功耗受限情况下多核处理器能效优化方案

将处理器功耗控制在预算以下有助于降低散热成本和提升系统稳定性,但现有功耗优化方案大多依赖线下分析得到的先验知识,影响实用性,而集中式搜索最优策略的算法也存在复杂度过高的问题。为此,提出功耗优化方案PPCM。利用动态电压频率调整(DVFS)技术控制CPU功耗在预算内以提高处理器能效。同时,将功耗控制和功耗分配解耦合以提高灵活性。采用动态调整的线性模型估计功耗,通过反馈控制技术对其进行调节。以计算访存比为指标在应用间分配功耗,并考虑多线程应用特征进行线程间功耗分配。实验结果表明,PPCM比Priority算法速度平均提高10.7%,能耗平均降低5.1%,能量-延迟积平均降低14.3%。与PCM CA算法相比,其速度平均提高4.5%,能量-延迟积平均降低5.0%。     

基于CPUfreq的DVFS节能技术的研究与实现

针对目前计算机系统普遍存在的功耗较大的问题,研究和实现了基于CPUfreq的DVFS节能软件;首先,分析和比较了计算机系统现有主要的功耗管理框架;然后,阐述了CPUfreq子系统及其框架结构,并基于CPUfreq子系统开发了DVFS节能软件,实现了对计算机CPU的动态电压频率调节(DVFS);最后,以720 p视频播放为应用实例,对使用DVFS节能软件后的计算机系统进行功耗测试;测试结果表明,DVFS节能软件可以实现对以PC为代表的计算机系统的初步节能。     

商用处理器上针对能耗优化的DVFS调节机制

针对动态电压频率调节(DVFS)对应用程序运行时性能与功耗的影响,基于区间划分方法,使用现有商用处理器提供的性能监测单元,提出一种考虑访存延迟变化的DVFS性能预测模型,并利用该模型实现针对能耗优化的DVFS调节机制(eDVFS)。实验结果表明,与Linux内核提供的ondemand调节策略相比,该eDVFS调节机制能够获得最大23%、平均6.85%的能耗优化。     

基于任务行为分析的DVFS机制

动态电压频率缩放（DVFS）技术是当前最有效的功耗调节手段之一．本文首先分析现有DVFS技术存在的不足,指出限制DVFS技术高效运用的核心因素;基于现有低效的方式我们提出一种基于任务行为分析的DVFS机制（TC-DVFS）．其具有三个层次：一、采集任务的系统调用信息;二、识别任务的关键系统调用,并以关键系统调用刻画任务行为;三、根据任务行为构建特征库,并以任务的特征库来指导DVFS．我们将TC-DVFS添加到linux内核中,并在intel-core2处理器平台上对不同类型的应用任务进行性能与功耗测试．结果显示TC-DVFS总体获得10％的性能提升,并降低5％调频失效率和5％的系统能耗．     

云计算环境下软硬件节能和负载均衡策略

针对云计算服务环境下软硬件节能和负载均衡优化问题,提出一种自适应的云计算环境下虚拟机(VM)动态迁移软节能策略。该策略采用常用的硬件能耗感知技术——动态电压频率调节(DVFS)来实现分段优化的系统部件静态节能,又通过VM在线迁移技术实现云平台的动态自适应软件节能。在CloudSim云仿真平台下对比实现DVFS静态节能和自适应负载均衡的软节能策略,经PlanetLab云平台监测数据验证,结果表明：软硬结合的自适应能耗感知策略能够高效节能96%; DVFS+MAD_MMT节能策略(采用平均绝对偏差算法判定主机是否超载,基于最短迁移时间(MMT)原则选择VM移出)     

基于DVFS感知与虚拟机动态合并的云数据中心能效策略

为了解决云数据中心资源分配时能耗与性能间的均衡问题,提出了一种基于DVFS感知与虚拟机动态合并的能效优化策略。首先,策略通过新的DVFS管理算法（DVFS-perf）在不降低系统性能的同时降低了数据中心功耗,然后,通过频率感知的虚拟机VM部署合并算法（Frequency-aware Placement）在实现DVFS最优配置的同时最小化总体能耗,同时确保了虚拟机映射时的QoS保障。最后,通过真实云负载数据流构建仿真实验进行了性能分析。结果表明,在动态负载条件下,策略可以在不降低QoS和不增加SLA违例的情况下,降低虚拟机迁移次数和数据中心的总体能耗,更好地实现能耗与性能的均衡。     

基于线性预测的移动终端LPDVFS策略

针对以Linux为内核的移动操作系统,提出一种细粒度的DVFS策略LPDVFS。该策略基于历史数据,使用线性预测的方法,指导电压频率调整方向和幅度。线性预测中的参数通过回归方法确定。实验结果表明,LPDVFS策略相比Linux内核默认使用的粗粒度调频策略,能降低系统13.55%的功耗,延长移动终端的续航时间。     

在异构系统上基于权重和复制的调度算法

动态电压和频率扩展技术（DVFS）的发展使异构系统可以实现低功耗，然而DVFS通过降低处理器的执行频率来降低功耗，大大增加了处理器临时故障风险，应用的可靠性受到极大威胁。针对先前算法在任务调度过程中容易出现调度失败的问题，提出一种基于权重和复制的调度算法（SAWR），以在异构系统上完成应用调度，满足并行应用的可靠性目标，同时降低系统功耗。仿真结果表明，与先前的算法相比，所提算法可以实现良好的性能。     

云计算数据中心可扩展服务器节能优化研究

摘要：云计算数据中心越来越庞大,硬件规模也日益增大,而且还会有大量的计算资源、存储资源会出现在云端,促使出现了一大批十万级、百万级、乃至千万级服务器的数据中心,且服务器还可以增量扩展与增量部署,高能耗问题已经日益凸显,严重制约到云计算数据中心的可持续性发展。本文提出了一种新型的云计算数据中心可扩展服务器节能优化策略——效能优化策略,能够基于全局角度来降低能源消耗,优化服务器选择过程,并且还可促使不同服务器之间实现负载均衡。仿真实验结果表明：基于能耗大小来看,本文提出的效能优化策略要比DVFS策略、无迁移策略所对应的能耗分别节约15.23%、24.33%;基于迁移数来看,本文提出的效能优化策略要比DVFS策略所对应的迁移次数减少2425次,总之,本文提出的效能优化策略总体而言要明显比DVFS策略、无迁移策略更优越。     

高效能多核处理器芯片功耗测试及其DVFS调度算法研究

针对处理器纳米级工艺快速发展，使高效能多核处理器芯片上集成晶体管，进而导致高效能多核处理芯片功耗大幅增加的问题，研究设计了一种双阈值功耗自适应的DVFS调度算法。该算法采用两级阈值调节配合功耗自适应实现了对高效能多核处理器的功耗优化，相较于传统的单阈值调节方式，该算法调节CPU的方式更科学有效。在大部分测试程序中，该算法的性能可保持在90%以上，最大功耗优化比例可达到35%以上。     

User-Driven Frequency Scaling

We propose and evaluate user-driven frequency scaling (UDFS) for improved power management on processors that support dynamic voltage and frequency scaling (DVFS), e.g, those used in current laptop and desktop computers. UDFS dynamically adapts CPU frequency to the individual user and the workload through a simple user feedback mechanism, unlike currently-used DVFS methods which rely only on CPU utilization. Our UDFS algorithms dramatically reduce typical operating frequencies while maintaining performance at satisfactory levels for each user. We evaluated our techniques through user studies conducted on a Pentium M laptop running Windows applications. The UDFS scheme reduces measured system power by 22.1%, averaged across all our users and applications, compared to the Windows XP DVFS scheme     

Managing power constraints in a single-core scenario through power tokens

Current microprocessors face constant thermal and power-related problems during their everyday use, usually solved by applying a power budget to the processor/core. Dynamic voltage and frequency scaling (DVFS) has been an effective technique that allowed microprocessors to match a predefined power budget. However, the continuous increase of leakage power due to technology scaling along with low resolution of DVFS makes it less attractive as a technique to match a predefined power budget as technology goes to deep-submicron. In this paper, we propose the use of microarchitectural techniques to accurately match a power constraint while maximizing the energy-efficiency of the processor. We will predict the processor power dissipation at cycle level (power token throttling) or at a basic block level (basic block level mechanism), using the dissipated power translated into tokens to select between different power-saving microarchitectural techniques. We also introduce a two-level approach in which DVFS acts as a coarse-grain technique to lower the average power dissipation towards the power budget, while microarchitectural techniques focus on removing the numerous power spikes. Experimental results show that the use of power-saving microarchitectural techniques in conjunction with DVFS is up to six times more precise, in terms of total energy consumed over the power budget, than only using DVFS to match a predefined power budget.     

PostgreSQL数据库在不同调节器中的能效比较

近年来,能效数据库系统成为数据库领域的一个研究议题.CPU动态电压频率调节(DVFS)是一种有效的动态功率节能技术.探寻PostgreSQL数据库在ACPI不同调节器下查询操作的性能、能耗、功率之间潜在联系,发现动态功耗管理与数据库系统的能效关系,通过运行TPC-H测试基准生成的数据库与相应22个查询,总结出调节器对数据库查询处理各种操作的影响.实验结果表明,DVFS可以对DBMS进行动态功耗管理是有效的,查询处理的不同操作具有各自特性,利用这些特性来设计效率更高的调节器是颇有前途的.     

Energy minimization for reliability-guaranteed real-time applications using DVFS and checkpointing techniques

This paper addresses the energy minimization issue when executing real-time applications that have stringent reliability and deadline requirements. To guarantee the satisfaction of the application’s reliability and deadline requirements, checkpointing, Dynamic Voltage Frequency Scaling (DVFS) and backward fault recovery techniques are used. We formally prove that if using backward fault recovery, executing an application with a uniform frequency or neighboring frequencies if the desired frequency is not available, not only consumes the minimal energy but also results in the highest system reliability. Based on this theoretical conclusion, we develop a strategy that utilizes DVFS and checkpointing techniques to execute real-time applications so that not only the applications reliability and deadline requirements are guaranteed, but also the energy consumption for executing the applications is minimized. The developed strategy needs at most one execution frequency change during the execution of an application, hence, the execution overhead caused by frequency switching is small, which makes the strategy particularly useful for processors with a large frequency switching overhead. We empirically compare the developed real-time application execution strategy with recently published work. The experimental results show that, without sacrificing reliability and deadline satisfaction guarantees, the proposed approach can save up to 12% more energy when compared with other approaches.     

Energy-centric DVFS controlling method for multi-core platforms

Dynamic voltage and frequency scaling (DVFS) is a well-known and effective technique for reducing energy consumption in modern processors. However, accurately predicting the effect of frequency scaling on system performance is a challenging problem in real environments. In this paper, we propose a realistic DVFS performance prediction method, and a practical DVFS control policy (eDVFS) that aims to minimize total energy consumption in multi-core platforms. We also present power consumption estimation models for CPU and DRAM by exploiting a hardware energy monitoring unit. We implemented eDVFS in Linux, and our evaluation results show that eDVFS can save a substantial amount of energy compared with Linux “on-demand” CPU governor in diverse environments.     

面向云计算中心效能优化的负载平衡方法

为了提升使用虚拟化技术的数据中心的能耗利用率,根据处理器DVFS(dynamic voltage and frequency scaling)变频技术的功耗特性,论证了在理想情况下,数据中心中所有处理器频率一致时能耗利用率最高;基于这一理论,提出了云计算中心的负载平衡方法;最后在CloudSim中进行了仿真实验,实验结果显示该方法能够优化数据中心的能耗。     

面向高性能业务应用的基于剖视信息的系统能耗优化

当前,很多部门使用高性能计算机周期性地进行业务性的数值计算。维护这些业务系统的主要代价是每天消耗的大量电能,降低能量消耗能够极大地降低维护业务系统的成本。高性能业务系统的核心是微处理器,当前,微处理器普遍支持动态电压调节技术。该技术通过降低微处理器的电压和频率减小微处理器的能耗,但是一般会导致系统性能的下降。提出了一种面向高性能业务应用的能量优化技术。该技术利用系统支持的多个频率层次,建立性能约束下的能量优化模型,优化业务应用的能耗。根据程序信息获取方式的差别,提出了SEOM 和 CEOM 两种能量优化模型,SEOM模型的程序信息可以直接测试获取,CEOM的程序信息采用编译器插桩方法获取。使用典型平台对能耗优化效果进行了验证,最多可节省12%的能耗。     

Exploiting primary/backup mechanism for energy efficiency in dependable real-time systems

Primary/Backup has been well studied as an effective fault-tolerance technique. In this paper, with the objectives of tolerating a single permanent fault and maintaining system reliability with respect to transient faults, we study dynamic-priority based energy-efficient fault-tolerance scheduling algorithms for periodic real-time tasks running on multiprocessor systems by exploiting the primary/backup technique while considering the negative effects of the widely deployed Dynamic Voltage and Frequency Scaling (DVFS) on transient faults. Specifically, by separating primary and backup tasks on their dedicated processors, we first devise two schemes based on the idea of Standby-Sparing (SS): For Paired-SS, processors are organized as groups of two (i.e., pairs) and the existing SS scheme is applied within each pair of processors after partitioning tasks to the pairs. In Generalized-SS, processors are divided into two groups (of potentially different sizes), which are denoted as primary and secondary processor groups, respectively. The main (backup) tasks are scheduled on the primary (secondary) processor group under the partitioned-EDF (partitioned-EDL) with DVFS (DPM) to save energy. Moreover, we propose schemes that allocate primary and backup tasks in a mixed manner to better utilize system slack on all processors for more energy savings. On each processor, the Preference-Oriented Earliest Deadline (POED) scheduler is adopted to run primary tasks at scaled frequencies as soon as possible (ASAP) and backup tasks at the maximum frequency as late as possible (ALAP) to save energy. Our empirical evaluations show that, for systems with a given number of processors, there normally exists a configuration for Generalized-SS with different number of processors in primary and backup groups, which leads to better energy savings when compared to that of the Paired-SS scheme. Moreover, the POED-based schemes normally have more stable performance and can achieve better energy savings.