Разработка многопоточных приложений

What's New? Intel® Advisor XE 2015

Intel® Advisor XE 2015

Intel Advisor XE 2015 is a successor product to Intel® Advisor 2013. Intel Advisor provides a set of tools that help you decide where to add parallelism to serial parts of your applications. The key features provided by this new major version since the initial Intel Advisor 2013 release include:

  • Linux*
  • Microsoft Windows* (XP, Vista, 7)
  • Microsoft Windows* 8.x
  • C/C++
  • Fortran
  • Featured Product Support
  • Featured Support Topics
  • Intel® Advisor XE 2015 Release Notes

    This page provides the current Release Notes for the Intel® Advisor XE 2015 for Linux* and Windows* products.

     

     

    Intel® Advisor XE 2015
    for Windows*

    Intel® Advisor XE 2015
    for Linux

     What's New!

  • Разработчики
  • Linux*
  • Microsoft Windows* (XP, Vista, 7)
  • Microsoft Windows* 8.x
  • C/C++
  • Fortran
  • Intel® Advisor XE
  • Featured Product Support
  • OpenMP* WORKSHARE constructs now parallelize with Intel® Fortran Compiler 15.0

    The Intel® Fortran Compiler 15.0 now generates multi-threaded code for select instances of the OpenMP WORKSHARE and PARALLEL WORKSHARE constructs involving array assignments.  Previously, these were implemented with the OpenMP SINGLE construct, meaning that only single-threaded code was generated.

     

    Multithreaded code is not always generated for the statements inside the block of an OMP WORKSHARE construct. Some statements parallelize; others do not parallelize and instead execute sequentially inside an OMP SINGLE construct to preserve the correct semantics of WORKSHARE.

  • Разработчики
  • Профессорский состав
  • Apple OS X*
  • Linux*
  • Microsoft Windows* (XP, Vista, 7)
  • Microsoft Windows* 8.x
  • Сервер
  • Fortran
  • Продвинутый
  • OpenMP*
  • Intel® Inspector XE 2015 Release Notes

    This page provides the current Release Notes for the Intel® Inspector XE 2015 for Linux* and Windows* products.

     

     

    Intel® Inspector XE 2015
    for Windows*

    Intel® Inspector XE 2015
    for Linux*

     What's New!

  • Linux*
  • Microsoft Windows* (XP, Vista, 7)
  • Microsoft Windows* 8.x
  • .NET*
  • C/C++
  • Fortran
  • Продвинутый
  • Начинающий
  • Средний
  • Intel® Inspector XE
  • inspector xe
  • Параллельные вычисления
  • Многопоточность
  • 如何在offload程序中控制协处理器的执行环境

    offload编译模式下Intel编译器的offload运行时系统提供了两种机制让主机CPU程序对协处理器上的执行环境进行控制:

    1. 在主机系统上设置环境变量,然后将这些环境变量传递到协处理器上
    2. 在主机程序中调用相应的运行环境控制函数

     

    环境变量:

    缺省情况下,当offload发生时运行时系统会把主机程序执行环境中的所有环境变量全部复制到协处理器的执行环境中。用户可以通过定义环境变量“MIC_ENV_PREFIX”的值来改变这一默认行为。当该环境变量被赋予某个特定值之后,offload运行时系统将不再复制全部主机环境变量,而改为只复制那些以“MIC_ENV_PREFIX”的值加上下划线为前缀的那些环境变量;而且,在协处理器执行环境中对应的环境变量将不会保留这些前缀。通过这种方式,用户就可以在主机系统和协处理器上对同一名字的环境变量使用不同的值。例如在主机系统中已如下方式设置环境变量:

     

    MIC_ENV_PREFIX=ABC

    OMP_NUM_THREADS=8

  • Разработчики
  • Студенты
  • Linux*
  • C/C++
  • Fortran
  • Средний
  • Intel® Composer XE
  • Intel Parallel Composer XE
  • Инструменты для разработки
  • Параллельные вычисления
  • Using Intel® Advisor XE to Observe Memory Accesses Dynamically

    Intel® Advisor XE is the premiere tool from Intel for helping to parallelize your code, but it can also be used in other ways. For example, you can take advantage of the Intel Advisor XE special annotation ANNOTATE_OBSERVE_USES to track all memory accesses to a particular variable.

     

    Assume you have a source file, foo.cpp, that contains an allocation point like:

    int * pArray = new int[size];

     

    You want to detect all accesses to the pArray elements that happen within the scope of a function bar()where bar() is invoked from bar.cpp.

  • Разработчики
  • Linux*
  • Microsoft Windows* (XP, Vista, 7)
  • Microsoft Windows* 8.x
  • C/C++
  • Fortran
  • Intel® Advisor XE
  • Featured Product Support
  • Featured Support Topics
  • Отладка
  • Параллельные вычисления
  • Многопоточность
  • Intel Software Conference 2014

     A Intel Software Brasil realizou neste mês o Intel Software Conference 2014, que aconteceu na Universidade Estácio de Sá (Rio de Janeiro) nos dias 26 e 27 de Maio e no IMAM (São Paulo) nos dias 28,29 e 30 de Maio.

    Foram realizadas palestras e "round tables" ministradas por profissionais da Intel do Brasil, Estados Unidos e Alemanha cobrindo dois temas: Computação Paralela e de Alto Desempenho nos primeiros quatro dias (RJ e SP) e Desenvolvimento Android no último dia (somente em São Paulo).  

    Confira logo abaixo os slides das apresentações realizadas.

  • Разработчики
  • Партнеры
  • Профессорский состав
  • Студенты
  • Android*
  • Linux*
  • Сервер
  • C#
  • C/C++
  • Fortran
  • Продвинутый
  • Средний
  • ПО для распределенных вычислений (кластеров)
  • Intel® Parallel Studio XE
  • Intel® Advanced Vector Extensions
  • Intel® Streaming SIMD Extensions
  • Интерфейс проверки сообщений
  • OpenCL*
  • OpenMP*
  • Оптимизация
  • Параллельные вычисления
  • Векторизация
  • Подписаться на Разработка многопоточных приложений