SIMD 编程的优势 --TickerTape Part 2

Ticker Tape 是一种技术演示,旨在鼓励开发人员在粒子系统中执行更为复杂的操作。参与该演示的开发人员会运用大量技术,来提高包括多线程和针对英特尔® SIMD 流指令扩展(SSE)的优化等在内的性能
Authored by admin Last updated on 01/24/2018 - 12:12

Эмуляция ткани с использованием структур массивов и Intel® Advanced Vector Extensions (Intel® AVX) с поддержкой 256-битных команд

В данной статье описывается программа, в которой реализован эффективный алгоритм эмуляции ткани с использованием нового набора инструкций Intel® AVX. Код программы доступен для скачивания.
Authored by admin Last updated on 01/24/2019 - 16:28

利用英特尔® SIMD 流指令扩展和英特尔® 高级矢量扩展指令集的图像处理加速技术

This article details optimized implementations of data transformations and algorithms together with analysis comparing performance and providing speedup measurements for Intel® SSE optimized code and estimates for Intel® AVX optimized code.
Authored by Larsson, Petter (Blackbelt) Last updated on 05/25/2018 - 15:30

利用英特尔高级矢量扩展指令集进行 Wiener 过滤

Wiener filtering (also known as Least Mean Square filtering) is a technique for removing unwanted noise from an image. This article discusses Wiener filtering, and includes an example of code that has been optimized using Intel® AVX
Authored by Last updated on 12/11/2018 - 13:12

在不编写 AVX 代码的情况下使用 AVX

1. 简介和工具
Authored by admin Last updated on 07/05/2019 - 20:45

避免 AVX-SSE 转换造成的性能损失

避免 AVX-SSE 转换造成的性能损失 (PDF 678 KB)

Authored by Patrick Konsor (Intel) Last updated on 07/05/2019 - 20:48

英特尔® MKL 中的英特尔® AVX 优化代码

Starting from Intel MKL 10.3, AVX code will be dispatched as one of the platforms in MKL and does not require special activation as in MKL 10.2.
Authored by Vipin Kumar E K (Intel) Last updated on 03/27/2019 - 12:20

在不编写 AVX 的情况下使用英特尔® AVX

Intel® AVX is a new 256-bit instruction set extension to Intel® Streaming SIMD Extensions and is designed for applications that are floating point intensive. This paper discusses options to integrate Intel® AVX into an application via use of intrinsics.
Authored by richard-hubbard (Intel) Last updated on 06/07/2017 - 12:12


Photo-realistic rendering requires accurate simulation of light propagation according to physics laws. The best known way to solve this problem is Monte Carlo ray tracing. We describe a state-of-the-art photo-realistic Monte Carlo rendering engine.
Authored by Sven Woop (Intel) Last updated on 08/02/2019 - 17:30

诊断信息 15532: 循环无法进行矢量化处理:编译时间不足妨碍了循环进行优化

产品版本: Intel(R) Visual Fortran 编译器 XE


使用 Visual Fortran 编译器的优化选项 ( -O2  -Qopt-report:2 )  时出现矢量化报告,表示编译时间不足妨碍了优化。

Authored by Devorah H. (Intel) Last updated on 07/05/2019 - 14:23