Gpu Parallel Program Development Using Cuda

ISBN-13: 9781498750752 / Angielski / Twarda / 2018 / 440 str.

Tolga Soyata

Opis

This book provides a hands-on, class-tested introduction to CUDA and GPU programming. It begins by introducing CPU programming and the concepts of P-threads, thread programming, multi-tasking, and parallelism, and then interweaves those concepts into an introduction of GPU programming. Using Nvidia's new platform, based on Amazon EC2 and Web GPU, the book uses a standardized architecture, while also exploring other architectures and their differences. The book also covers GPU multi-threading and Global Memory, CUDA atomics and the use of libraries on GPUs. Example applications in image processing, face detection, and tumor detection are also included.

Spis treści

Introduction to Parallelism and GPU Programming. Introduction to Pthreads. Introduction to Multi-threading. Multi-threading Analysis. Introduction to AWS and the first GPU program. Analysis of the first CUDA program. How to run programs outside Amazon, on a different Unix system. How to run programs outside Amazon, on a different Windows system. Introduction to GPU Multi-threading and Global Memory. In-depth look at Global Memory and GPU Threads. Introduction to Shared Memory. In-depth look at Shared Memory. Performance Bottlenecks in GPU Architecture. Compute Capability and PTX. Host-Device Data Movement Mechanism. CUDA Streaming. CUDA Atomics. OpenGL-CUDA Interoperability. OpenGL and Real-Time GPU Processing. Example Applications - Edge Detection (CUBLAS). Example Applications - Sophisticated Image Processing (CUFFT). Example Applications- Elastography Based Tumor Detection (CUSOLVER). Example Applications - Real-Time Face Recognition (OpenCV, CUBLAS).