OpenCL in Scientific High Performance Computing: The Good, the Bad, and the Ugly

OpenCL in Scientific High Performance Computing: The Good, the Bad, and the Ugly
复制标题

OpenCL 在科学高性能计算中的应用:好的、坏的和丑陋的

DOI:
10.1145/3078155.3078170
复制
发表时间:
2017
期刊:
Proceedings of the 5th International Workshop on OpenCL
影响因子:
--
通讯作者:
Matthias Noack
Matthias Noack
中科院分区:
--
文献类型:
--
作者:
Matthias Noack

文献摘要

参考文献

被引文献

相似文献

对于编写一个新的科学应用程序,跨现有和未来硬件的可移植性应该是主要的设计目标,因为有许多不同的计算设备,程序代码通常比系统寿命长得多。与解决并行性或异构性的其他编程模型不同,OpenCL确实提供了跨各种HPC相关架构的实际可移植性。除此之外,它还具有一系列其他优点,例如仅使用库实现,以及使用运行时内核编译。我们目前的经验,利用OpenCL与C++,MPI和CMake在两个现实世界的科学代码。我们的目标是Cray XC40超级计算机,配备多核和众核(Xeon Phi)CPU,以及多个配备Nvidia和AMD GPU的小型系统。我们揭示了在这种情况下出现的实际问题,如OpenCL和MPI之间的相互作用,讨论解决方案,并指出当前的限制OpenCL在科学HPC领域的应用程序开发人员和用户的角度来看。
For writing a new scientific application, portability across existing and future hardware should be the major design goal, as there is a multitude of different compute devices, and programme codes typically outlive systems by far. Unlike other programming models that address parallelism or heterogeneity, OpenCL does provide practical portability across a wide range of HPC-relevant architectures. Other than that, it has a range of further advantages like being a library-only implementation, and using runtime kernel-compilation. We present experiences with utilising OpenCL alongside C++, MPI, and CMake in two real-world scientific codes. Our targets are a Cray XC40 supercomputer with multi- and many-core (Xeon Phi) CPUs, as well as multiple smaller systems with Nvidia and AMD GPUs. We shed light on practical issues arising in such a scenario, like the interaction between OpenCL and MPI, discuss solutions, and point out current limitations of OpenCL in the domain of scientific HPC from an application developer's and user's point of view.
彗星 67P/CHURYUMOV–GERASIMENKO 上的主要尘埃传输方向
DOI: 10.1088/2041-8205/813/2/l33
发表时间: 2015
期刊: The Astrophysical Journal Letters
影响因子: --
作者:
Tobias Kramer;M. Noack
通讯作者: M. Noack
关于罗塞塔在彗星 67P/CHURYUMOV-GERASIMENKO 昼夜自转期间观察到的内彗发结构的起源
DOI: 10.3847/2041-8205/823/1/l11
发表时间: 2016
期刊: The Astrophysical Journal Letters
影响因子: --
作者:
Tobias Kramer;M. Noack
通讯作者: M. Noack
OpenCL:来来回回
DOI: 10.1016/b978-0-12-803819-2.00001-x
发表时间: 2015
期刊: 2014 IEEE 28th International Parallel and Distributed Processing Symposium
影响因子: --
作者:
M. Noack;Florian Wende;Klaus
通讯作者: Klaus