Optimizing Loop-Level Parallelism in Cray XMT Applications
S-2487-10 - Oct 2009
Provides guidance and techniques for improving parallelization for Cray XMT programs. This Whitepaper was superseded by the 1.4 version and supports the Cray XMT release.
Links
- Available formats
- Table of contents
- Software releases this book supports
- Other versions of this book
Available formats
|
S-2487-10.pdf |
|
html-S-2487-10 |
Table of contents
1 Introduction2 Overview of the Cray XMT System
2.1 The Cray XMT Programming Environment and Tools
2.2 Language Extensions
2.3 Loop-level Parallelism and Canal
3 Identifying Parallelism
3.1 Conditions for Safe Parallelization
4 Compiler Transformations
4.1 Scalar Expansion
4.2 Reductions
4.3 Linear Recurrences
4.4 Nested Parallelism and Loop Collapse
5 Pragmas
6 Implementing Parallelism
6.1 Parallel Regions
6.2 Styles of Parallelism
6.3 Loop Scheduling
7 An Example Loop
8 Summary
9 Acknowledgments
10 About the Authors
11 Selected Bibliography
Software Releases this book supports
| Product | Version | Sub Product | Release Date |
|---|---|---|---|
| unsupported | [no version] | Jan 1998 |
Other versions of this book
| Publication Number | Release Date | Supported Software Releases |
|---|---|---|
| S-2487-14 | Dec 2009 | Knowledge Base 1.0 |