Enabling Connectionless DAPL UD in the Intel® MPI Library

What is DAPL UD?

Traditional InfiniBand* support involves MPI message transfer over the Reliable Connection (RC) protocol. While RC is long-standing and rich in functionality, it does have certain drawbacks: since it requires that each pair of processes setup a one-to-one connection at the start of the execution, memory consumption could (at the worst case) grow linearly as more MPI ranks are added and the number of pair connections grows.

  • Разработчики
  • Linux*
  • Microsoft Windows* (XP, Vista, 7)
  • Сервер
  • C/C++
  • Fortran
  • Средний
  • Intel® MPI Library
  • user datagrams
  • ud
  • dapl ud
  • IB
  • InfiniBand
  • scalability
  • Интерфейс проверки сообщений
  • Кластерные вычисления
  • Ultrabook Part 2: Intel® VTune™ Amplifier XE 2011 with Windows 8* and Visual Studio* 2012 RC

    As I continue to explore different Ultrabook capabilities, in this blog I decided to look into a powerful threading and performance optimization tool for C/C++, .NET, and FORTRAN developers who need to understand an application's serial and parallel behavior to improve performance and scalability: Intel® VTune™ Amplifier XE 2011.

    Classroom challenge: Matrix Multiplication, Performance and Scalability in OpenMP

    A simple, widely known and studied problem was posed to the class students: matrix multiplication. We made an internal contest, which was to obtain the fastest serial code in which the students learned a lot about compiler optimizations, and even more, the effect of caches in code performance. The objective of the contest was to extrapoloate this exercise into a massive multicore architecture. Students were given kickstart code with a naive C using an OpenMP implemention of the problem, and a series of rules.

    Parallelization of SMOKE Gaming Demo via Intel® Threading Building Blocks

    This paper describes the steps in the process of characterizing and optimizing the already parallel SMOKE Gaming Demo [1] using Intel's software suite of tools. We argue that the techniques used here are applicable to other gaming codes as well.
  • Компоненты Intel® Threading Building Blocks
  • scalability
  • Разработка игр
  • Графика
  • Параллельные вычисления
  • Многопоточность
  • Courseware - Programming Language Design

    Portable Parallel Programs using Declarative Programming and Architecture-aware Libraries

    Material Type:

    Article / White paper

    ISN Logo

    Technical Format:

    PDF document


  • Профессорский состав
  • Студенты
  • courseware
  • programming languages
  • Programming Language Design
  • scalability
  • portability
  • Parallel Programming
  • Declarative Languages
  • Performance and Portability Benefits of Ct

    We explain at a high level how Ct works with large problems, uses TBB for threading, and has performance-driven application libraries that port to new Intel Architectures.
  • Intel® Integrated Performance Primitives
  • Библиотека Intel® Math Kernel Library
  • Компоненты Intel® Threading Building Blocks
  • Architecture
  • FFT
  • compilation
  • lapack
  • BLAS
  • scalability
  • runtime
  • memory bottlenecks
  • modularity
  • fusion
  • simd-ization
  • Векторизация
  • Подписаться на scalability