Parallel and High Performance Computing offers techniques guaranteed to boost your code’s effectiveness. Summary Complex calculations, like training deep learning models or running large-scale simulations, can take an extremely long time. Efficient parallel programming can save hours—or even days—of computing time. Parallel and High Performance Computing shows you how to deliver faster run-times, greater scalability, and increased energy efficiency to your programs by mastering parallel techniques for multicore processor and GPU hardware. About the technology Write fast, powerful, energy efficient programs that scale to tackle huge volumes of data. Using parallel programming, your code spreads data processing tasks across multiple CPUs for radically better performance. With a little help, you can create software that maximizes both speed and efficiency. About the book Parallel and High Performance Computing offers techniques guaranteed to boost your code’s effectiveness. You’ll learn to evaluate hardware architectures and work with industry standard tools such as OpenMP and MPI. You’ll master the data structures and algorithms best suited for high performance computing and learn techniques that save energy on handheld devices. You’ll even run a massive tsunami simulation across a bank of GPUs. What's inside Planning a new parallel project Understanding differences in CPU and GPU architecture Addressing underperforming kernels and loops Managing applications with batch scheduling About the reader For experienced programmers proficient with a high-performance computing language like C, C++, or Fortran. About the author Robert Robey works at Los Alamos National Laboratory and has been active in the field of parallel computing for over 30 years. Yuliana Zamora is currently a PhD student and Siebel Scholar at the University of Chicago, and has lectured on programming modern hardware at numerous national conferences. Table of Contents PART 1 INTRODUCTION TO PARALLEL COMPUTING 1 Why parallel computing? 2 Planning for parallelization 3 Performance limits and profiling 4 Data design and performance models 5 Parallel algorithms and patterns PART 2 CPU: THE PARALLEL WORKHORSE 6 Vectorization: FLOPs for free 7 OpenMP that performs 8 MPI: The parallel backbone PART 3 GPUS: BUILT TO ACCELERATE 9 GPU architectures and concepts 10 GPU programming model 11 Directive-based GPU programming 12 GPU languages: Getting down to basics 13 GPU profiling and tools PART 4 HIGH PERFORMANCE COMPUTING ECOSYSTEMS 14 Affinity: Truce with the kernel 15 Batch schedulers: Bringing order to chaos 16 File operations for a parallel world 17 Tools and resources for better code

Software -- Operating Systems.

This edited book aims to present the state of the art in research and development of the convergence of high-performance computing and parallel programming for various engineering and scientific applications. The book has consolidated algorithms, techniques, and methodologies to bridge the gap between the theoretical foundations of academia and implementation for research, which might be used in business and other real-time applications in the future.The book outlines techniques and tools used for emergent areas and domains, which include acceleration of large-scale electronic structure simulations with heterogeneous parallel computing, characterizing power and energy efficiency of a data-centric high-performance computing runtime and applications, security applications of GPUs, parallel implementation of multiprocessors on MPI using FDTD, particle-based fused rendering, design and implementation of particle systems for mesh-free methods with high performance, and evolving topics on heterogeneous computing. In the coming days the need to converge HPC, IoT, cloud-based applications will be felt and this volume tries to bridge that gap.

CUDA for Engineers gives you direct, hands-on engagement with personal, high-performance parallel computing, enabling you to do computations on a gaming-level PC that would have required a supercomputer just a few years ago. The authors introduce the essentials of CUDA C programming clearly and concisely, quickly guiding you from running sample programs to building your own code. Throughout, you’ll learn from complete examples you can build, run, and modify, complemented by additional projects that deepen your understanding. All projects are fully developed, with detailed building instructions for all major platforms. Ideal for any scientist, engineer, or student with at least introductory programming experience, this guide assumes no specialized background in GPU-based or parallel computing. In an appendix, the authors also present a refresher on C programming for those who need it. Coverage includes Preparing your computer to run CUDA programs Understanding CUDA’s parallelism model and C extensions Transferring data between CPU and GPU Managing timing, profiling, error handling, and debugging Creating 2D grids Interoperating with OpenGL to provide real-time user interactivity Performing basic simulations with differential equations Using stencils to manage related computations across threads Exploiting CUDA’s shared memory capability to enhance performance Interacting with 3D data: slicing, volume rendering, and ray casting Using CUDA libraries Finding more CUDA resources and code Realistic example applications include Visualizing functions in 2D and 3D Solving differential equations while changing initial or boundary conditions Viewing/processing images or image stacks Computing inner products and centroids Solving systems of linear algebraic equations Monte-Carlo computations

This book focuses on the theoretical and practical aspects of parallel programming systems for today's high performance multi-core processors and discusses the efficient implementation of key algorithms needed to implement parallel programming models. Such implementations need to take into account the specific architectural aspects of the underlying computer architecture and the features offered by the execution environment. This book briefly reviews key concepts of modern computer architecture, focusing particularly on the performance of parallel codes as well as the relevant concepts in parallel programming models. The book then turns towards the fundamental algorithms used to implement the parallel programming models and discusses how they interact with modern processors. While the book will focus on the general mechanisms, we will mostly use the Intel processor architecture to exemplify the implementation concepts discussed but will present other processor architectures where appropriate. All algorithms and concepts are discussed in an easy to understand way with many illustrative examples, figures, and source code fragments. The target audience of the book is students in Computer Science who are studying compiler construction, parallel programming, or programming systems. Software developers who have an interest in the core algorithms used to implement a parallel runtime system, or who need to educate themselves for projects that require the algorithms and concepts discussed in this book will also benefit from reading it. You can find the source code for this book at https://github.com/parallel-runtimes/lomp.

The book discusses the fundamentals of high-performance computing. The authors combine visualization, comprehensibility, and strictness in their material presentation, and thus influence the reader towards practical application and learning how to solve real computing problems. They address both key approaches to programming modern computing systems: multithreading-based parallelizing in shared memory systems, and applying message-passing technologies in distributed systems. The book is suitable for undergraduate and graduate students, and for researchers and practitioners engaged with high-performance computing systems. Each chapter begins with a theoretical part, where the relevant terminology is introduced along with the basic theoretical results and methods of parallel programming, and concludes with a list of test questions and problems of varying difficulty. The authors include many solutions and hints, and often sample code.

High Performance Computing is an integrated computing environment for solving large-scale computational demanding problems in science, engineering and business. Newly emerging areas of HPC applications include medical sciences, transportation, financial operations and advanced human-computer interface such as virtual reality. High performance computing includes computer hardware, software, algorithms, programming tools and environments, plus visualization. The book addresses several of these key components of high performance technology and contains descriptions of the state-of-the-art computer architectures, programming and software tools and innovative applications of parallel computers. In addition, the book includes papers on heterogeneous network-based computing systems and scalability of parallel systems. The reader will find information and data relative to the two main thrusts of high performance computing: the absolute computational performance and that of providing the most cost effective and affordable computing for science, industry and business. The book is recommended for technical as well as management oriented individuals.

An overview of the most prominent contemporary parallel processing programming models, written in a unique tutorial style. With the coming of the parallel computing era, computer scientists have turned their attention to designing programming models that are suited for high-performance parallel computing and supercomputing systems. Programming parallel systems is complicated by the fact that multiple processing units are simultaneously computing and moving data. This book offers an overview of some of the most prominent parallel programming models used in high-performance computing and supercomputing systems today. The chapters describe the programming models in a unique tutorial style rather than using the formal approach taken in the research literature. The aim is to cover a wide range of parallel programming models, enabling the reader to understand what each has to offer. The book begins with a description of the Message Passing Interface (MPI), the most common parallel programming model for distributed memory computing. It goes on to cover one-sided communication models, ranging from low-level runtime libraries (GASNet, OpenSHMEM) to high-level programming models (UPC, GA, Chapel); task-oriented programming models (Charm++, ADLB, Scioto, Swift, CnC) that allow users to describe their computation and data units as tasks so that the runtime system can manage computation and data movement as necessary; and parallel programming models intended for on-node parallelism in the context of multicore architecture or attached accelerators (OpenMP, Cilk Plus, TBB, CUDA, OpenCL). The book will be a valuable resource for graduate students, researchers, and any scientist who works with data sets and large computations. Contributors Timothy Armstrong, Michael G. Burke, Ralph Butler, Bradford L. Chamberlain, Sunita Chandrasekaran, Barbara Chapman, Jeff Daily, James Dinan, Deepak Eachempati, Ian T. Foster, William D. Gropp, Paul Hargrove, Wen-mei Hwu, Nikhil Jain, Laxmikant Kale, David Kirk, Kath Knobe, Ariram Krishnamoorthy, Jeffery A. Kuehn, Alexey Kukanov, Charles E. Leiserson, Jonathan Lifflander, Ewing Lusk, Tim Mattson, Bruce Palmer, Steven C. Pieper, Stephen W. Poole, Arch D. Robison, Frank Schlimbach, Rajeev Thakur, Abhinav Vishnu, Justin M. Wozniak, Michael Wilde, Kathy Yelick, Yili Zheng

Based on a course developed by the author, Introduction to High Performance Scientific Computing introduces methods for adding parallelism to numerical methods for solving differential equations. It contains exercises and programming projects that facilitate learning as well as examples and discussions based on the C programming language, with additional comments for those already familiar with C++. The text provides an overview of concepts and algorithmic techniques for modern scientific computing and is divided into six self-contained parts that can be assembled in any order to create an introductory course using available computer hardware. Part I introduces the C programming language for those not already familiar with programming in a compiled language. Part II describes parallelism on shared memory architectures using OpenMP. Part III details parallelism on computer clusters using MPI for coordinating a computation. Part IV demonstrates the use of graphical programming units (GPUs) to solve problems using the CUDA language for NVIDIA graphics cards. Part V addresses programming on GPUs for non-NVIDIA graphics cards using the OpenCL framework. Finally, Part VI contains a brief discussion of numerical methods and applications, giving the reader an opportunity to test the methods on typical computing problems.

Gain Critical Insight into the Parallel I/O Ecosystem Parallel I/O is an integral component of modern high performance computing (HPC), especially in storing and processing very large datasets to facilitate scientific discovery. Revealing the state of the art in this field, High Performance Parallel I/O draws on insights from leading practitioners, researchers, software architects, developers, and scientists who shed light on the parallel I/O ecosystem. The first part of the book explains how large-scale HPC facilities scope, configure, and operate systems, with an emphasis on choices of I/O hardware, middleware, and applications. The book then traverses up the I/O software stack. The second part covers the file system layer and the third part discusses middleware (such as MPIIO and PLFS) and user-facing libraries (such as Parallel-NetCDF, HDF5, ADIOS, and GLEAN). Delving into real-world scientific applications that use the parallel I/O infrastructure, the fourth part presents case studies from particle-in-cell, stochastic, finite volume, and direct numerical simulations. The fifth part gives an overview of various profiling and benchmarking tools used by practitioners. The final part of the book addresses the implications of current trends in HPC on parallel I/O in the exascale world.