This book shows hows how high-performance application developers can use the power of GPUs using Fortran. Gregory Ruetsch and Massimiliano Fatica presume no prior parallel computing experience, and cover the basics along with best practices for efficient GPU computing using CUDA Fortran.

In order to add CUDA Fortran to existing Fortran codes, they explain how to understand the target GPU architecture, identify computationally-intensive parts of the code, and modify the code to manage the data and parallelism and optimize performance – all in Fortran, without having to rewrite in another language.

Author: Gregory Ruetsch and Massimiliano Fatica
Publisher: Morgan Kaufmann
Date: July 2024
Pages: 350
ISBN: 978-0443219771
Print: 044321977X
Kindle: B0D9B5QPCQ
Audience: Developers interested in Fortran
Level: Intermediate
Category: Other Languages

• Presents optimization strategies for current hardware, including Hopper generation GPUs
• Includes discussions of new language and hardware features, including managed memory, tensor cores, shuffle instructions, new multi-GPU paradigms
• Offers resources and strategies for porting large codes to GPUs, including language features as well as library use

For more Book Watch just click.

Book Watch is I Programmer's listing of new books and is compiled using publishers' publicity material. It is not to be read as a review where we provide an independent assessment. Some, but by no means all, of the books in Book Watch are eventually reviewed.

To have new titles included in Book Watch contact  BookWatch@i-programmer.info

Follow @bookwatchiprog on Twitter or subscribe to I Programmer's Books RSS feed for each day's new addition to Book Watch and for new reviews.