High Performance Computing Programming and Applications

Covering all three levels of parallelism, this book presents techniques that address performance issues in the programming of HPC applications. Drawing on their experience with chips from AMD and systems, interconnects, and software from Cray Inc., the authors explore the problems that create bottle...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Levesque, John, Wagenbreth, Gene
Format: E-Book
Sprache:Englisch
Veröffentlicht: Milton Chapman and Hall/CRC 2010
CRC Press LLC
Chapman & Hall
CRC Press
Ausgabe:1
Schriftenreihe:Chapman & Hall/CRC Computational Science
Schlagworte:
High performance computing
Programming
Supercomputers
Processor Counts
Clock Cycle
High Performance Computing
Array Syntax
Hardware Counter
Larger Processor Counts
Oating Point Operation
Memory Bandwidth
Cache Line
Weak Scaling
MPI Task
Load Imbalance
Clo Ck
Vector Length
Nth Column
OpenMP Region
Multicore Node
MPI Program
OMP
ENDDO ENDDO
Prefetch Instructions
Multicore Socket
MPI Application
Computational Intensity
DDR2
ISBN:1420077058, 9781420077056
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Inhaltsangabe:
  • Front Cover -- Contents -- Introduction -- Chapter 1: Multicore Architectures -- Chapter 2: The MPP : A Combination of Hardware and Software -- Chapter 3: How Compilers Optimize Programs -- Chapter 4: Parallel Programming Paradigms -- Chapter 5: A Strategy for Porting an Application to a Large MPP System -- Chapter 6: Single Core Optimization -- Chapter 7: Parallelism across the Nodes -- Chapter 8: Node Performance -- Chapter 9: Accelerators and Conclusion -- Appendix A: Common Compiler Directives -- Appendix B: Sample MPI Environment Variables -- References -- Back Cover