018.8752132","DOIUrl":"https://doi.org/10.1109/IGCC.2018.8752132","url":null,"abstract":"Modern supercomputers and cloud providers rely on server nodes that are equipped with multiple CPU sockets and general purpose GPUs (GPGPUs) to handle the high demand for intensive computations. These servers consume much higher power than commodity servers, and integrating them with power capping systems used in modern clusters presents new challenges. In this paper, we propose a new power capping controller, PowerCoord, that is specifically designed for servers with multiple CPU and GPU sockets that are running multiple jobs at a time. PowerCoord coordinates among the various power domains (e.g., CPU sockets and GPUs) inside a server to meet target power caps, while seeking to maximize throughput. Our approach also takes into consideration job deadlines and priorities. Because performance modeling for co-located jobs is error-prone, PowerCoord uses a learning method to adapt to various workloads. PowerCoord has a number of heuristic policies to allocate power among the various CPUs and GPUs, and it uses reinforcement learning to select the best policy during runtime. Based on the observed state of the system, PowerCoord shifts the distribution of selected policies. We implement our power cap controller on a real multi-CPU/GPU server with low overhead, and we demonstrate that it is able to meet target power caps while maximizing the throughput, and balancing other demands such as priorities and deadlines. Compared to prior published techniques, our results show that PowerCoord improves the throughput by an average of 14.4% under power caps.","PeriodicalId":388554,"journal":{"name":"2018 Ninth International Green and Sustainable Computing Conference (IGSC)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125788127","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: 8

IGSC 2018 PhD Workshop on Energy- efficient Networks of Computers (E2NC): From the Chip to the Cloud IGSC 2018节能计算机网络(E2NC)博士研讨会:从芯片到云

2018 Ninth International Green and Sustainable Computing Conference (IGSC) Pub Date : 2018-10-01 DOI: 10.1109/igcc.2018.8752116

引用次数: 0