Buch, Englisch, 187 Seiten, Format (B × H): 148 mm x 210 mm, Gewicht: 2703 g
ISBN: 978-3-658-10112-1
Verlag: Springer
Ralf Karrenberg presents Whole-Function Vectorization (WFV), an approach that allows a compiler to automatically create code that exploits data-parallelism using SIMD instructions. Data-parallel applications such as particle simulations, stock option price estimation or video decoding require the same computations to be performed on huge amounts of data. Without WFV, one processor core executes a single instance of a data-parallel function. WFV transforms the function to execute multiple instances at once using SIMD instructions. The author describes an advanced WFV algorithm that includes a variety of analyses and code generation techniques. He shows that this approach improves the performance of the generated code in a variety of use cases.
Zielgruppe
- Computer science researchers and students working in data-parallel computing
- Software and compiler engineers in the fields high-performance computing and compiler construction
Autoren/Hrsg.
Fachgebiete
- Mathematik | Informatik EDV | Informatik Technische Informatik Grid-Computing & Paralleles Rechnen
- Mathematik | Informatik EDV | Informatik Programmierung | Softwareentwicklung Compiler
- Mathematik | Informatik EDV | Informatik Programmierung | Softwareentwicklung Funktionale, Logische, Parallele und Visuelle Programmierung
Weitere Infos & Material
Introduction.- Foundations & Terminology.- Overview.- Related Work.- SIMD Property Analyses.- Whole-Function Vectorization.- Dynamic Code Variants.- Evaluation.- Conclusion.- Outlook.
