2017 Eighth International Green and Sustainable Computing Conference (IGSC)最新文献_第3页

Dynamic energy and reliability management in network-on-chip based chip multiprocessors 基于片上网络的多处理器动态能量与可靠性管理

2017 Eighth International Green and Sustainable Computing Conference (IGSC) Pub Date : 2017-10-01 DOI: 10.1109/IGCC.2017.8323594

M. Moghaddam

引用次数: 5

Holistic energy efficient crosstalk mitigation in DRAM DRAM中整体节能串扰缓解

2017 Eighth International Green and Sustainable Computing Conference (IGSC) Pub Date : 2017-10-01 DOI: 10.1109/IGCC.2017.8323590

A. Jones, R. Melhem, Donald Kline

引用次数: 3

Understanding the role of memory subsystem on performance and energy-efficiency of Hadoop applications 了解内存子系统在Hadoop应用程序性能和能效方面的作用

2017 Eighth International Green and Sustainable Computing Conference (IGSC) Pub Date : 2017-10-01 DOI: 10.1109/IGCC.2017.8323591

Hosein Mohammadi Makrani, Shahab Tabatabaei, S. Rafatirad, H. Homayoun

{"title":"Understanding the role of memory subsystem on performance and energy-efficiency of Hadoop applications","authors":"Hosein Mohammadi Makrani, Shahab Tabatabaei, S. Rafatirad, H. Homayoun","doi":"10.1109/IGCC.2017.8323591","DOIUrl":"https://doi.org/10.1109/IGCC.2017.8323591","url":null,"abstract":"The memory subsystem has always been one of the performance bottlenecks in computer systems. Given the large size of data, therefore, the questions of whether Big Data requires big memory and whether main memory subsystem plays an intrinsic role in the performance and energy-efficiency of Big Data are becoming important. In this paper, through a comprehensive real-system experimental analysis of performance, power and resource utilization, we have evaluated main memory characteristic of Hadoop MapReduce, a de facto standard for big data analytics. Through a methodical experimental setup we have analyzed the impact of DRAM capacity, operating frequency, and the number of channels on power and performance to understand the main memory requirements of this important Big Data framework. The characterization results across various Hadoop MapReduce applications from different domains illustrate that Hadoop MapReduce workloads show two distinct behaviors of being either CPU-intensive or Disk-intensive. Our experimental results showed that DRAM frequency as well as number of channels do not play a significant role on the performance of Hadoop workloads. On the other hand, our results indicate that increasing the number of DRAM channels reduces DRAM power and improves the energy-efficiency of Hadoop MapReduce applications.","PeriodicalId":133239,"journal":{"name":"2017 Eighth International Green and Sustainable Computing Conference (IGSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125757444","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: 14

Sustainable fault management and error correction for next-generation main memories 下一代主存储器的可持续性故障管理和纠错

2017 Eighth International Green and Sustainable Computing Conference (IGSC) Pub Date : 2017-10-01 DOI: 10.1109/IGCC.2017.8323584

Donald Kline, R. Melhem, A. Jones

{"title":"Sustainable fault management and error correction for next-generation main memories","authors":"Donald Kline, R. Melhem, A. Jones","doi":"10.1109/IGCC.2017.8323584","DOIUrl":"https://doi.org/10.1109/IGCC.2017.8323584","url":null,"abstract":"As technology nodes continue to scale, main memories experience both increasing energy consumption as well as reliability challenges. In order to address rising failure rates due to problems with yield and runtime effects, such as crosstalk, due to process variation in small feature sizes, improved correction capabilities at the bit-level are increasingly essential. To address this challenge, we propose a sustainable approach to error correction in deeply scaled memories. In particular, we propose a novel area-efficient and sustainable fault map (SFaultMap) which targets holistic energy considerations to improve reliability while minimizing both operational and embodied energy. To demonstrate the effectiveness of SFaultMap we conduct a sustain-ability study, based on holistic energy consumption, to evaluate under which scenarios different solutions should be employed. In all cases and scenarios with moderate to high fault rates, SFaultMap has reduced energy over Error Correcting Pointers (ECP) for a five year lifetime. Moreover, as fault rate increases, the indifference time for ECP to recover upfront manufacturing energy increases from years to decades.","PeriodicalId":133239,"journal":{"name":"2017 Eighth International Green and Sustainable Computing Conference (IGSC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123032836","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: 17

Understanding the impact of object oriented programming and design patterns on energy efficiency 了解面向对象编程和设计模式对能源效率的影响

2017 Eighth International Green and Sustainable Computing Conference (IGSC) Pub Date : 2017-10-01 DOI: 10.1109/IGCC.2017.8323605

Sepideh Maleki, Cuijiao Fu, Arun Banotra, Ziliang Zong

引用次数: 12

Selective checkpointing for minimizing recovery energy and efforts of smartphone apps 选择性检查点，最大限度地减少智能手机应用程序的恢复能量和努力

2017 Eighth International Green and Sustainable Computing Conference (IGSC) Pub Date : 2017-10-01 DOI: 10.1109/IGCC.2017.8323571

Li Li, Yunhao Bai, Xiaorui Wang, Mai Zheng, Feng Qin

{"title":"Selective checkpointing for minimizing recovery energy and efforts of smartphone apps","authors":"Li Li, Yunhao Bai, Xiaorui Wang, Mai Zheng, Feng Qin","doi":"10.1109/IGCC.2017.8323571","DOIUrl":"https://doi.org/10.1109/IGCC.2017.8323571","url":null,"abstract":"Unintended smartphone rebooting and unexpected shutdown (due to reasons like battery run outs, overheating, or automatic app upgrades) is annoying. What can be even worse is that a phone user has to restart, from the very beginning, the apps he or she was using when the phone got rebooted, because all the app states would be lost, especially when the number of apps in use is large. Hence, a recovery service is sorely needed for today's smartphones where apps are becoming increasingly complex. While checkpointing has long been used for desktop and laptop computers, such whole-system state preserving techniques cannot be applied to smartphones directly, due to the constraints of smartphones on energy, delay, and storage space. In this paper, we propose SmartCP, an intelligent checkpointing methodology, in order to reduce the energy required by a smartphone and the amount of efforts required by a user to recover the app states after the smartphone restarts. SmartCP selectively checkpoints the most important apps based on the apps' characteristics and predicted future usage, under the resource constraints of the phone. We propose a novel model that quantitatively analyzes the recovery energy and efforts of each category of smartphone apps and formulate selective checkpointing as a constrained optimization problem. We prototype SmartCP on Android and evaluate it using real-world traces as well as real user feedback. The results show that SmartCP outperforms two alternative app selection schemes by saving 28% more energy and 39% more recovery efforts on average.","PeriodicalId":133239,"journal":{"name":"2017 Eighth International Green and Sustainable Computing Conference (IGSC)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134478598","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

Architecture independent integrated early performance and energy estimation 独立于架构的集成早期性能和能量评估

2017 Eighth International Green and Sustainable Computing Conference (IGSC) Pub Date : 2017-10-01 DOI: 10.1109/IGCC.2017.8323602

Antonino Tumeo

{"title":"Architecture independent integrated early performance and energy estimation","authors":"Antonino Tumeo","doi":"10.1109/IGCC.2017.8323602","DOIUrl":"https://doi.org/10.1109/IGCC.2017.8323602","url":null,"abstract":"The end of Dennard's scaling, coupled with the necessity to keep increasing computational performance in constrained power envelopes, is leading developers towards the need to optimize applications not only for performance, but also for energy consumption. In such a scenario, solutions that enable estimating performance and energy consumption of a program as early as possible, even during development and without the necessity to access the final target hardware, can become fundamental tools to reduce the design space, the optimization effort, and provide potential opportunities to automate the optimization process itself. In this position paper, we discuss the design of a performance and energy estimation framework based on a retargetable compiler. Our proposed approach targets the Intermediate Representation (IR) of the LLVM compiler. The IR based approach enables, after a model is built, estimation from a host different from the target architecture, even considering dynamic information. We present the rationale behind such a framework, identify opportunities and components readily available (such as static analysis, quick ways to add instrumentation for dynamic profiling, and the multiple backends), and aspects that still need further research efforts (such as more effective non-linear, or machine learning based models). We also discuss a hand-developed case study, based on a simple sparse matrix vector multiplication with a linear model, to motivate the needs for such a framework.","PeriodicalId":133239,"journal":{"name":"2017 Eighth International Green and Sustainable Computing Conference (IGSC)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126171579","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

Optimizing checkpoint intervals for reduced energy use in exascale systems 优化检查点间隔，以减少百亿亿级系统的能源使用

2017 Eighth International Green and Sustainable Computing Conference (IGSC) Pub Date : 2017-10-01 DOI: 10.1109/IGCC.2017.8323598

D. Dauwe, Rohan Jhaveri, S. Pasricha, A. A. Maciejewski, H. Siegel

{"title":"Optimizing checkpoint intervals for reduced energy use in exascale systems","authors":"D. Dauwe, Rohan Jhaveri, S. Pasricha, A. A. Maciejewski, H. Siegel","doi":"10.1109/IGCC.2017.8323598","DOIUrl":"https://doi.org/10.1109/IGCC.2017.8323598","url":null,"abstract":"In today's high performance computing (HPC) systems, the probability of applications experiencing failures has increased significantly with the increase in the number of system nodes. It is expected that exascale-sized systems are likely to operate with mean time between failures (MTBF) of as little as a few minutes, causing frequent interrupts in application execution as well as substantially greater energy costs in a system that will already consume large amounts of energy. State-of-the-art HPC resilience techniques proposed for use in these future systems complicate the energy problem further as the overhead associated with utilizing these techniques also further increases energy use. While work has been done that attempts to analyze and improve the energy use of systems utilizing resilience techniques, our work offers a new approach through the optimization of checkpoint interval lengths that allows a system designer the freedom to choose between intervals that optimize for application performance efficiency or energy use in both a traditional checkpoint and multilevel checkpoint approach to resilience. We create a set of equations able to optimize for either performance efficiency or energy use, demonstrate that distinct intervals exist when optimizing for either one metric or the other, and examine the sensitivity of this phenomena to changes in several system parameters and application characteristics.","PeriodicalId":133239,"journal":{"name":"2017 Eighth International Green and Sustainable Computing Conference (IGSC)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116571600","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: 18

Power and energy implications of misunderstanding DRAM 误解DRAM的功率和能量含义

2017 Eighth International Green and Sustainable Computing Conference (IGSC) Pub Date : 2017-10-01 DOI: 10.1109/IGCC.2017.8323589

D. Kopta, E. Brunvand

引用次数: 0

Energy-efficient primary/backup scheduling techniques for heterogeneous multicore systems 异构多核系统的节能主备调度技术

2017 Eighth International Green and Sustainable Computing Conference (IGSC) Pub Date : 2017-10-01 DOI: 10.1109/IGCC.2017.8323569

A. Roy, Hakan Aydin, Dakai Zhu

引用次数: 9