百科.dev
全部条目在线工具AI 编程趋势榜开源项目技术资讯提交条目
登录
< 返回工具列表
K

kokkos-tutorials

> 编程语言
开源

Kokkos C++ 性能可移植编程生态系统教程

384 stars0 点赞1 次浏览
访问官网GitHub

工具介绍

Kokkos C++ 性能可移植编程生态系统教程

Kokkos Tutorials

This repository contains tutorials for the Kokkos C++ programming model (github.com/kokkos/kokkos).

The Kokkos Lectures

The most comprehensive recording of our tutorials - the The Kokkos Lectures - are available on YouTube. For more information on that, including the Slides and Recordings visit: The Kokkos Lectures Wiki

Building the slides

You need a recent Latex version installed on the system with the following packages: pgffor, beramono, comment, eso-pic, fontenc, inputenc, listings, lstlinebgrd, minted, paralist, pgf, pgfplotstable, soul, subfig, textpos, tikz, ulem, xcolor, and xparse.

To compile the slides, please run

bash
cd Content/Presentations/
make

Old Slides

The old slides are available in this repository under the legacy tag.

Building the Tutorials

All the tutorial folders can be built using CMake.

CMake

CMake can build against an installed Kokkos library or download one automatically using FetchContent.

Without any Kokkos already installed, from an exercise directory, one can run the following:

bash
cmake -B build_dir # -DKokkos_* options
cmake --build build_dir

Kokkos options are described in CMake options.

For example, OpenMP CPU exercises can be built as:

bash
cmake -B build_openmp -DKokkos_ENABLE_OPENMP=ON
cmake --build build_openmp

On Mac, if OpenMP is not available, one can use the Threads backend:

bash
cmake -B build_threads -DKokkos_ENABLE_THREADS=ON
cmake --build build_threads

For a NVIDIA gpu, using gpu arch autodetection:

bash
cmake -B build_cuda -DKokkos_ENABLE_CUDA=ON
cmake --build build_cuda

To pass an already installed Kokkos library, you can use classical CMake variables, such as Kokkos_ROOT, or CMAKE_PREFIX_PATH.

Issues· 0 开放

查看全部 Issues在 GitHub 打开

暂无开放 Issues,或尚未同步最近议题。

> 标签

C++

暂无评论,来聊聊你的看法吧

> 工具信息

发布日期2026年8月1日
最后更新2026年9月17日
分类编程语言
定价开源

> 相关工具

T
TypeScript
JavaScript 的超集,为前端与全栈提供静态类型
P
Python
通用编程语言,广泛用于 Web、数据与 AI
G
Go
Google 推出的简洁高效系统语言