DOCSLIB.ORG

Intel(R) Math Kernel Library for Windows* Developer Guide

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Intel(R) Math Kernel Library for Windows* Developer Guide Intel® Math Kernel Library for Windows* OS Developer Guide Intel® MKL 11.3 - Windows* OS Revision: 053 Legal Information Contents Contents Legal Information................................................................................ 9 Getting Help and Support................................................................... 11 Introducing the Intel® Math Kernel Library.........................................13 What's New........................................................................................ 15 Notational Conventions...................................................................... 17 Related Information........................................................................... 19 Chapter 1: Getting Started Checking Your Installation......................................................................... 21 Setting Environment Variables .................................................................. 21 Compiler Support.....................................................................................22 Using Code Examples............................................................................... 23 What You Need to Know Before You Begin Using the Intel® Math Kernel Library............................................................................................... 23 Chapter 2: Structure of the Intel® Math Kernel Library Architecture Support................................................................................ 27 High-level Directory Structure....................................................................27 Layered Model Concept.............................................................................29 Chapter 3: Linking Your Application with the Intel® Math Kernel Library Linking Quick Start...................................................................................31 Using the /Qmkl Compiler Option.......................................................31 Automatically Linking a Project in the Visual Studio* Integrated Development Environment with Intel® MKL......................................32 Automatically Linking Your Microsoft Visual C/C++* Project with Intel® MKL.......................................................................... 32 Automatically Linking Your Intel® Visual Fortran Project with Intel® MKL.......................................................................... 32 Using the Single Dynamic Library.......................................................33 Selecting Libraries to Link with.......................................................... 33 Using the Link-line Advisor................................................................34 Using the Command-line Link Tool..................................................... 34 Linking Examples..................................................................................... 34 Linking on IA-32 Architecture Systems............................................... 34 Linking on Intel(R) 64 Architecture Systems........................................ 35 Linking in Detail.......................................................................................36 Dynamically Selecting the Interface and Threading Layer...................... 36 Linking with Interface Libraries.......................................................... 38 Using the cdecl and stdcall Interfaces.........................................38 Using the ILP64 Interface vs. LP64 Interface............................... 39 Using the SP2DP Interface........................................................ 41 Linking with Fortran 95 Interface Libraries.................................. 41 Linking with Threading Libraries.........................................................41 Linking with Computational Libraries.................................................. 43 Linking with Compiler Run-time Libraries............................................ 44 3 Intel® Math Kernel Library for Windows* OS Developer Guide Linking with System Libraries............................................................ 44 Building Custom Dynamic-link Libraries.......................................................45 Using the Custom Dynamic-link Library Builder in the Command-line Mode......................................................................................... 45 Composing a List of Functions .......................................................... 46 Specifying Function Names............................................................... 47 Building a Custom Dynamic-link Library in the Visual Studio* Development System................................................................... 48 Distributing Your Custom Dynamic-link Library.....................................49 Chapter 4: Managing Performance and Memory Improving Performance with Threading....................................................... 51 OpenMP* Threaded Functions and Problems........................................ 51 Functions Threaded with Intel® Threading Building Blocks......................53 Avoiding Conflicts in the Execution Environment...................................54 Techniques to Set the Number of Threads........................................... 54 Setting the Number of Threads Using an OpenMP* Environment Variable......................................................................................55 Changing the Number of OpenMP* Threads at Run Time....................... 55 Using Additional Threading Control.....................................................58 Intel MKL-specific Environment Variables for OpenMP Threading Control...............................................................................58 MKL_DYNAMIC........................................................................59 MKL_DOMAIN_NUM_THREADS.................................................. 59 Setting the Environment Variables for Threading Control...............61 Calling Intel MKL Functions from Multi-threaded Applications................. 61 Using Intel® Hyper-Threading Technology............................................ 63 Managing Multi-core Performance...................................................... 63 Improving Performance for Small Size Problems ..........................................64 Using MKL_DIRECT_CALL in C Applications..........................................64 Using MKL_DIRECT_CALL in Fortran Applications..................................65 Limitations of the Direct Call ............................................................ 65 Other Tips and Techniques to Improve Performance......................................66 Coding Techniques........................................................................... 66 Improving Intel(R) MKL Performance on Specific Processors.................. 67 Operating on Denormals................................................................... 67 Fast Fourier Transform Optimized Radices........................................... 67 Using Memory Functions .......................................................................... 67 Avoiding Memory Leaks in Intel MKL...................................................67 Redefining Memory Functions............................................................ 68 Chapter 5: Language-specific Usage Options Using Language-Specific Interfaces with Intel® Math Kernel Library.................71 Interface Libraries and Modules......................................................... 71 Fortran 95 Interfaces to LAPACK and BLAS..........................................72 Compiler-dependent Functions and Fortran 90 Modules.........................73 Using the stdcall Calling Convention in C/C++..................................... 73 Compiling an Application that Calls the Intel® Math Kernel Library and Uses the CVF Calling Conventions.................................................. 74 Mixed-language Programming with the Intel Math Kernel Library.................... 75 4 Contents Calling LAPACK, BLAS, and CBLAS Routines from C/C++ Language Environments..............................................................................75 Using Complex Types in C/C++......................................................... 76 Calling BLAS Functions that Return the Complex Values in C/C++ Code.. 77 Chapter 6: Obtaining Numerically Reproducible Results Getting Started with Conditional Numerical Reproducibility ........................... 82 Specifying Code Branches......................................................................... 83 Reproducibility Conditions......................................................................... 84 Setting the Environment Variable for Conditional Numerical Reproducibility......85 Code Examples........................................................................................85 Chapter 7: Coding Tips Example of Data Alignment....................................................................... 89 Using Predefined Preprocessor Symbols for Intel® MKL Version-Dependent Compilation.........................................................................................90 Chapter 8: Managing Output Using Intel MKL Verbose Mode................................................................... 93 Version Information Line...................................................................93 Call Description Line.........................................................................94 Chapter 9: Working with the Intel® Math Kernel Library Cluster Software Message-Passing Interface Support...........................................................
Load more

Recommended publications
  • Examining the Viability of FPGA Supercomputing
    1 Examining the Viability of FPGA Supercomputing Stephen D. Craven and Peter Athanas Bradley Department of Electrical and Computer Engineering Virginia Polytechnic Institute and State University Blacksburg, VA 24061 USA email: {scraven,athanas}@vt.edu Abstract—For certain applications, custom computational hardware created using field programmable gate arrays (FPGAs) produces significant performance improvements over processors, leading some in academia and industry to call for the inclusion of FPGAs in supercomputing clusters. This paper presents a comparative analysis of FPGAs and traditional processors, focusing on floating- point performance and procurement costs, revealing economic hurdles in the adoption of FPGAs for general High-Performance Computing (HPC). Index Terms— computational accelerator, digital arithmetic, Field programmable gate arrays, high- performance computing, supercomputers. I. INTRODUCTION Supercomputers have experienced a recent resurgence, fueled by government research dollars and the development of low-cost supercomputing clusters. Unlike the Massively Parallel Processor (MPP) designs found in Cray and CDC machines of the 70s and 80s, featuring proprietary processor architectures, many modern supercomputing clusters are constructed from commodity PC processors, significantly reducing procurement costs. In an effort to improve performance, several companies offer machines that place one or more FPGAs in each node of the cluster. Configurable logic devices, of which FPGAs are one example, permit the device’s hardware to be programmed multiple times after manufacture. A wide body of research over two decades has repeatedly demonstrated significant performance improvements for certain classes of applications when implemented within an FPGA’s configurable logic [1]. Applications well suited to speed-up by FPGAs typically exhibit massive parallelism and small integer or fixed-point data types.
    [Show full text]
  • Overview of the SPEC Benchmarks
    9 Overview of the SPEC Benchmarks Kaivalya M. Dixit IBM Corporation “The reputation of current benchmarketing claims regarding system performance is on par with the promises made by politicians during elections.” Standard Performance Evaluation Corporation (SPEC) was founded in October, 1988, by Apollo, Hewlett-Packard,MIPS Computer Systems and SUN Microsystems in cooperation with E. E. Times. SPEC is a nonprofit consortium of 22 major computer vendors whose common goals are “to provide the industry with a realistic yardstick to measure the performance of advanced computer systems” and to educate consumers about the performance of vendors’ products. SPEC creates, maintains, distributes, and endorses a standardized set of application-oriented programs to be used as benchmarks. 489 490 CHAPTER 9 Overview of the SPEC Benchmarks 9.1 Historical Perspective Traditional benchmarks have failed to characterize the system performance of modern computer systems. Some of those benchmarks measure component-level performance, and some of the measurements are routinely published as system performance. Historically, vendors have characterized the performances of their systems in a variety of confusing metrics. In part, the confusion is due to a lack of credible performance information, agreement, and leadership among competing vendors. Many vendors characterize system performance in millions of instructions per second (MIPS) and millions of floating-point operations per second (MFLOPS). All instructions, however, are not equal. Since CISC machine instructions usually accomplish a lot more than those of RISC machines, comparing the instructions of a CISC machine and a RISC machine is similar to comparing Latin and Greek. 9.1.1 Simple CPU Benchmarks Truth in benchmarking is an oxymoron because vendors use benchmarks for marketing purposes.
    [Show full text]
  • Performance of a Computer (Chapter 4) Vishwani D
    ELEC 5200-001/6200-001 Computer Architecture and Design Fall 2013 Performance of a Computer (Chapter 4) Vishwani D. Agrawal & Victor P. Nelson epartment of Electrical and Computer Engineering Auburn University, Auburn, AL 36849 ELEC 5200-001/6200-001 Performance Fall 2013 . Lecture 1 What is Performance? Response time: the time between the start and completion of a task. Throughput: the total amount of work done in a given time. Some performance measures: MIPS (million instructions per second). MFLOPS (million floating point operations per second), also GFLOPS, TFLOPS (1012), etc. SPEC (System Performance Evaluation Corporation) benchmarks. LINPACK benchmarks, floating point computing, used for supercomputers. Synthetic benchmarks. ELEC 5200-001/6200-001 Performance Fall 2013 . Lecture 2 Small and Large Numbers Small Large 10-3 milli m 103 kilo k 10-6 micro μ 106 mega M 10-9 nano n 109 giga G 10-12 pico p 1012 tera T 10-15 femto f 1015 peta P 10-18 atto 1018 exa 10-21 zepto 1021 zetta 10-24 yocto 1024 yotta ELEC 5200-001/6200-001 Performance Fall 2013 . Lecture 3 Computer Memory Size Number bits bytes 210 1,024 K Kb KB 220 1,048,576 M Mb MB 230 1,073,741,824 G Gb GB 240 1,099,511,627,776 T Tb TB ELEC 5200-001/6200-001 Performance Fall 2013 . Lecture 4 Units for Measuring Performance Time in seconds (s), microseconds (μs), nanoseconds (ns), or picoseconds (ps). Clock cycle Period of the hardware clock Example: one clock cycle means 1 nanosecond for a 1GHz clock frequency (or 1GHz clock rate) CPU time = (CPU clock cycles)/(clock rate) Cycles per instruction (CPI): average number of clock cycles used to execute a computer instruction.
    [Show full text]
  • Investigations of Various HPC Benchmarks to Determine Supercomputer Performance Efficiency and Balance
    Investigations of Various HPC Benchmarks to Determine Supercomputer Performance Efficiency and Balance Wilson Lisan August 24, 2018 MSc in High Performance Computing The University of Edinburgh Year of Presentation: 2018 Abstract This dissertation project is based on participation in the Student Cluster Competition (SCC) at the International Supercomputing Conference (ISC) 2018 in Frankfurt, Germany as part of a four-member Team EPCC from The University of Edinburgh. There are two main projects which are the team-based project and a personal project. The team-based project focuses on the optimisations and tweaks of the HPL, HPCG, and HPCC benchmarks to meet the competition requirements. At the competition, Team EPCC suffered with hardware issues that shaped the cluster into an asymmetrical system with mixed hardware. Unthinkable and extreme methods were carried out to tune the performance and successfully drove the cluster back to its ideal performance. The personal project focuses on testing the SCC benchmarks to evaluate the performance efficiency and system balance at several HPC systems. HPCG fraction of peak over HPL ratio was used to determine the system performance efficiency from its peak and actual performance. It was analysed through HPCC benchmark that the fraction of peak ratio could determine the memory and network balance over the processor or GPU raw performance as well as the possibility of the memory or network bottleneck part. Contents Chapter 1 Introduction ..............................................................................................
    [Show full text]
  • Intel® Math Kernel Library (Intel® MKL) 10.2 In-Depth Intel® Math Kernel Library (Intel® MKL) 10.2: In-Depth
    Intel® Math Kernel Library (Intel® MKL) 10.2 In-Depth Intel® Math Kernel Library (Intel® MKL) 10.2: In-Depth Contents Intel® Math Kernel Library (Intel® MKL) 10.2. .4 Performance Improvements in Intel MKL 10.2. 6 Highlights . 4 Performance Improvements in Intel MKL 10.1. 7 Features. 4 Performance Improvements in Version 10.0. 7 Multicore ready . 4 BLAS . 7 Automatic runtime processor detection . .4 LAPACK . 7 Support for C and Fortran interfaces . 4 FFTs . 7 Support for all Intel® processors in one package . 4 VML/VSL . .7 Royalty-free distribution rights . 4 Functionality. 7 New in Intel MKL 10.2. 4 Linear Algebra: BLAS and LAPACK . .7 Performance Improvements . 4 BLAS . 8 C#/ .Net support . 4 Sparse BLAS . 8 BLAS . 4 LAPACK . .8 LAPACK . .5 BLAS and LAPACK Performance . .8 FFT . 5 Linear Algebra: ScaLAPACK . 9 PARDISO . 5 ScaLAPACK Performance . 9 New in Intel® MKL 10.1. .5 Raw Performance . 9 Computational Layer . .5 Block Size Robustness . 10 PARDISO Direct Sparse Solver . 5 References. 10 Sparse BLAS . .5 Linear Algebra: Sparse Solvers . 1. 0 LAPACK . 5 PARDISO*: Parallel Direct Sparse Solver . 11 Discrete Fourier Transform Interface (DFTI) . 5 New Out-of-Core Support! . 1. 1 Iterative Solver Preconditioner . 6 Iterative Solvers . .11 Vector Math Functions . 6 FGMRES Solver . 1. 1 User’s Guide . 6 Conjugate Gradient Solver . 11 ILU0/ILUT Preconditioners . 1. 2 Sparse BLAS . 1. 2 2 Intel® Math Kernel Library (Intel® MKL) 10.2: In-Depth References. 12 LINPACK Benchmark . 19 Fast Fourier Transforms (FFT) . 1. 2 Ease of Use . 19 Interfaces . .12 Performance . 20 Fortran and C .
    [Show full text]
  • PT-365-Updated-Classroom-Material-March-May-20.Pdf
    Dear Students, Hope your preparation is going well. We wish to communicate our plan, at part of PT 365, for the upcoming prelims examination. Given that Prelims examination is now scheduled for 4th October, we will be covering current affairs till the month of August in the following manner - • PT 365 Updation - o Coverage - Current affairs for the months of March, April and May • PT 365 Extended - o Tentative date of release - 10th September o Coverage - Current affairs for the months of June, July and August Hope these documents help you in boosting your preparation and building up your confidence further as you wind up your preparations. Best Wishes Team Vision IAS Table of Contents 1. POLITY AND CONSTITUTION __________ 4 2.2.2. Organisation for the Prohibition of Chemical 1.1. Issues Related to Constitution ________ 4 Weapons _____________________________ 15 1.1.1. Right to Property____________________ 4 2.2.3. Multilateral Development Banks ______ 15 1.1.2. Reservation in Scheduled Areas ________ 4 2.2.4. WHO ____________________________ 16 1.1.3. Jammu & Kashmir Domicile Rules_______ 5 2.2.4.1. World Health Assembly (WHA) ____ 16 1.1.4. Constitutional Articles in News _________ 5 2.2.4.2. WHO executive board ___________ 16 1.2. Issues Related to Functioning of 2.2.4.3. World Health Organization Funding 16 Parliament/ State Legislature/Local 2.3. International Events _______________ 17 2.3.1. UN75 ___________________________ 17 Government __________________________ 6 2.3.2. Open Skies Treaty __________________ 17 1.2.1. Rajya Sabha Elections ________________ 6 2.3.3.
    [Show full text]
  • Supercomputers – Prestige Objects Or Crucial Tools for Science and Industry?
    Supercomputers – Prestige Objects or Crucial Tools for Science and Industry? Hans W. Meuer a 1, Horst Gietl b 2 a University of Mannheim & Prometeus GmbH, 68131 Mannheim, Germany; b Prometeus GmbH, 81245 Munich, Germany; This paper is the revised and extended version of the Lorraine King Memorial Lecture Hans Werner Meuer was invited by Lord Laird of Artigarvan to give at the House of Lords, London, on April 18, 2012. Keywords: TOP500, High Performance Computing, HPC, Supercomputing, HPC Technology, Supercomputer Market, Supercomputer Architecture, Supercomputer Applications, Supercomputer Technology, Supercomputer Performance, Supercomputer Future. 1 e-mail: [email protected] 2 e-mail: [email protected] 1 Content 1 Introduction ..................................................................................................................................... 3 2 The TOP500 Supercomputer Project ............................................................................................... 3 2.1 The LINPACK Benchmark ......................................................................................................... 4 2.2 TOP500 Authors ...................................................................................................................... 4 2.3 The 39th TOP500 List since 1993 .............................................................................................. 5 2.4 The 39th TOP10 List since 1993 ...............................................................................................
    [Show full text]
  • Understanding IBM Pseries Performance and Sizing
    Understanding IBM pSeries Performance and Sizing Comprehend IBM RS/6000 and IBM ^ pSeries hardware architectures Get an overview of current industry benchmarks Understand how to size your system Nigel Trickett Tatsuhiko Nakagawa Ravi Mani Diana Gfroerer ibm.com/redbooks SG24-4810-01 International Technical Support Organization Understanding IBM ^ pSeries Performance and Sizing February 2001 Take Note! Before using this information and the product it supports, be sure to read the general information in Appendix A, “Special notices” on page 377. Second Edition (February 2001) This edition applies to IBM RS/6000 and IBM ^ pSeries as of December 2000, and Version 4.3.3 of the AIX operating system. This document was updated on January 24, 2003. Comments may be addressed to: IBM Corporation, International Technical Support Organization Dept. JN9B Building 003 Internal Zip 2834 11400 Burnet Road Austin, Texas 78758-3493 When you send information to IBM, you grant IBM a non-exclusive right to use or distribute the information in any way it believes appropriate without incurring any obligation to you. © Copyright International Business Machines Corporation 1997, 2001. All rights reserved. Note to U.S Government Users – Documentation related to restricted rights – Use, duplication or disclosure is subject to restrictions set forth in GSA ADP Schedule Contract with IBM Corp. Contents Preface. 9 The team that wrote this redbook. 9 Comments welcome. 11 Chapter 1. Introduction . 1 Chapter 2. Background . 5 2.1 Performance of processors . 5 2.2 Hardware architectures . 6 2.2.1 RISC/CISC concepts . 6 2.2.2 Superscalar architecture: pipeline and parallelism . 7 2.2.3 Memory management .
    [Show full text]
  • AMD Opteron™ Processor Benchmarking for Clustered Systems
    W H I T E P A P E R AMD Opteron™ Processor Benchmarking for Clustered Systems Doug O’flaherty and Michael Goddard AMD One AMD Place Sunnyvale, CA 94088 Page 1 AMD Opteron™ Processor Benchmarking for Clustered Systems July 15, 2003 W H I T E P A P E R Objective The selection of a High-Performance Computing (HPC) platform is a process of evaluation and analysis. The goal is to deliver the appropriate combination of SMP and cluster configuration, processor, memory, interconnect, and storage that optimizes performance. This is often done without being able to run the customer-specific application on the complete system prior to selection. Since the application specific metrics are absent, industry benchmarks provide a basis for comparison. Industry standard benchmarks are system or sub-system metrics for performing a particular computing task. There are as many benchmarks as there are computing tasks. This paper examines AMD Opteron™ processor performance across a suite of industry standard benchmarks. The metrics reflect the AMD Opteron processor’s unique architecture, which balances bandwidth with outstanding computing performance to deliver true scalability for HPC applications. Introduction Benchmarks seek to provide comparative results—a quantitative analysis of disparate systems performing similar computational tasks. The benchmarking effort typically attempts to set performance expectations of real world tasks. However, to achieve objective results, each benchmark is limited in the scope of its measurements. Some benchmarks emphasize raw floating-point operations per second, while others measure memory access latency and bandwidth, while others script a particular workload in a specific application. Because applications are diverse and more complex than a combination of metrics, no single benchmark is a metric of a processor’s ability to perform real-world computation.
    [Show full text]
  • Solution of Algebraic Equations by Using Autonomous Computational Methods
    Solution of Algebraic Equations by Using Autonomous Computational Methods Andrew Pownuk Department of Mathematical Sciences University of Texas at El Paso, El Paso, Texas, USA [email protected], https://andrew.pownuk.com AMS Fall Central Sectional Meeting September 12-13, 2020 1 / 63 Outline 1 Game Theory 2 Autonomous Computational Methods 3 Algebraic Equations 4 Generalizations and Possible Limitations 5 Autonomous Computational Methods 6 Machine Learning 7 Conclusions 2 / 63 Checkers (Game Theory) Game Theory Autonomous Computational Methods Algebraic Equations Generalizations and Possible Limitations Autonomous Computational Methods Machine Figure: Game tree Learning Conclusions Arthur Samuel in 1959 applied alphabeta pruning in order to create a program that learned how to play checkers. Alphabeta pruning is a search algorithm that seeks to decrease the number of nodes that are evaluated by the minimax algorithm in its search tree. 3 / 63 Game Theory ( tic-tac-toe) Game Theory Autonomous Computational Methods Algebraic Equations Generalizations and Possible Limitations Autonomous Computational Methods Machine Learning Conclusions Figure: Game tree 4 / 63 Game Theory (GO) Game Theory Autonomous Computational Methods Algebraic Equations Generalizations and Possible Limitations Autonomous Computational Methods Machine Learning Conclusions Figure: Game tree 5 / 63 Game Theory (Winning Strategy) Game Theory Autonomous Computational Methods Algebraic Equations Generalizations and Possible Limitations Autonomous Computational Methods Machine Learning Conclusions Figure: Game tree 6 / 63 Basic Mathematical Operations Game Theory Autonomous Computational Addition Methods 1 + 1 = 2 Algebraic Equations 1 + 0 = 1 Generalizations and Possible Limitations 2 + (−1) = 1 Autonomous Computational Multiplication Methods 1 ∗ 0 = 0 Machine Learning i ∗ i = −1 Conclusions Algebra a + b = b + a a(b + c) = ab + ac etc.
    [Show full text]
  • 12121Ijwest01.Pdf
    International Journal of Web & Semantic Technology (IJWesT) Vol.12, No.1, January 2021 U-MENTALISM PATENT: THE BEGINNING OF CINEMATIC SUPERCOMPUTATION Luís Homem Centro de Filosofia das Ciências da Universidade de Lisboa ABSTRACT This paper discloses in synthesis a super-computation computer architecture (CA) model, presently a provisional Patent Application at INPI (nº 116408). The outline is focused on a method to perform computation at or near the speed of light, resorting to an inversion of the Princeton CA. It expands from isomorphic binary/RGB (typical) digital “images”, in a network of (UTM)s over Turing-machines (M)s. From the binary/RGB code, an arithmetic theory of (typical) digital images permits fully synchronous/orthogonal calculus in parallelism, wherefrom an exponential surplus is achieved. One such architecture depends on any “cell”-like exponential-prone basis such as the “pixel”, or rather the RGB “octet-byte”, limited as it may be, once it is congruent with any wave-particle duality principle in observable objects under the electromagnetic spectrum and reprogrammable designed. Well-ordered instructions in binary/RGB modules are, further, programming composed to alter the structure of the Internet, in virtual/virtuous eternal recursion/recurrence, under man-machine/machine-machine communication ontology. KEYWORDS U-Mentalism, Super-computation, Computer Architecture, Cybernetics, Programming Languages Design 1. INTRODUCTION This document is intended to serve as white paper to describe in the most possible composed details
    [Show full text]
  • Hardware Architecture and Basics of Parallel Computing
    Hardware architecture and basics of parallel computing Gian Franco Marras [email protected] Dipartimento Supercalcolo, Applicazioni e Innovazione (SCAI) CINECA - High Performance System Group Casalecchio di Reno (BO) – Italy www.cineca.it - www.cineca.it/en/index.htm Outline • Parallel Architectures & Parallel Programming • Message Passing Interface • Point-point comunication • Collective comunication • OpenMP • Directives • Runtime Library Routines • Environment Variables Parallel Architectures and Parallel Programming An overview What is a Supercomputer? A supercomputer is a computer that is at the frontline of current processing capacity, particulary speed of calculation. Supercomputers are used for highly calculation- intensive tasks such as problems involving quantum physics, weather forecasting, climate research, molecular modeling, physical simulations and a particular class of problems, known as Grand Challenge problems. What is Grand Challenge Problem? A grand challenge is a fundamental problem in science or engineering, with broad applications, whose solution would be enabled by the application of high performance computing resources that could become available in the near future. Which are Grand Challenges today? • Prediction of weather and global change • Material science and Superconductivity • Structural biology • Human genome • Astronomy • Turbolence • Design of hypersonic aircraft • Geophysics • ... Parallel computing Parallel computing is a form of computation in which many calculations are carried out simultaneously,
    [Show full text]