Energy-Efficient In-Memory Data Stores on Hybrid Memory Hierarchies

Increasingly large amounts of data are stored in main memory of data center servers. However, DRAM-based memory is an important consumer of energy and is unlikely to scale in the future. Various byte-addressable non-volatile memory (NVM) technologies promise high density and near-zero static energy, however they suffer from increased latency and increased dynamic energy consumption.

This paper proposes to leverage a hybrid memory architecture, consisting of both DRAM and NVM, by novel, application-level data management policies that decide to place data on DRAM vs. NVM. We analyze modern column-oriented and key-value data stores and demonstrate the feasibility of application-level data management. Cycle-accurate simulation confirms that our methodology reduces the energy with least performance degradation as compared to the current state-of-the-art hardware or OS approaches. Moreover, we utilize our techniques to apportion DRAM and NVM memory sizes for these workloads.

Application-Level Energy Awareness for OpenMP

Power, and consequently energy, has recently attained first-class system resource status, on par with conventional metrics such as CPU time. To reduce energy consumption, many hardware- and OS-level solutions have been investigated. However, application-level information - which can provide the system with valuable insights unattainable otherwise - was only considered in a handful of cases. We introduce OpenMPE, an extension to OpenMP designed for power management. OpenMP is the de-facto standard for programming parallel shared memory systems, but does not yet provide any support for power control. Our extension exposes (i) per-region multi-objective optimization hints and (ii) application-level adaptation parameters, in order to create energy-saving opportunities for the whole system stack. We have implemented OpenMPE support in a compiler and runtime system, and empirically evaluated its performance on two architectures, mobile and desktop. Our results demonstrate the effectiveness of OpenMPE with geometric mean energy savings across 9 use cases of 15 % while maintaining full quality of service.

ALEA: Fine-Grain Energy Profiling with Basic Block Sampling

Energy efficiency is an essential requirement for all contemporary computing systems. We thus need tools to measure the energy consumption of computing systems and to understand how workloads affect it. Significant recent research effort has targeted direct power measurements on production computing systems using on-board sensors or external instruments. These direct methods have in turn guided studies of software techniques to reduce energy consumption via workload allocation and scaling. Unfortunately, direct energy measurements are hampered by the low power sampling frequency of power sensors. The coarse granularity of power sensing limits our understanding of how power is allocated in systems and our ability to optimize energy efficiency via workload allocation.
We present ALEA, a tool to measure power and energy consumption at the granularity of basic blocks, using a probabilistic approach. ALEA provides fine-grained energy profiling via sta- tistical sampling, which overcomes the limitations of power sens- ing instruments. Compared to state-of-the-art energy measurement tools, ALEA provides finer granularity without sacrificing accuracy. ALEA achieves low overhead energy measurements with mean error rates between 1.4% and 3.5% in 14 sequential and paral- lel benchmarks tested on both Intel and ARM platforms. The sampling method caps execution time overhead at approximately 1%. ALEA is thus suitable for online energy monitoring and optimization. Finally, ALEA is a user-space tool with a portable, machine-independent sampling method. We demonstrate two use cases of ALEA, where we reduce the energy consumption of a k-means computational kernel by 37% and an ocean modelling code by 33%, compared to high-performance execution baselines, by varying the power optimization strategy between basic blocks.

HpMC: An Energy- Aware Management System for Multi-Level Memory Architectures

DRAM technology faces density and power challenges to increase capacity because of limitations of physical cell design. To overcome these limitations, system designers are exploring alternative solutions that combine DRAM and emerging NVRAM technologies. Previous work on heterogeneous memories focuses, mainly, on two system designs: PCache, a hierarchical, inclusive memory system, and HRank, a flat, non-inclusive memory system. We demonstrate that neither of these designs can universally achieve high performance and energy efficiency across a suite of HPC workloads. In this work, we investigate the impact of a number of multilevel memory designs on the performance, power, and energy consumption of applications. To achieve this goal and overcome the limited number of available tools to study heterogeneous memories, we created HMsim, an infrastructure that enables n-level, heterogeneous memory studies by leveraging existing memory simulators. We, then, propose HpMC, a new memory controller design that combines the best aspects of existing management policies to improve performance and energy. Our energy-aware memory management system dynamically switches between PCache and HRank based on the temporal locality of applications. Our results show that HpMC reduces energy consumption from 13% to 45% compared to PCache and HRank, while providing the same bandwidth and higher capacity than a conventional DRAM system.

Energy Saving - Another Perspective for Parameter Optimization of P and PI Controllers

Modern control methods like optimal control and model predictive control (MPC) provide a framework for simultaneous regulation of the tracking performance and limiting the control energy, thus have been widely deployed in industrial applications. Yet, due to its simplicity and robustness, the conventional P (Proportional) and PI (Proportional–Integral) control are still the most common methods used in many engineering systems, such as electric power systems, automotive, and Heating, Ventilation and Air Conditioning (HVAC) for buildings, where energy efficiency and energy saving are the critical issues to be addressed. Yet, little has been done so far to explore the effect of its parameter tuning on both the system performance and control energy consumption, and how these two objectives are correlated within the P and PI control framework. In this paper, the P and PI controllers are designed with a simultaneous consideration of these two aspects. Two case studies are investigated in detail, including the control of Voltage Source Converters (VSCs) for transmitting offshore wind power to onshore AC grid through High Voltage DC links, and the control of HVAC systems. Results reveal that there exists a better trade-off between the tracking performance and the control energy through a proper choice of the P and PI controller parameters.

Optimization of Controller Parameters for Energy Saving

Among various technologies to tackle the twin challenges of sustainable energy supply and climate change, energy saving through advanced control plays a crucial role in decarbonizing the whole energy system. Modern control technologies, such as optimal control and model predictive control do provide a framework to simultaneously regulate the system performance and limit control energy. However, few have been done so far to exploit the full potential of controller design in reducing the energy consumption while maintaining desirable system performance. This paper investigates the correlations between control energy consumption and system performance using two popular control approaches widely used in the industry, namely the PI control and subspace model predictive control. Our investigation shows that the controller design is a delicate synthesis procedure in achieving better trade-o between system performance and energy saving, and proper choice of values for the control parameters may potentially save a significant amount of energy

Exploiting Significance of Computations for Energy-Constrained Approximate Computing

Approximate execution is a viable technique for environments with energy constraints, provided that applications are given the mechanisms to produce outputs of the highest possible quality within the available energy budget. This paper introduces a framework for energy-constrained execution with controlled and graceful quality loss. A simple programming model allows developers to structure the computation in different tasks, and to express the relative importance of these tasks for the quality of the end result. For non-significant tasks, the developer can also supply less costly, approximate versions. The target energy consumption for a given execution is specified when the application is launched. A significance-aware runtime system employs an application-specific analytical energy model to decide how many cores to use for the execution, the operating frequency for these cores, as well as the degree of task approximation, so as to maximize the quality of the output while meeting the user-specified energy constraints. Evaluation on a dual-socket 16-core Intel platform using 9 benchmark kernels shows that the proposed framework picks the optimal configuration with high accuracy. Also, a comparison with loop perforation (a well-known compile-time approximation technique), shows that the proposed framework results in significantly higher quality for the same energy budget.

Energy Optimization of Memory Intensive Parallel Workloads

Energy consumption is an important concern in modern multicore processors. The energy consumed by a multicore processor during the execution of an application can be minimized by tuning the hardware state utilizing knobs such as frequency, voltage etc. The existing theoretical work on energy minimization using Global DVFS (Dynamic Voltage and Frequency Scaling), despite being thorough, ignores the time and the energy consumed by the CPU on memory accesses and the dynamic energy consumed by the idle cores. This article presents an analytical energy-performance model for parallel workloads that accounts for the time and the energy consumed by the CPU chip on memory accesses in addition to the time and energy consumed by the CPU on CPU instructions. In addition, the model we present also accounts for the dynamic energy consumed by the idle cores. The existing work on global DVFS for parallel workloads shows that using a single frequency for the entire duration of a parallel application is not energy optimal and that varying the frequency according to the changes in the parallelism of the workload can save energy. We present an analytical framework around our energy-performance model to predict the operating frequencies (that depend upon the amount of parallelism) for global DVFS that minimize the overall CPU energy consumption. We show how the optimal frequencies in our model differ from the optimal frequencies in a model that does not account for memory accesses. We further show how the memory intensity of an application affects the optimal frequencies.

Applications of statistical models in proportioning medium strength self-compacting concrete

Self-compacting concrete (SCC) is generally designed with a relatively higher content of finer, which includes cement, and dosage of superplasticizer than the conventional concrete. The design of the current SCC leads to high compressive strength, which is already used in special applications, where the high cost of materials can be tolerated. Using SCC, which eliminates the need for vibration, leads to increased speed of casting and thus reduces labour requirement, energy consumption, construction time, and cost of equipment. In order to obtain and gain maximum benefit from SCC it has to be used for wider applications. The cost of materials will be decreased by reducing the cement content and using a minimum amount of admixtures. This paper reviews statistical models obtained from a factorial design which was carried out to determine the influence of four key parameters on filling ability, passing ability, segregation and compressive strength. These parameters are important for the successful development of medium strength self-compacting concrete (MS-SCC). The parameters considered in the study were the contents of cement and pulverised fuel ash (PFA), water-to-powder ratio (W/P), and dosage of superplasticizer (SP). The responses of the derived statistical models are slump flow, fluidity loss, rheological parameters, Orimet time, V-funnel time, L-box, JRing combined to Orimet, JRing combined to cone, fresh segregation, and compressive strength at 7, 28 and 90 days. The models are valid for mixes made with 0.38 to 0.72 W/P ratio, 60 to 216 kg/m3 of cement content, 183 to 317 kg/m3 of PFA and 0 to 1% of SP, by mass of powder. The utility of such models to optimize concrete mixes to achieve good balance between filling ability, passing ability, segregation, compressive strength, and cost is discussed. Examples highlighting the usefulness of the models are presented using isoresponse surfaces to demonstrate single and coupled effects of mix parameters on slump flow, loss of fluidity, flow resistance, segregation, JRing combined to Orimet, and compressive strength at 7 and 28 days. Cost analysis is carried out to show trade-offs between cost of materials and specified consistency levels and compressive strength at 7 and 28 days that can be used to identify economic mixes. The paper establishes the usefulness of the mathematical models as a tool to facilitate the test protocol required to optimise medium strength SCC.

Integrating Land Use Planning and Transportation: Policy formulation in the Belfast Metropolitan Area

Much of the interest in sustainable cities relates to the inexorable rise in the demand for car travel and the contribution that certain urban forms and land-use relationships can make to reducing energy consumption. Indeed, this demand is fuelled more by increased spatial separation of homes and workplaces, shops and schools than by any rise in trip making. This paper evaluates recent efforts to integrate land-use planning and transportation policy in the Belfast Metropolitan Area by reviewing the policy formulation process at both a regional and city scale. The paper suggests that considerable progress has been made in integrating these two areas of public policy, both institutionally and conceptually. However, concerns are expressed that the rhetoric of sustainability may prove difficult to translate into implementation, leading to a further dislocation of land-use and transportation.

Integrating Land-use Planning and Transportation in Belfast: A New Policy Agenda for Sustainable Development

Much of the interest in promoting sustainable development in planning for the city-region focuses on the apparently inexorable rise in the demand for car travel and the contribution that certain urban forms and land-use relationships can make to reducing energy consumption. Within this context, policy prescription has increasingly favoured a compact city approach with increasing urban residential densities to address the physical separation of daily activities and the resultant dependency on the private car. This paper aims to outline and evaluate recent efforts to integrate land use and transport policy in the Belfast Metropolitan Area in Northern Ireland. Although considerable progress has been made, this paper underlines the extent of existing car dependency in the metropolitan area and prevailing negative attitudes to public transport, and argues that although there is a rhetorical support for the principles of sustainability and the practice of land-use/transportation integration, this is combined with a selective reluctance to embrace local changes in residential environment or in lifestyle preferences which might facilitate such principles.

Performance analysis of an improved power-saving medium access protocol for IEEE 802.11 point coordination function WLAN

Wireless enabled portable devices must operate with the highest possible energy efficiency while still maintaining a minimum level and quality of service to meet the user's expectations. The authors analyse the performance of a new pointer-based medium access control protocol that was designed to significantly improve the energy efficiency of user terminals in wireless local area networks. The new protocol, pointer controlled slot allocation and resynchronisation protocol (PCSAR), is based on the existing IEEE 802.11 point coordination function (PCF) standard. PCSAR reduces energy consumption by removing the need for power saving stations to remain awake and listen to the channel. Using OPNET, simulations were performed under symmetric channel loading conditions to compare the performance of PCSAR with the infrastructure power saving mode of IEEE 802.11, PCF-PS. The simulation results demonstrate a significant improvement in energy efficiency without significant reduction in performance when using PCSAR. For a wireless network consisting of an access point and 8 stations in power saving mode, the energy saving was up to 31% while using PCSAR instead of PCF-PS, depending upon frame error rate and load. The results also show that PCSAR offers significantly reduced uplink access delay over PCF-PS while modestly improving uplink throughput.

Improved power-saving medium access protocol for IEEE 802.11e QoS-enabled wireless networks

The performance of a new pointer-based medium-access control protocol that was designed to significantly improve the energy efficiency of user terminals in quality-of-service-enabled wireless local area networks was analysed. The new protocol, pointer-controlled slot allocation and resynchronisation protocol (PCSARe), is based on the hybrid coordination function-controlled channel access mode of the IEEE 802.11e standard. PCSARe reduces energy consumption by removing the need for power-saving stations to remain awake for channel listening. Discrete event network simulations were performed to compare the performance of PCSARe with the non-automatic power save delivery (APSD) and scheduled-APSD power-saving modes of IEEE 802.11e. The simulation results show a demonstrable improvement in energy efficiency without significant reduction in performance when using PCSARe. For a wireless network consisting of an access point and eight stations in power-saving mode, the energy saving was up to 39% when using PCSARe instead of IEEE 802.11e non-APSD. The results also show that PCSARe offers significantly reduced uplink access delay over IEEE 802.11e non-APSD, while modestly improving the uplink throughput. Furthermore, although both had the same energy consumption, PCSARe gave a 25% reduction in downlink access delay compared with IEEE 802.11e S-APSD.

Effect of Selfish Node Behavior on Efficient Topology Design

The problem of topology control is to assign per-node transmission power such that the resulting topology is energy efficient and satisfies certain global properties such as connectivity. The conventional approach to achieve these objectives is based on the fundamental assumption that nodes are socially responsible. We examine the following question: if nodes behave in a selfish manner, how does it impact the overall connectivity and energy consumption in the resulting topologies? We pose the above problem as a noncooperative game and use game-theoretic analysis to address it. We study Nash equilibrium properties of the topology control game and evaluate the efficiency of the induced topology when nodes employ a greedy best response algorithm. We show that even when the nodes have complete information about the network, the steady-state topologies are suboptimal. We propose a modified algorithm based on a better response dynamic and show that this algorithm is guaranteed to converge to energy-efficient and connected topologies. Moreover, the node transmit power levels are more evenly distributed, and the network performance is comparable to that obtained from centralized algorithms.