DOCSLIB.ORG

Interim Progress Report: Public Prototype Software Release and Development Infrastructure

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Interim Progress Report: Public Prototype Software Release and Development Infrastructure E-Infrastructures H2020- INFRAEDI-2018-2020 INFRAEDI-01-2018: Pan-European High Performance Computing infrastructure and services (PRACE) PRACE-6IP PRACE Sixth Implementation Phase Project Grant Agreement Number: INFRAEDI-823767 D8.3 Interim Progress Report: Public Prototype Software Release and Development Infrastructure Final Version: 1.2 Author(s): Fabio Affinito, Joost VandeVondele, Alex Upton Date: 29.04.2020 D8.3 Interim Progress Report: Public Prototype Software Release and Development Infrastructure Project and Deliverable Information Sheet PRACE Project Project Ref. №: INFRAEDI-823767 Project Title: PRACE Sixth Implementation Phase Project Project Web Site: http://www.prace-project.eu Deliverable ID: < D8.3 > Deliverable Nature: <Report> Dissemination Level: Contractual Date of Delivery: PU 30/04/2020 Actual Date of Delivery: 30/04/2020 EC Project Officer: Leonardo Flores Añover Document Control Sheet Title: Interim Progress Report: Public Prototype Software Release Document and Development Infrastructure ID: D8.3 Version: 1.2 Status: Final Available at: http://www.prace-project.eu Software Tool: Microsoft Word 2016 File(s): D8.3 Written by: Fabio Affinito, Joost VandeVondele, Alex Upton PRACE-6IP- INFRAEDI-823767 i 29.04.2020 D8.3 Interim Progress Report: Public Prototype Software Release and Development Infrastructure Authorship Contributors: Fabio Affinito, Constantia Alexandrou, Momme Allalen, Simone Bacchio, Marco Bettiol, Mauro Bianco, John Biddiscombe, Fabian Boesch, Ricard Borrel, Matic Brank, David Brayford, John Brennan, Dirk Brömmel, Tomas Brzobohaty, Mark Bull, Junxian Chew, Zahra Chitgar, Laurent Chôné, Olivier Coulaud, Tilman Dannert, Edoardo Di Napoli, Jacob Finkenrath, Urs Ganse, Christophe Geuzaine, Paul Gibbon, Luc Giraud, Aleksander Grm, Kenneth Hanley, Berk Hess, Koen Hillewaert, Victor Holanda, Guillaume Houzeaux, Luigi Iapichino, Alberto Invernizzi, Ferdinand Jamitzky, Niclas Jansson, Joe Jordan, Prashanth Kanduri, Sebastian Keller, Leon Kos, Giannis Koutsou, Marcin Krotkiewski, Carlos Lopez, Martti Louhivuori, Michele Martone, Michal Merta, Niall Moran, Teodor Nikolov, Henrik Nortamo, Lee O'Riordan, Phillip Otte, Dejan Penko, Adam Peplinski, Janez Povh, Lara Querciagrossa, Philipp Schlatter, Gregor Simič, Ujjwal Sinha, Raffaele Solcà, Thomas Toulorge, Alex Upton, Joost VandeVondele, Ivona Vasileska, Xinzhe Wu, Shuhei Yamamoto, Jan Zapletal, Artem Zhmurov Reviewed by: Florian Berberich, JUELICH Cédric Jourdain, CINES Approved by: MB/TB Document Status Sheet Version Date Status Comments 0.1 31/03/2020 1st Draft Missing executive summary, introduction and conclusions 0.2 02/04/2020 2nd Draft (ready for Added executive internal review) summary, introduction and conclusions 0.3 14/04/2020 3rd Draft (following Changed spelling to internal review) British English, changed formatting of links to PRACE-6IP- INFRAEDI-823767 ii 29.04.2020 D8.3 Interim Progress Report: Public Prototype Software Release and Development Infrastructure references, minor changes to text and overall formatting 1.0 21/04/2020 Minor formatting changes and additional references 1.1 22/04/2020 1.2 29/04/202 Final Updated contributors PRACE-6IP- INFRAEDI-823767 iii 29.04.2020 D8.3 Interim Progress Report: Public Prototype Software Release and Development Infrastructure Document Keywords Keywords: PRACE, HPC, Research Infrastructure, Exascale, Forward-looking software solutions Disclaimer This deliverable has been prepared by the responsible Work Package of the Project in accordance with the Consortium Agreement and the Grant Agreement n° INFRAEDI-823767. It solely reflects the opinion of the parties to such agreements on a collective basis in the context of the Project and to the extent foreseen in such agreements. Please note that even though all participants to the Project are members of PRACE AISBL, this deliverable has not been approved by the Council of PRACE AISBL and therefore does not emanate from it nor should it be considered to reflect PRACE AISBL’s individual opinion. Copyright notices 2020 PRACE Consortium Partners. All rights reserved. This document is a project document of the PRACE project. All contents are reserved by default and may not be disclosed to third parties without the written consent of the PRACE partners, except as mandated by the European Commission contract INFRAEDI-823767 for reviewing and dissemination purposes. All trademarks and other rights on third party products mentioned in this document are acknowledged as own by the respective holders. PRACE-6IP- INFRAEDI-823767 iv 29.04.2020 D8.3 Interim Progress Report: Public Prototype Software Release and Development Infrastructure Table of Contents Project and Deliverable Information Sheet .................................................................................. i Document Control Sheet ................................................................................................................. i Document Status Sheet ................................................................................................................. ii Document Keywords ..................................................................................................................... iv List of Figures .............................................................................................................................. vii List of Tables ................................................................................................................................ vii References and Applicable Documents ..................................................................................... vii List of Acronyms and Abbreviations ........................................................................................... ix List of Project Partner Acronyms ................................................................................................. x Executive Summary ....................................................................................................................... 1 1 Introduction ............................................................................................................................. 2 2 PiCKeX- Particle Kinetic codes for Exascale plasma simulation ....................................... 3 2.1 Introduction and summary ............................................................................................. 3 2.2 Prototype software release .............................................................................................. 3 2.3 Development infrastructure ............................................................................................ 3 2.4 Planned work for the next six months ........................................................................... 4 3 MoPHA – Modernisation of Plasma Physics Simulation Codes for Heterogeneous Exascale Architectures ................................................................................................................... 5 3.1 Introduction and summary ............................................................................................. 5 3.2 Prototype software release .............................................................................................. 5 3.3 Development infrastructure ............................................................................................ 6 3.4 Status and outlook Planned work for the next six months .......................................... 6 4 NB-LIB: Performance portable library for N-body force calculations at the Exascale ... 8 4.1 Introduction and summary ............................................................................................. 8 4.2 Prototype software release .............................................................................................. 8 4.3 Development infrastructure ............................................................................................ 9 4.4 Planned work for the next six months ........................................................................... 9 5 LoSync – Synchronisation reducing programming techniques and runtime support ... 10 5.1 Introduction and summary ........................................................................................... 10 5.2 Project Prototype software release .............................................................................. 10 5.3 Development infrastructure .......................................................................................... 11 5.4 Planned work for the next six months ......................................................................... 11 PRACE-6IP- INFRAEDI-823767 v 29.04.2020 D8.3 Interim Progress Report: Public Prototype Software Release and Development Infrastructure 6 FEM/BEM based domain decomposition solvers .............................................................. 12 6.1 Introduction and summary ........................................................................................... 12 6.2 Prototype software release ............................................................................................ 12 6.3 Development infrastructure .......................................................................................... 13 6.4 Planned work for the next six months ......................................................................... 13 7 Performance portable linear algebra .................................................................................. 14 7.1 Introduction and summary ..........................................................................................
Load more

Recommended publications
  • Debian Developer's Reference Version 12.0, Released on 2021-09-01
    Debian Developer’s Reference Release 12.0 Developer’s Reference Team 2021-09-01 CONTENTS 1 Scope of This Document 3 2 Applying to Become a Member5 2.1 Getting started..............................................5 2.2 Debian mentors and sponsors......................................6 2.3 Registering as a Debian member.....................................6 3 Debian Developer's Duties 9 3.1 Package Maintainer's Duties.......................................9 3.1.1 Work towards the next stable release............................9 3.1.2 Maintain packages in stable .................................9 3.1.3 Manage release-critical bugs.................................. 10 3.1.4 Coordination with upstream developers............................ 10 3.2 Administrative Duties.......................................... 10 3.2.1 Maintaining your Debian information............................. 11 3.2.2 Maintaining your public key.................................. 11 3.2.3 Voting.............................................. 11 3.2.4 Going on vacation gracefully.................................. 12 3.2.5 Retiring............................................. 12 3.2.6 Returning after retirement................................... 13 4 Resources for Debian Members 15 4.1 Mailing lists............................................... 15 4.1.1 Basic rules for use....................................... 15 4.1.2 Core development mailing lists................................. 15 4.1.3 Special lists........................................... 16 4.1.4 Requesting new
    [Show full text]
  • Tuto Documentation Release 0.1.0
    Tuto Documentation Release 0.1.0 DevOps people 2020-05-09 09H16 CONTENTS 1 Documentation news 3 1.1 Documentation news 2020........................................3 1.1.1 New features of sphinx.ext.autodoc (typing) in sphinx 2.4.0 (2020-02-09)..........3 1.1.2 Hypermodern Python Chapter 5: Documentation (2020-01-29) by https://twitter.com/cjolowicz/..................................3 1.2 Documentation news 2018........................................4 1.2.1 Pratical sphinx (2018-05-12, pycon2018)...........................4 1.2.2 Markdown Descriptions on PyPI (2018-03-16)........................4 1.2.3 Bringing interactive examples to MDN.............................5 1.3 Documentation news 2017........................................5 1.3.1 Autodoc-style extraction into Sphinx for your JS project...................5 1.4 Documentation news 2016........................................5 1.4.1 La documentation linux utilise sphinx.............................5 2 Documentation Advices 7 2.1 You are what you document (Monday, May 5, 2014)..........................8 2.2 Rédaction technique...........................................8 2.2.1 Libérez vos informations de leurs silos.............................8 2.2.2 Intégrer la documentation aux processus de développement..................8 2.3 13 Things People Hate about Your Open Source Docs.........................9 2.4 Beautiful docs.............................................. 10 2.5 Designing Great API Docs (11 Jan 2012)................................ 10 2.6 Docness.................................................
    [Show full text]
  • Alinex Data Store
    Alinex Data Store Read, work and write data structures to differents stores Alexander Schilling Copyright © 2019 - 2021 <a href="https://alinex.de">Alexander Schilling</a> Table of contents Table of contents 1. Home 6 1.1 Alinex Data Store 6 1.1.1 Usage 6 1.1.2 Debugging 6 1.1.3 Module Usage 7 1.1.4 Chapters 7 1.1.5 Support 7 1.2 Command Line Usage 8 1.2.1 Input 8 1.2.2 Output 8 1.2.3 Transform Files 9 1.2.4 Using Definition 9 1.2.5 Examples 9 1.3 Last Changes 10 1.3.1 Version 1.16.0 - (12.05.2021) 10 1.3.2 Version 1.15.0 - (02.01.2021) 10 1.3.3 Version 1.13.0 - (16.06.2020) 10 1.3.4 Version 1.12.0 - (27.01.2020) 10 1.3.5 Version 1.11.0 - (13.01.2020) 11 1.3.6 Version 1.10.0 - (22.11.2019) 11 1.3.7 Version 1.9.1 - (13.11.2019) 11 1.3.8 Version 1.8.0 - (31.10.2019) 11 1.3.9 Version 1.7.0 - (13.10.2019) 11 1.3.10 Version 1.6.0 - (01.10.2019) 11 1.3.11 Version 1.5.0 - (28.08.2019) 12 1.3.12 Version 1.4.0 - (15.08.2019) 12 1.3.13 Version 1.3.0 - (6.08.2019) 12 1.3.14 Version 1.2.0 - (22.06.2019) 13 1.3.15 Version 1.1.0 - (17.05.2019) 13 1.3.16 Version 1.0.0 - (12.05.2019) 13 1.3.17 Version 0.7.0 (29.04.2019) 13 1.3.18 Version 0.6.0 (26.04.2019) 14 1.3.19 Version 0.5.0 (19.04.2019) 14 1.3.20 Version 0.4.0 (17.04.2019) 14 1.3.21 Version 0.3.0 (15.04.2019) 14 - 2/80 - Copyright © 2019 - 2021 <a href="https://alinex.de">Alexander Schilling</a> Table of contents 1.3.22 Version 0.2.0 (12.04.2019) 14 1.3.23 Version 0.1.0 (0t.04.019) 14 1.4 Roadmap 16 1.4.1 Add Protocols 16 1.4.2 Multiple sources 16 1.5 Privacy statement 17 2.
    [Show full text]
  • Towards the First Practical Applications of Quantum Computers
    Towards the First Practical Applications of Quantum Computers by Kevin J. Sung A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy (Computer Science and Engineering) in the University of Michigan 2020 Doctoral Committee: Professor Christopher Peikert, Co-Chair Adjunct Professor Yaoyun Shi, Co-Chair Dr. Ryan Babbush, Google Professor John P. Hayes Professor Emeritus Kim Winick Kevin J. Sung [email protected] ORCID iD: 0000-0001-6459-6374 ©2020 Kevin J. Sung To my family ii Acknowledgments This thesis was made possible by my supportive advisors Yaoyun Shi and Christopher Peikert, my friends, and my family. I would like to thank the Google AI Quantum team for hosting me while I performed much of the research in this thesis. I cannot express how lucky I feel to have had ac- cess to their state-of-the-art quantum computing hardware. The experiments on this hardware that I present in this thesis were the result of large team-wide collaborations. iii TABLE OF CONTENTS Dedication ....................................... ii Acknowledgments ................................... iii List of Figures ..................................... vii List of Tables ...................................... xiii List of Algorithms ................................... xv List of Appendices ................................... xvi Abstract ......................................... xvii Chapter 1 Introduction ..................................... 1 1.1 Quantum computing in the NISQ era....................1 1.1.1 The
    [Show full text]
  • D4.1 Source Code and Documentation Repository
    D4.1 Source code and documentation repository Co-funded by the Horizon 2020 Framework Programme of the European Union GRANT AGREEMENT NUMBER: 842009 - NIVA DELIVERABLE NUMBER D4.1 DELIVERABLE TITLE Source code and documentation repository RESPONSIBLE AUTHOR Konstantinos Kountouris – Nikolaos Galanis, OPEKEPE Greece 1 GRANT AGREEMENT N. 842009 PROJECT ACRONYM NIVA PROJECT FULL NAME A New IACS Vision in Action STARTING DATE (DUR.) 1/06/2019 ENDING DATE 30/05/2022 PROJECT WEBSITE COORDINATOR Sander Janssen ADDRESS Droevendaalsesteeg 1, Wageningen REPLY TO [email protected] PHONE +31 317 481908 EU PROJECT OFFICER Mrs. Francisca Cuesta Sanchez WORKPACKAGE N. | TITLE WP4 | Knowledge Information System WORKPACKAGE LEADER 8 - AGEA DELIVERABLE N. | TITLE D4.1 | Source code and documentation repository RESPONSIBLE AUTHOR Konstantinos Kountouris – Nikolaos Galanis, OPEKEPE Greece REPLY TO [email protected], [email protected] DOCUMENT URL DATE OF DELIVERY (CONTRACTUAL) 31 August 2019 (M3) DATE OF DELIVERY (SUBMITTED) 30 September 2019 (M4) VERSION | STATUS V1.0| Final NATURE Report DISSEMINATION LEVEL PUBLIC Konstantinos Kountouris – Nikolaos Galanis - Ioannis Andreou, OPEKEPE AUTHORS (PARTNER) Greece 2 VERSION MODIFICATION(S) DATE AUTHOR(S) Konstantinos Kountouris – Nikolaos Galanis - Ioannis 1.0 Final version 24 August 2019 Andreou, OPEKEPE Greece 3 Table of Contents Choosing the proper tool ........................................................................................ 5 Requirements and Assumptions ...........................................................................
    [Show full text]
  • Software Engineer Is .Jusiak.Net Kr Is @Jusiak.Net (0) 791-384-1386
    Krzysztof (Kris) Jusiak Software Engineer http://kr is .jusiak.net kr is @jusiak.net (0) 791-384-1386 Education 2005 - 2010 Wroclaw University of Technology Wroclaw (Poland) MSc in Computer Science, specialised in Software Engineering (Top grade) Employment 2013 – Present King London (United Kingdom) Game/Software Developer (Mobile) King is a worldwide leader in casual games with more than 30 billion games played per month globally. We are a leading interactive entertainment company for the mobile world. Our mission is to provide highly engaging content to our audience to match their mobile lifestyles: anywhere, anytime, through any platform and on any device. Software Developer in a scrum team responsible for development and releases of mobile games played by millions active daily players. 90% of my job is focused on developing software using C++14 standard for different platforms such as, iOS, Android and Facebook (HTML5 - Emscripten). My core role is to provide high quality features and review/refactor already implemented. I am also involved in recruitment process by being a technical expert on interviews. I have done a lot of improvements to the projects I have been involved in, such as, performance/compile times optimizations, introduction of static analysis tools as well as a replacement of Service Locator pattern by Dependency Injection. • Implementing and releasing multi-platform games played by more than 100 millions active daily players • Reduced time to render the textures by 10% by changing loading files caching mechanism • Implemented an integration test framework which eliminated commonly reoccurring issues 2009 – 2013 Nokia Networks Wroclaw (Poland) Software Engineer Nokia Networks is the world’s specialist in mobile broadband, which helps enable end users to do more than ever before with the world’s most efficient mobile networks, the intelligence to maximize their value and the services to make it all work together.
    [Show full text]
  • Easybuild Documentation Release 20210907.0
    EasyBuild Documentation Release 20210907.0 Ghent University Tue, 07 Sep 2021 08:55:41 Contents 1 What is EasyBuild? 3 2 Concepts and terminology 5 2.1 EasyBuild framework..........................................5 2.2 Easyblocks................................................6 2.3 Toolchains................................................7 2.3.1 system toolchain.......................................7 2.3.2 dummy toolchain (DEPRECATED) ..............................7 2.3.3 Common toolchains.......................................7 2.4 Easyconfig files..............................................7 2.5 Extensions................................................8 3 Typical workflow example: building and installing WRF9 3.1 Searching for available easyconfigs files.................................9 3.2 Getting an overview of planned installations.............................. 10 3.3 Installing a software stack........................................ 11 4 Getting started 13 4.1 Installing EasyBuild........................................... 13 4.1.1 Requirements.......................................... 14 4.1.2 Using pip to Install EasyBuild................................. 14 4.1.3 Installing EasyBuild with EasyBuild.............................. 17 4.1.4 Dependencies.......................................... 19 4.1.5 Sources............................................. 21 4.1.6 In case of installation issues. .................................. 22 4.2 Configuring EasyBuild.......................................... 22 4.2.1 Supported configuration
    [Show full text]
  • Arxiv:1812.09167V1 [Quant-Ph] 21 Dec 2018 It with the Tex Typesetting System Being a Prime Example
    Open source software in quantum computing Mark Fingerhutha,1, 2 Tomáš Babej,1 and Peter Wittek3, 4, 5, 6 1ProteinQure Inc., Toronto, Canada 2University of KwaZulu-Natal, Durban, South Africa 3Rotman School of Management, University of Toronto, Toronto, Canada 4Creative Destruction Lab, Toronto, Canada 5Vector Institute for Artificial Intelligence, Toronto, Canada 6Perimeter Institute for Theoretical Physics, Waterloo, Canada Open source software is becoming crucial in the design and testing of quantum algorithms. Many of the tools are backed by major commercial vendors with the goal to make it easier to develop quantum software: this mirrors how well-funded open machine learning frameworks enabled the development of complex models and their execution on equally complex hardware. We review a wide range of open source software for quantum computing, covering all stages of the quantum toolchain from quantum hardware interfaces through quantum compilers to implementations of quantum algorithms, as well as all quantum computing paradigms, including quantum annealing, and discrete and continuous-variable gate-model quantum computing. The evaluation of each project covers characteristics such as documentation, licence, the choice of programming language, compliance with norms of software engineering, and the culture of the project. We find that while the diversity of projects is mesmerizing, only a few attract external developers and even many commercially backed frameworks have shortcomings in software engineering. Based on these observations, we highlight the best practices that could foster a more active community around quantum computing software that welcomes newcomers to the field, but also ensures high-quality, well-documented code. INTRODUCTION Source code has been developed and shared among enthusiasts since the early 1950s.
    [Show full text]
  • Erik Lindahl
    HPC Software Engineering Erik Lindahl XSEDE/PRACE/RIKEN/SciNet HPC Summer School Ostrava, CZ, 2018 Extra Q & A session: Here (or outside at the tables) 12.45 today! “The application of a systematic, disciplined, quantifiable approach to the development, operation and maintenance of software, and the study of these approaches, that is, the application of engineering to software.” Experiences from 20 years of GROMACS development The GROMACS picture until early 2011 Source code repository: • Simulation hardware project, turned software CVS • Early development based on our own needs • Turned GPL in 2001, LGPL in 2012 Build Chain: • Organic growth of development Automake/Autoconf/libtool • Roughly 10-15 core developers Bug Tracking: • Another 15-20 active contributors Bugzilla • Currently 3,076,420 lines of C++11 code (“C++11”) • Over the years we have used Fortran, C, Assembly Testing: • Lots of old code. Lots of new code. Lots of complicated (read: bad) code written by scientists Software Scientist engineer • Trained in physics, • Trained in CS/software chemistry, etc. • Care about their problem • Care about their code • Care about short-term • Care about long-term deadlines maintenance • New code = asset • New code = liability • Writes more code than • Reads much more code she reads than she writes Without proper software engineering, we are building a technical debt that sooner or later will have to be paid. “Technical Debt is a wonderful metaphor developed by Ward Cunningham to help us think about this problem. In this metaphor, doing things the quick and dirty way sets us up with a technical debt, which is similar to a financial debt.
    [Show full text]
  • How Google Tests Software
    How Google Tests Software James Whittaker Jason Arbon Jeff Carollo • nTr Addison-Wesley Upper Saddle River, NJ • Boston • Indianapolis • San Francisco New York • Toronto • Montreal • London • Munich • Paris • Madrid Capetown • Sydney • Tokyo • Singapore • Mexico City ' ' ^ : Г: С : '. , Table of Contents Foreword by Alberto Savoia Xlll Foreword by Patrick Copeland xvii Preface ХХШ Chapter 1 Introduction to Google Software Testing 1 Quality^Test 5 Roles 6 Organizational Structure 8 Crawl, Walk, Run 10 Types of Tests 12 Chapter 2 The Software Engineer in Test 15 The Life of an SET 17 Development and Test Workflow 17 Who Are These SETs Anyway? 22 The Early Phase of a Project 22 Team Structure 24 Design Docs 25 Interfaces and Protocols 27 Automation Planning 28 Testability 29 SET Workflow: An Example 32 Test Execution 40 Test Size Definitions 41 Use of Test Sizes in Shared Infrastructure 44 Benefits of Test Sizes 46 Test Runtime Requirements 48 Case 1: Change in Common Library 52 Test Certified 54 An Interview with the Founders of the Test Certified Program 57 Interviewing SETs 62 An Interview with Tool Developer Ted Mao 68 An Interview with Web Driver Creator Simon Stewart 70 How Google Tests Software Chapter 3 The Test Engineer 75 A User-Facing Test Role 75 The Life of а ТЕ 76 Test Planning 79 Risk 97 Life of a Test Case 108 Life of a Bug 113 Recruiting TEs 127 Test Leadership at Google 134 Maintenance Mode Testing 137 Quality Bots Experiment 141 BITE Experiment 153 Google Test Analytics 163 Free Testing Workflow 169 External Vendors 173
    [Show full text]
  • Arxiv:1302.3247V5 [Quant-Ph] 10 Dec 2014 Pairwise Interaction
    Permutation-invariant quantum codes Yingkai Ouyang University of Waterloo, Waterloo, Ontario, Canada and Singapore University of Technology and Design, Singapore∗ A quantum code is a subspace of a Hilbert space of a physical system chosen to be correctable against a given class of errors, where information can be encoded. Ideally, the quantum code lies within the ground space of the physical system. When the physical model is the Heisenberg ferromagnet in the absence of an external magnetic field, the corresponding ground-space contains all permutation-invariant states. We use techniques from combinatorics and operator theory to construct families of permutation-invariant quantum codes. These codes have length proportional to t2; one family of codes perfectly corrects arbitrary weight t errors, while the other family of codes approximately correct t spontaneous decay errors. The analysis of our codes' performance with respect to spontaneous decay errors utilizes elementary matrix analysis, where we revisit and extend the quantum error correction criterion of Knill and Laflamme, and Leung, Chuang, Nielsen and Yamamoto. PACS numbers: 03.65.Aa,03.67.Pp,05.30.-d,75.10.Pq I. INTRODUCTION label the particles in the system, and e = fi; jg labels the exchange interactions in the system. Here Je and A quantum bit (qubit) is a fundamental resource Si denote the exchange constants and the vector of required in many quantum information theoretic tasks, spin operators respectively. Since exchange operators such as in quantum cryptographic protocols [1] and in essentially swap particles (see ex. 1.9 of Ref. [12] quantum computers [2]. To combat decoherence, a two- or Ref.
    [Show full text]
  • Interfacing Epetra to the RSB Sparse Matrix Format for Shared-Memory Performance
    Interfacing Epetra to the RSB sparse matrix format for shared-memory performance Michele Martone High Level Support Team Max Planck Institute for Plasma Physics Garching bei M¨unchen,Germany 5th European Trilinos User Group Meeting Garching bei M¨unchen, Germany April 19, 2016 1 / 18 Background: sparse kernels can be performance critical Sparse kernel Operation definition1 SpMV: Matrix-Vector Multiply \y β y + α A x" SpMV-T: (Transposed) \y β y + α AT x" SpSV : Triangular Solve \x α L−1 x" SpSV-T : (Transposed) \x α L−T x" Epetra_... Epetra_CrsMatrix I CRS (Compressed Row Storage) versatile and straightforward I class Epetra CrsMatrix can rely on Intel MKL 1A is a sparse matrix, L sparse triangular, x; y vectors or multi-vectors, α; β scalars. 2 / 18 Background: optimized sparse matrix classes Epetra_... Epetra_CrsMatrix Epetra_OskiMatrix I OSKI (Optimized Sparse Kernels Interface) library, by R.Vuduc I kernels for iterative methods, e.g. SpMV, SpSV I autotuning framework I OSKI + Epetra = class Epetra OskiMatrix, by I.Karlin 3 / 18 Background: librsb I a stable \Sparse BLAS"-like kernels library: I Sparse BLAS API (blas sparse.h) I own API (rsb.h) I LGPLv3 licensed I librsb-1.2 at http://librsb.sourceforge.net/ I OpenMP threaded 2 I C/C++/FORTRAN interface 2ISO-C-BINDING for own and F90 for Sparse BLAS 4 / 18 What can librsb do 3 I can be multiple times faster than Intel MKL's CRS in I symmetric/transposed sparse matrix multiply (SpMV) I multi-RHS (SpMM) I large matrices I threaded SpSV/SpSM (sparse triangular solve) I iterative methods ops: scaling, extraction, update, ..
    [Show full text]