Technical Article

Оптимизировали, оптимизировали, да не выоптимизировали!

Оптимизация? Конечно, каждый сталкивался с данной задачей при разработке своих, сколь-нибудь значительных, требующих определённых вычислений, приложений. При этом способов оптимизировать код существует огромное множество, и, как следствие, различных путей сделать это в автоматическом режиме с помощью опций компилятора. Вот здесь и возникает проблема – как выбрать то, что нужно нам и не запутаться?

An Overview of Advanced Server-Based Networking Technologies

This guide is an overview of tools for advanced technologies in SDN and NFV. It covers DPDK, Open vSwitch, SR-IOV, Fd.io and VPP, and describes virtualization scenarios using one or more of the tools.
  • Networking
  • Network Functions Virtualization (NFV)
  • Software Defined Networking (SDN)
  • Intel® Advisor on Cray* Systems

    Introduction

    Intel® Advisor provides two analysis workflows to ensure that C, C++, and Fortran applications make the most of today's processor architectures: a Vectorization Workflow and a Threading Workflow.

    Vectorization Workflow: This workflow lets you identify loops that will benefit most from vectorization, identify issues preventing vectorization, estimate the benefit of alternative data reorganizations, and analyze instruction mix in the application.

  • Linux*
  • Unix*
  • Beginner
  • Intermediate
  • Intel® Parallel Studio XE
  • Intel® Advisor
  • Cray
  • Minimize Node.js* I/O Bottlenecks with Linux Kernel Library and Data Plane Developer Kit

    In this experiment a Node.js application, Security Compass Let’s Chat*, runs on top of the Linux Kernel Library (LKL) and the DPDK for better I/O throughput. See how the binding between Node.js and DPDK using LKL was implemented.
  • Networking
  • Node.js*
  • 面向英特尔 Python* 分发包的 Docker 映像

    我们发布了面向英特尔 Python 的 Docker 映像。如欲获取映像,请访问Docker Hub,访问 GitHub 获取 Dockerfile。我们为 Python 2 和 Python 3 提供映像,映像分为核心配置和完整配置。核心配置包含 NumPy/Scipy 和关联组件,完整配置包含我们所有分发包。 如果您想自定义 Docker 映像,可以从我们发布的 Dockerfile 入手,也可以使用 Docker FROM 命令,将映像用作基础。

    入门知识:

    Docker 是一项热门的 Linux 容器技术,通过一个简单的命令行接口,支持服务和应用的部署与可重复性。 更多信息详见 Docker 官方网站,https://www.docker.com/

    获取面向分发包的 Docker 映像:

  • Artificial Intelligence
  • Intel® Distribution for Python*
  • 借助 Anaconda* 安装英特尔® Python* 分发包和英特尔® 性能库

    我们与 Continuum Analytics* 公司通力合作,致力于使用 Conda* 软件包管理器和 Anaconda 云* 简化英特尔® Python* 分发包和社区论坛支持的英特尔® 性能库(如英特尔® 数学核心函数库(英特尔® MKL))。最低版本要求为 conda 4.1.11,所以,请首先更新您的 conda。

    conda update conda

    通知 conda 选择英特尔软件包(如果可用的话),而非默认软件包。

    conda config --add channels intel

    安装英特尔® Python* 分发包

    建议您在安装时创建一个新环境。执行以下命令,安装核心 python3 环境:

  • Artificial Intelligence
  • Python*
  • Intel® Distribution for Python*
  • Intel® Math Kernel Library
  • installation
  • Conda
  • Anaconda
  • 隆重推出英特尔® Python* 分发包

    我非常高兴地宣布英特尔推出了首款支持 Anaconda* 的英特尔® Python 分发包*。英特尔为何要创建 python 分发包?我们希望为 python 用户提供他们习以为常的高效,同时确保性能不受影响。我们的客户告诉我们,很难找到一款充分利用最新款处理器的 Python。单路至强融核系统每周期可以执行 4600 次单精度浮点运算,但是某些常用的 python 软件堆栈每周期浮点运算次数仅为 4 次,这是因为它们无法利用多个内核或最新 SIMD 指令。

    Tuning SIMD vectorization when targeting Intel® Xeon® Processor Scalable Family

    Introduction

    The Intel® Xeon® Processor Scalable Family is based on the server microarchitecture codenamed Skylake.

    For best possible performance on the Intel Xeon Processor Scalable Family, applications should be compiled with processor-specific option [Q]xCORE-AVX512 using the Intel® C++ and Fortran compilers. Note that applications built with this option will not run on non-Intel or older instruction-sets based processors.

  • Linux*
  • Microsoft Windows* 10
  • C/C++
  • Fortran
  • Development Tools
  • Parallel Computing
  • Vectorization
  • Using Intel® Advisor and VTune™ Amplifier with MPI

    Introduction

    This article describes how to use Intel® Advisor and VTune™ Amplifier in a Linux* distributed environment. While specifically designed to collect performance data at the node and core level, both tools can be used with MPI. The document covers basic utilization with an MPI launcher from the command line, as well as more advanced customizations.

  • Linux*
  • Intel® Parallel Studio XE
  • Intel® Advisor
  • Intel® VTune™ Amplifier
  • Cluster Computing
  • Parallel Computing
  • Subscribe to Technical Article