IBM System Blue Gene Solution: Blue Gene/P Application Development

An IBM Redbooks publication

Published 11 September 2009, updated 10 April 2012

cover image

ISBN-10: 0738433330
ISBN-13: 9780738433332
IBM Form #: SG24-7287-03
(406 pages)

Authors: Carlos Sosa, Brant Knudson


This IBM® Redbooks® publication is one in a series of IBM books written specifically for the IBM System Blue Gene/P Solution. The Blue Gene/P system is the second generation of a massively parallel supercomputer from IBM in the IBM System Blue Gene Solution series. In this book, we provide an overview of the application development environment for the Blue Gene/P system. We intend to help programmers understand the requirements to develop applications on this high-performance massively parallel supercomputer.

In this book, we explain instances where the Blue Gene/P system is unique in its programming environment. We also attempt to look at the differences between the IBM System Blue Gene/L Solution and the Blue Gene/P Solution. In this book, we do not delve into great depth about the technologies that are commonly used in the supercomputing industry, such as Message Passing Interface (MPI) and Open Multi-Processing (OpenMP), nor do we try to teach parallel programming. References are provided in those instances for you to find more information if necessary.

Prior to reading this book, you must have a strong background in high-performance computing (HPC) programming. The high-level programming languages that we use throughout this book are C/C++ and Fortran95. Previous experience using the Blue Gene/L system can help you better understand some concepts in this book that we do not extensively discuss. However, several IBM Redbooks publications about the Blue Gene/L system are available for you to obtain general information about the Blue Gene/L system. We recommend that you refer to "IBM Redbooks" on page 371 for a list of those publications.

Table of contents

Part 1. Blue Gene/P: System and environment overview
Chapter 1. Hardware overview
Chapter 2. Software overview
Part 2. Kernel overview
Chapter 3. Kernel functionality
Chapter 4. Execution process modes
Chapter 5. Memory
Chapter 6. System calls
Part 3. Applications environment
Chapter 7. Parallel paradigms
Chapter 8. Developing applications with IBM XL compilers
Chapter 9. Running and debugging applications
Chapter 10. Checkpoint and restart support for applications
Chapter 11. mpirun
Chapter 12. High-Throughput Computing (HTC) paradigm
Part 4. Job scheduler interfaces
Chapter 13. Control system (Bridge) APIs
Chapter 14. Real-time Notification APIs
Chapter 15. Dynamic Partition Allocator APIs
Part 5. Applications
Chapter 16. Performance overview of engineering and scientific applications
Appendix A. Blue Gene/P hardware-naming conventions
Appendix B. Files on architectural features
Appendix C. Header files and libraries
Appendix D. Environment variables
Appendix E. Porting applications
Appendix F. Mapping
Appendix G. htcpartition
Appendix H. Use of GNU profiling tool on Blue Gene/P
Appendix I. Statement of completion

Follow IBM Redbooks

Follow IBM Redbooks