|
所在平台: Coursera |
课程主页: https://www.coursera.org/learn/cuda-advanced-libraries
课程评论：没有评论
课程名称：CUDA高级库 课程概述：本课程将完成GPU专业化的学习，重点关注CUDA工具包中分发的领先库。学生将学习如何使用CuFFT和线性代数库进行复杂的数学计算。同时，将介绍Thrust库在表示常见数据结构和相关算法方面的能力。通过使用cuDNN和cuTensor，学生将能够开发有助于对象检测、人类语言翻译和图像分类的机器学习应用。 课程大纲：
第一部分
标题：课程概述
描述：本模块的目的是让学生了解课程的运行方式、主题、评估方式及期望。
第二部分
标题：cuFFT
描述：cuFFT提供在大数据集上执行快速傅里叶变换(FFT)的能力。学生将学习常见的用例，如快速乘法大多项式、信号处理和矩阵运算。他们将使用此库开发处理音频或视频信号的软件。
第三部分
标题：CUDA线性代数
描述：CUDA工具包包含多种线性代数库，如cuBLAS、NVBLAS、cuSPARSE和cuSOLVER。学生将学习这些库的不同功能和限制，并将这些知识应用于计算矩阵点积、行列式及解决复杂线性系统。
第四部分
标题：CUDA Thrust库
描述：大多数开发人员使用超出CUDA程序员核心原始数据和指针的数据结构，这使得纯CUDA开发变得困难。学生将学习Thrust库，该库添加了向量数据结构和相关算法，从而简化他们的代码。学生将创建能转化、简化和排序大数据集的软件。
第五部分
标题：CUDA机器学习
描述：数据科学家、机器学习和人工智能专家正在利用神经网络解决人类语言翻译、图像分类和对象检测/规避等问题。
Part: 1
Title:Course Overview
Description:The purpose of this module is for students to understand how the course will be run, topics, how they will be assessed, and expectations.
Part: 2
Title:cuFFT
Description:cuFFT provides the ability to perform fast Fourier transforms (FFTs) on large datasets. Students will learn of common use cases such as fast multiplication of large polynomials, signal processing, and matrix operations. They will use this library to develop software that process audio or video signals.
Part: 3
Title:CUDA Linear Algebra
Description:The CUDA Toolkit includes a number of linear algebra libraries, such as cuBLAS, NVBLAS, cuSPARSE, and cuSOLVER. Students will learn the different capabilities and limitations of many of them and apply that knowledge to compute matrix dot products, determinant, and finding solutions to complex linear systems.
Part: 4
Title:The CUDA Thrust Library
Description:Most developers utilize data structures beyond the primitives and pointers that make up the core of CUDA programmers, which makes pure CUDA development difficult. Students will learn about the Thrust library that adds the vector data structure and associated algorithms that allow for simplification of their code. Students will create software that transform, reduction, and sort large datasets.
Part: 5
Title:CUDA Machine Learning
Description:Data Scientists, Machine Learning, and Artificial intelligence experts are using neural networks to solve problems such as human language translation, image classification, and object detection/avoidance.
This course will complete the GPU specialization, focusing on the leading libraries distributed as part of the CUDA Toolkit. Students will learn how to use CuFFT, and linear algebra libraries to perform complex mathematical computations. The Thrust library’s capabilities in representing common data structures and associated algorithms will be introduced. Using cuDNN and cuTensor they will be able to develop machine learning applications that help with object detection, human language translation and image classification.
