In this work, the unique power measurement capabilities of the Cray XT architecture were exploited to gain an understanding of power and energy use, and the effects of tuning both CPU and network bandwidth. Modifications were made to deterministically halt cores when idle. Additionally, capabilities were added to alter operating P-state. At the application level, an understanding of the power requirements of a range of important DOE/NNSA production scientific computing applications running at large scale is gained by simultaneously collecting current and voltage measurements on the hosting nodes. The effects of both CPU and network bandwidth tuning are examined, and energy savings opportunities without impact on run-time performance are demonstrated. This research suggests that next-generation large-scale platforms should not only approach CPU frequency scaling differently, but could also benefit from the capability to tune other platform components to achieve more energy-efficient performance.
Recognition of the importance of power in the field of High Performance Computing, whether it be as an obstacle, expense or design consideration, has never been greater and more pervasive. While research has been conducted on many related aspects, there is a stark absence of work focused on large scale High Performance Computing. Part of the reason is the lack of measurement capability currently available on small or large platforms. Typically, research is conducted using coarse methods of measurement such as inserting a power meter between the power source and the platform, or fine grained measurements using custom instrumented boards (with obvious limitations in scale). To collect the measurements necessary to analyze real scientific computing applications at large scale, an in-situ measurement capability must exist on a large scale capability class platform. In response to this challenge, we exploit the unique power measurement capabilities of the Cray XT architecture to gain an understanding of power use and the effects of tuning. We apply these capabilities at the operating system level by deterministically halting cores when idle. At the application level, we gain an understanding of the power requirements of a range of important DOE/NNSA production scientific computing applications running at large scale (thousands of nodes), while simultaneously collecting current and voltage measurements on the hosting nodes. We examine the effects of both CPU and network bandwidth tuning and demonstrate energy savings opportunities of up to 39% with little or no impact on run-time performance. Capturing scale effects in our experimental results was key. Our results provide strong evidence that next generation large-scale platforms should not only approach CPU frequency scaling differently, but could also benefit from the capability to tune other platform components, such as the network, to achieve energy efficient performance.
This book constitutes revised selected papers from the Conference on Energy Efficiency in Large Scale Distributed Systems, EE-LSDS, held in Vienna, Austria, in April 2013. It served as the final event of the COST Action IC0804 which started in May 2009. The 15 full papers presented in this volume were carefully reviewed and selected from 31 contributions. In addition, 7 short papers and 3 demo papers are included in this book. The papers are organized in sections named: modeling and monitoring of power consumption; distributed, mobile and cloud computing; HPC computing; wired and wireless networking; and standardization issues.
High-performance computing platforms have become critical in meeting the demands of modern computing applications. Rising performance requirements in a broad range of platforms from mobile devices to server systems combined with the proliferation of these high-performance computing platforms has increased the energy costs incurred and lead to an exigent need for improvement in platform energy efficiency. This requires infrastructure for monitoring of energy consumption and methods to reduce the platform energy costs. In this dissertation, we present a new measurement infrastructure to provide real-time event-synchronized platform energy measurements, demonstration of these energy measurement capabilities through application to network data transport and an operating system task scheduler that utilizes these energy measurements to greatly improve energy efficiency for multi-core computing platforms. The energy measurement infrastructure is integrated at the platform level and provides event-synchronized energy measurements for the complete platform along with important components such as the CPU, memory modules, secondary storage, peripherals and others. Furthermore, since modern secondary storage devices have buffering mechanisms that defer data write operations, the energy consumption of these operations is modeled and the model is integrated into the platform to characterize the impact of deferred operations. The energy measurement capabilities are demonstrated through application to network data transport where a data file is transported over a network link. The data compression scheme is dynamically selected using real-time energy measurements during transport of the data file to enable adaptation to the dynamic system and network conditions. The energy cost of transporting the data file is significantly reduced through the use of this energy aware compression algorithm. A novel task scheduler is presented and is designed to improve energy efficiency of multiprocessing platforms. It utilizes real-time energy measurements along with CPU performance monitoring units to identify inefficient tasks that suffer from co-run degradation due to resource contention. These inefficient tasks have their scheduling priority modified to avoid contention. Evaluation of the scheduler demonstrates large energy and execution time benefits on a quad-core platform.
This book explores energy efficiency techniques for high-performance computing (HPC) systems using power-management methods. Adopting a step-by-step approach, it describes power-management flows, algorithms and mechanism that are employed in modern processors such as Intel Sandy Bridge, Haswell, Skylake and other architectures (e.g. ARM). Further, it includes practical examples and recent studies demonstrating how modem processors dynamically manage wide power ranges, from a few milliwatts in the lowest idle power state, to tens of watts in turbo state. Moreover, the book explains how thermal and power deliveries are managed in the context this huge power range. The book also discusses the different metrics for energy efficiency, presents several methods and applications of the power and energy estimation, and shows how by using innovative power estimation methods and new algorithms modern processors are able to optimize metrics such as power, energy, and performance. Different power estimation tools are presented, including tools that break down the power consumption of modern processors at sub-processor core/thread granularity. The book also investigates software, firmware and hardware coordination methods of reducing power consumption, for example a compiler-assisted power management method to overcome power excursions. Lastly, it examines firmware algorithms for dynamic cache resizing and dynamic voltage and frequency scaling (DVFS) for memory sub-systems.
This book constitutes the refereed proceedings of the 4th International Workshop, PMBS 2013 in Denver, CO, USA in November 2013. The 14 papers presented in this volume were carefully reviewed and selected from 37 submissions. The selected articles broadly cover topics on massively parallel and high-performance simulations, modeling and simulation, model development and analysis, performance optimization, power estimation and optimization, high performance computing, reliability, performance analysis, and network simulations.
A comprehensive treatment of systems and software testing using state of the art methods and tools This book provides valuable insights into state of the art software testing methods and explains, with examples, the statistical and analytic methods used in this field. Numerous examples are used to provide understanding in applying these methods to real-world problems. Leading authorities in applied statistics, computer science, and software engineering present state-of-the-art methods addressing challenges faced by practitioners and researchers involved in system and software testing. Methods include: machine learning, Bayesian methods, graphical models, experimental design, generalized regression, and reliability modeling. Analytic Methods in Systems and Software Testing presents its comprehensive collection of methods in four parts: Part I: Testing Concepts and Methods; Part II: Statistical Models; Part III: Testing Infrastructures; and Part IV: Testing Applications. It seeks to maintain a focus on analytic methods, while at the same time offering a contextual landscape of modern engineering, in order to introduce related statistical and probabilistic models used in this domain. This makes the book an incredibly useful tool, offering interesting insights on challenges in the field for researchers and practitioners alike. Compiles cutting-edge methods and examples of analytical approaches to systems and software testing from leading authorities in applied statistics, computer science, and software engineering Combines methods and examples focused on the analytic aspects of systems and software testing Covers logistic regression, machine learning, Bayesian methods, graphical models, experimental design, generalized regression, and reliability models Written by leading researchers and practitioners in the field, from diverse backgrounds including research, business, government, and consulting Stimulates research at the theoretical and practical level Analytic Methods in Systems and Software Testing is an excellent advanced reference directed toward industrial and academic readers whose work in systems and software development approaches or surpasses existing frontiers of testing and validation procedures. It will also be valuable to post-graduate students in computer science and mathematics.
This book constitutes the thoroughly refereed post-conference proceedings of the 10th International Conference on Large-Scale Scientific Computations, LSSC 2015, held in Sozopol, Bulgaria, in June 2015. The 49 revised full papers presented were carefully reviewed and selected from 64 submissions. The general theme for LSSC 2015 was Large-Scale Scientific Computing with a particular focus on the organized special sessions: enabling exascale computation; control and uncertain systems; computational microelectronics - from monte carlo to deterministic approaches; numerical methods for multiphysics problems; large-scale models: numerical methods, parallel computations and applications; mathematical modeling and analysis of PDEs describing physical problems; a posteriori error control and iterative methods for maxwell type problems; efficient algorithms for hybrid HPC systems; multilevel methods on graphs; and applications of metaheuristics to large-scale problems.
The twin challenge of meeting global energy demands in the face of growing economies and populations and restricting greenhouse gas emissions is one of the most daunting ones that humanity has ever faced. Smart electrical generation and distribution infrastructure will play a crucial role in meeting these challenges. We would need to develop capabilities to handle large volumes of data generated by the power system components like PMUs, DFRs and other data acquisition devices as well as by the capacity to process these data at high resolution via multi-scale and multi-period simulations, cascading and security analysis, interaction between hybrid systems (electric, transport, gas, oil, coal, etc.) and so on, to get meaningful information in real time to ensure a secure, reliable and stable power system grid. Advanced research on development and implementation of market-ready leading-edge high-speed enabling technologies and algorithms for solving real-time, dynamic, resource-critical problems will be required for dynamic security analysis targeted towards successful implementation of Smart Grid initiatives. This books aims to bring together some of the latest research developments as well as thoughts on the future research directions of the high performance computing applications in electric power systems planning, operations, security, markets, and grid integration of alternate sources of energy, etc.
