New
Programming Massively Parallel Processors,
Edition 5 A Hands-on ApproachEditors: By Wen-mei W. Hwu, David B. Kirk and Izzat El Hajj
Publication Date:
01 Sep 2026
Hazards
-
The publication contains no hazards
Conformance
-
PDF/UA-1
-
The publication contains a conformance statement that it meets the EPUB Accessibility 1.1, WCAG 2.1, Level AA standard. Please see https://bornaccessible.benetech.org/certified-publishers/ for further details of our compatibility testing.
-
The publication was certified on 20250710
-
Accessibility addendum
-
The certifier's credential is https://bornaccessible.benetech.org/certified-publishers/
-
For detailed accessibility information, see Elsevier’s website at https://www.elsevier.com/about/accessibility
-
Compatibility tested
-
For queries regarding accessibility information, contact [email protected]
Ways Of Reading
-
This e-publication is accessible to the full extent that the file format and types of content allow, on a specific reading device, by default, without necessarily including any additions such as textual descriptions of images or enhanced navigation.
-
Short alternative textual descriptions
-
Information-rich images are described by extended descriptions
-
Visualised data also available as non-graphical data
-
All contents of the digital publication necessary to use and understanding, including any text, images (via alternative descriptions), video (via audio description) is fully accessible via suitable audio reproduction.
Navigation
-
The contents of the PDF have been tagged to permit access by assistive technologies as per PDF-UA-1 standard.
-
Index with links to referenced entries
-
Page breaks included from the original print source
-
Elements such as headings, tables, etc. for structured navigation
Additional Accessibility Information
-
All (or substantially all) textual matter is arranged in a single logical reading order (including text that is visually presented as separate from the main text flow, e.g., in boxouts, captions, tables, footnotes, endnotes, citations, etc.). Non-textual content is also linked from within this logical reading order. (Purely decorative non-text content can be ignored).
-
The language of the text has been specified (e.g., via the HTML or XML lang attribute) to optimise text-to-speech (and other alternative renderings), both at the whole document level and, where appropriate, for individual words, phrases or passages in a different language.
-
For readers with color vision deficiency, use of color (e.g., in diagrams, graphics and charts, in prompts, or on buttons inviting a response) is not the sole means of graphical distinction or of conveying information
-
Content is enhanced with ARIA roles to optimize organization and facilitate navigation
-
Where interactive content is included in the product, controls are provided (e.g., for speed, pause and resume, reset) and labelled to make their use clear.
-
Content provides explanations for unusual words, abbreviations, acronyms, idioms, jargon in an accessible form, such as glossaries, scripted pop-ups.
-
WCAG v2.2
Product Content
-
Content includes any type of illustrations.
-
The primary content is text.
-
Content includes a significant number of actionable (clickable) web links to external content, downloadable resources, supplementary material, etc.
-
Content includes a significant number of actionable (clickable) cross-references, hyperlinked notes and annotations, or with other actionable links between largely textual elements (e.g., quiz/test questions, ‘choose your own ending’, etc.).
-
Additional text not part of main content
-
Content includes photographs, whether in a plate section / insert or not.
-
Content includes figures, diagrams, charts and/or graphs, including other ‘mechanical’ (i.e. non-photographic) illustrations.
-
Sequential art
-
Text within images
-
Content includes mathematical notations, formulae.
Note
-
This product relies on 3rd party tooling which may impact the accessibility features visible in inspection copies. All accessibility features mentioned would be present in the purchased version of the title.
Programming Massively Parallel Processors: A Hands-on Approach Fifth Edition shows both students and professionals alike the basic concepts of parallel programming and GPU architecture. Concise, intuitive, and practical, it is based on years of road-testing in the authors' own parallel computing courses. Various techniques for constructing and optimizing parallel programs are explored in detail, while case studies demonstrate the development process, which begins with computational thinking and ends with effective and efficient parallel programs. This new edition has been updated with an expanded repertoire of optimizations, new patterns and applications, ad more coverage of important CUDA features.
Key Features
· Expanded optimization checklist with a more comprehensive demonstration of essential optimizations across patterns
· New pattern and application chapters including: filtering, wavefront parallelism, advanced optimizations for matrix multiplication, and large language models (LLMs) · More coverage of important CUDA features including warp-level programming, cooperative groups, CUDA C++ atomics, and multi-GPU programming with NCCL and NVSHMEM
About the author
By Wen-mei W. Hwu, CTO, MulticoreWare and professor specializing in compiler design, computer architecture, microarchitecture, and parallel processing, University of Illinois at Urbana-Champaign, USA; David B. Kirk, NVIDIA Fellow and Izzat El Hajj, Assistant Professor, Department of Computer Science, American University of Beirut, Lebanon
1. Introduction
Part I. Fundamental Concepts
2. Heterogeneous data parallel computing
3. Multidimensional grids and data
4. Compute architecture and scheduling
5. Memory architecture and data locality
6. Performance considerations
Part II. Parallel Patterns
7. Convolution
8. Stencil
9. Parallel histogram
10. Reduction
11. Prefix sum (scan)
12. Merge
Part III. Advanced Patterns and Applications
13. Sorting
14. Filtering (new)
15. Sparse matrix computation
16. Wavefront Algorithms (new)
17. Graph traversal
18. Deep learning
19. Multi-GPU API (new)
20. Electrostatic potential map
21. Parallel programming and computational thinking
Part IV. Advanced Practices
22. Programming a heterogeneous computing cluster
23. Advanced Optimizations for Matrix Multiplication (new)
24. Advanced practices and future evolution
25. Conclusion and outlook
Part I. Fundamental Concepts
2. Heterogeneous data parallel computing
3. Multidimensional grids and data
4. Compute architecture and scheduling
5. Memory architecture and data locality
6. Performance considerations
Part II. Parallel Patterns
7. Convolution
8. Stencil
9. Parallel histogram
10. Reduction
11. Prefix sum (scan)
12. Merge
Part III. Advanced Patterns and Applications
13. Sorting
14. Filtering (new)
15. Sparse matrix computation
16. Wavefront Algorithms (new)
17. Graph traversal
18. Deep learning
19. Multi-GPU API (new)
20. Electrostatic potential map
21. Parallel programming and computational thinking
Part IV. Advanced Practices
22. Programming a heterogeneous computing cluster
23. Advanced Optimizations for Matrix Multiplication (new)
24. Advanced practices and future evolution
25. Conclusion and outlook
ISBN:
9780443439001
Page Count:
680
Retail Price
:
Upper-level undergraduate through graduate level students studying parallel computing within computer science or engineering