CUDA (formerly an abbreviation of Compute Unified Device Architecture) is a parallel computing platform and API model created by Nvidia allowing software developers to use a CUDA-enabled graphics processing unit (GPU) for general purpose processing. This 90-pages tutorial introduces the CUDA concepts in an easy-to-grasp and interactive way with ready-to-run code samples tested on Windows and Linux. Starting from scratch, a complete stand-alone GPU tool is implemented which automatically performs a ciphertext-only attack on ciphertexts encrypted by monoalphabetic substitution and columnar transposition. Throughout this process, you will learn how to architect the tool, what optimizations could significantly accelerate the routines, why the choice of an adequate metaheuristic is critical, and how to draw sketches to enlighten the design process. This tutorial will be incorporated in the CrypTool book as chapter 13.
翻译:CUDA(前称计算统一设备架构缩略语)是Nvidia创建的平行计算平台和 API 模型,使软件开发者能够使用 CUDA 驱动的图形处理器(GPU) 进行一般用途处理。 这个90页的辅导用在 Windows 和 Linux 上测试的即时运行代码样本以简单易懂和互动的方式介绍了 CUDA 概念。 从零开始, 实施一个完整的独立 GPU 工具, 自动对通过单体畸形替代和分体转换定位加密的密码进行密码攻击。 在这一过程中, 您将学习如何设计工具, 哪些优化可以大大加快常规, 为什么选择适当的计量术至关重要, 以及如何绘制草图来指导设计过程。 此教义将被纳入 CrypTool 书第13章。