（翻译经典教材）CUDA面向大众的超级计算.docVIP

CUDA，面向大众的超级计算 Rob Farber 1 当开发在GPU上运行的软件时，CUDA让你能够用熟悉的编程习惯来进行开发 Are you interested in getting orders-of-magnitude performance increases over standard multi-core processors, while programming with a high-level language such as C? And would you like that capability to scale across many devices as well? 在使用像C这样的高级语言进行编程时，你是否考虑过从标准的多核处理器中获取几个数量级的巨大的性能提升？你是否乐意于从其它设备中也这样做呢？ Many people (myself included) have achieved this level of performance and scalability on non-trivial problems by using CUDA (short for Compute Unified Device Architecture) from NVIDIA to program inexpensive multi-threaded GPUs. I purposefully stress programming because CUDA is an architecture designed to let you do your work, rather than forcing your work to fit within a limited set of performance libraries. With CUDA, you get to exploit your abilities to design software to achieve best performance on your multi-threaded hardware -- and have fun as well because figuring out the right mapping is captivating, plus the software development environment is both reasonable and straightforward. CUDA（Compute Unified Device Architecture）是NVIDIA公司的可编程多线程GPU提供的一种技术，很多人（包括我）在使用这种技术时，都获得了性能的提升，并且没有遇到什么困难。我通常要强调“可编程性”这个词，因为CUDA架构设计的初衷，就是让人们自由地做自己的工作，而不是强迫人们局限在一组库函数上边。在CUDA架构下，你可以把你的能力用在设计软件上边——此软件可以在你的多线程硬件下表现出最好的性能。你有了出从的计算性能，再加上便利的开发环境，所以你可以尽情地享受快乐了。 This is the first of a series of articles to introduce you to the power of CUDA -- through working code -- and to the thought process to help you map applications onto multi-threaded hardware (such as GPUs) to get big performance increases. Of course, not all problems can be mapped efficiently onto multi-threaded hardware, so part of my thought process will be to distinguish what will and what wont work, plus provide a common-sense idea of what might work well-enough. 通过代码的方式，我们会有一个关于介绍CUDA强劲性能的系列文章，这里是本系列的开头部分。为了获取强劲的性能，我们将逐步帮助你把程序移植到多线程设备上（例如GPU）。当然，并不是所有的应用都可以进行有效地移植，对此我会加以指明，并提供一个也许会起作用的改进办法。 CUDA programming and GPGPU programming are not the same (although CU