Next Previous Contents

---

Linux Parallel Processing HOWTO

Hank Dietz, pplinux@ecn.purdue.edu

v980105, 5 January 1998

---

Parallel Processing refers to the concept of speeding-up the execution of a program by dividing the program into multiple fragments that can execute simultaneously, each on its own processor. A program being executed across N processors might execute N times faster than it would using a single processor. This document discusses the four basic approaches to parallel processing that are available to Linux users: SMP Linux systems, clusters of networked Linux systems, parallel execution using multimedia instructions (i.e., MMX), and attached (parallel) processors hosted by a Linux system.

---

1. Introduction

• 1.1 Is Parallel Processing What I Want?
• 1.2 Terminology
• 1.3 Example Algorithm
• 1.4 Organization Of This Document

2. SMP Linux

• 2.1 SMP Hardware
• 2.2 Introduction To Shared Memory Programming
• 2.3 bb_threads
• 2.4 LinuxThreads
• 2.5 System V Shared Memory
• 2.6 Memory Map Call

3. Clusters Of Linux Systems

• 3.1 Why A Cluster?
• 3.2 Network Hardware
• 3.3 Network Software Interface
• 3.4 PVM (Parallel Virtual Machine)
• 3.5 MPI (Message Passing Interface)
• 3.6 AFAPI (Aggregate Function API)
• 3.7 Other Cluster Support Libraries
• 3.8 General Cluster References

4. SIMD Within A Register (e.g., using MMX)

• 4.1 SWAR: What Is It Good For?
• 4.2 Introduction To SWAR Programming
• 4.3 MMX SWAR Under Linux

5. Linux-Hosted Attached Processors

• 5.1 A Linux PC Is A Good Host
• 5.2 Did You DSP That?
• 5.3 FPGAs And Reconfigurable Logic Computing

6. Of General Interest

• 6.1 Programming Languages And Compilers
• 6.2 Performance Issues
• 6.3 Conclusion - It's Out There

---

Next Previous Contents