Dive into GPU-accelerated application development with this comprehensive CUDA 10 programming tutorial. Learn to harness the power of modern GPUs for high-performance computing in C and C++ projects. Explore hands-on examples that introduce CUDA programming fundamentals, including the CUDA programming model, shared memory usage, and the NVIDIA Visual Profiler. Discover how to leverage CUDA's powerful libraries for machine learning, image processing, linear algebra, and parallel algorithms. Gain practical knowledge on implementing deep learning techniques and utilizing concurrency and streams for optimal performance. By the end of this 30-minute tutorial, acquire the skills to immediately incorporate CUDA programming into your applications, unlocking the tremendous computational potential of GPUs. Access accompanying code files on GitHub to reinforce your learning experience. Prerequisite: A solid understanding of modern C++ (C++17) programming.
Overview
Syllabus
Learning CUDA 10 Programming : The Course Overview | packtpub.com.
Learning CUDA 10 Programming : The CUDA Programming Model | packtpub.com.
Learning CUDA 10 Programming : The NVIDIA Visual Profiler | packtpub.com.
Learning CUDA 10 Programming : Introduction to Shared Memory | packtpub.com.
Learning CUDA 10 Programming : Deep Learning | packtpub.com.
Learning CUDA 10 Programming : Concurrency and Streams | packtpub.com.
Learning CUDA 10 Programming : What We Have Learned | packtpub.com.
Taught by
Packt Video
