欢迎大家赞助一杯啤酒🍺 我们准备了下酒菜：Formal mathematics/Isabelle/ML, Formal verification/Coq/Agda, C++/Erlang/Lisp
OpenACC
来自开放百科 - 灰狐
（版本间的差异）
小 (→图集) |
小 (→链接) |
||
| （未显示1个用户的1个中间版本） | |||
| 第20行： | 第20行： | ||
*[http://docs.huihoo.com/gputechconf/gtc2015/S5388-OpenACC-for-Fortran-Programmers.pdf OpenACC for Fortran Programmers] | *[http://docs.huihoo.com/gputechconf/gtc2015/S5388-OpenACC-for-Fortran-Programmers.pdf OpenACC for Fortran Programmers] | ||
*[http://docs.huihoo.com/gputechconf/gtc2015/S5139-Showing-the-Missing-Middle-Enabling-OpenACC-Performance-Analysis.pdf Showing the Missing Middle Enabling OpenACC Performance Analysis] | *[http://docs.huihoo.com/gputechconf/gtc2015/S5139-Showing-the-Missing-Middle-Enabling-OpenACC-Performance-Analysis.pdf Showing the Missing Middle Enabling OpenACC Performance Analysis] | ||
| + | *[http://docs.huihoo.com/gputechconf/gtc2015/S5366-Extended-OpenACC-Programming-to-Exploit-GPU-Specific-Features-Still-at-a-High-Level.pdf Extended OpenACC Programming to Exploit GPU-Specific Features Still at a High Level] | ||
| + | *[http://docs.huihoo.com/gputechconf/gtc2015/S5721-In-Depth-Performance-Analysis-for-OpenACC-CUDA-OpenCL-Applications-with-Score-P-and-Vampir.pdf In-Depth Performance Analysis for OpenACC/CUDA/OpenCL Applications with Score-P and Vampir] | ||
| + | *[http://docs.huihoo.com/gputechconf/gtc2015/S5202-Porting-Computational-Physics-Applications-to-the-Titan-Supercomputer-with-OpenACC-and-OpenMP.pdf Porting Computational Physics Applications to the Titan Supercomputer with OpenACC and OpenMP] | ||
==图集== | ==图集== | ||
| 第30行： | 第33行： | ||
*[http://www.nvidia.cn/object/openacc-cn.html NVIDIA OpenACC工具包] | *[http://www.nvidia.cn/object/openacc-cn.html NVIDIA OpenACC工具包] | ||
| + | [[category:parallel computing]] | ||
[[category:HPC]] | [[category:HPC]] | ||
[[category:GPU]] | [[category:GPU]] | ||
[[category:deep learning]] | [[category:deep learning]] | ||
2017年3月4日 (六) 23:16的最后版本
|
您可以在Wikipedia上了解到此条目的英文信息 OpenACC Thanks, Wikipedia. |
OpenACC 是一种全新的开放式并行编程标准，该标准旨在让数以百万计的科技类 Fortran 和 C 语言程序员能够轻松利用异构 CPU/GPU 计算系统的强大能力改变行业面貌。
OpenACC 让并行程序员能够为编译器提供简单的提示，亦称「指令」，使编译器能够识别哪些代码部分需要加速，无需程序员修改或改编底层代码本身。 在把计算任务映射到加速器上这方面，指令通过向编译器呈现出并行机制，从而让编译器能够执行这方面的详细工作。
OpenACC 指令由 PGI、Cray 以及英伟达在 CAPS 的支持下开发而成，是多家企业希望利用指令来简化 GPU 编程模型的一个共同愿景。这些企业均致力于支持一种共同的编程标准。
目录 |
[编辑] 指南
[编辑] 文档
- OpenACC 2.5 and Beyond
- Advanced OpenACC Programming
- Experiences in Porting Scientific Applications to GPUs Using OpenACC
- Hands on Lab Multi GPU Programming with MPI and OpenACC
- GPU Acceleration Using OpenACC and C++ Classes
- Introduction to Compiler Directives with OpenACC
- Comparing OpenACC and OpenMP Performance and Programmability
- A Simulation of Global Atmosphere Model NICAM on TSUBAME2.5 Using OpenACC
- OpenACC for Fortran Programmers
- Showing the Missing Middle Enabling OpenACC Performance Analysis
- Extended OpenACC Programming to Exploit GPU-Specific Features Still at a High Level
- In-Depth Performance Analysis for OpenACC/CUDA/OpenCL Applications with Score-P and Vampir
- Porting Computational Physics Applications to the Titan Supercomputer with OpenACC and OpenMP
[编辑] 图集
OpenACC
[编辑] 链接
分享您的观点
