JavaScript is required to for searching.
Skip Navigation Links
Exit Print View
Oracle Solaris Studio 12.3: C User's Guide     Oracle Solaris Studio 12.3 Information Library
search filter icon
search icon

Document Information

Preface

1.  Introduction to the C Compiler

2.  C-Compiler Implementation-Specific Information

3.  Parallelizing C Code

3.1 Overview of Parallelization

3.2 Parallelizing for OpenMP

3.2.1 Handling OpenMP Runtime Warnings

3.2.2 Environment Variables

3.2.3 Using restrict in Parallel Code

3.3 Data Dependence and Interference

3.3.1 Parallel Execution Model

3.3.2 Private Scalars and Private Arrays

3.3.3 Storeback

3.3.4 Reduction Variables

3.4 Speedups

3.4.1 Amdahl's Law

3.4.1.1 Overheads

3.4.1.2 Gustafson's Law

3.5 Load Balance and Loop Scheduling

3.5.1 Static or Chunk Scheduling

3.5.2 Self-Scheduling

3.5.3 Guided Self-Scheduling

3.6 Loop Transformations

3.6.1 Loop Distribution

3.6.2 Loop Fusion

3.6.3 Loop Interchange

3.7 Aliasing and Parallelization

3.7.1 Array and Pointer References

3.7.2 Restricted Pointers

3.8 Memory-Barrier Intrinsics

4.  lint Source Code Checker

5.  Type-Based Alias Analysis

6.  Transitioning to ISO C

7.  Converting Applications for a 64-Bit Environment

8.  cscope: Interactively Examining a C Program

A.  Compiler Options Grouped by Functionality

B.  C Compiler Options Reference

C.  Implementation-Defined ISO/IEC C99 Behavior

D.  Features of C99

E.  Implementation-Defined ISO/IEC C90 Behavior

F.  ISO C Data Representations

G.  Performance Tuning

H.  Oracle Solaris Studio C: Differences Between K&R C and ISO C

Index

3.1 Overview of Parallelization

The C compiler generates parallel code for those loops that it determines are safe to parallelize. Typically, these loops have iterations that are independent of each other. For such loops, the order in which iterations are executed or if they are executed in parallel, does not matter. Many, though not all, vector loops fall into this category.

Because of the way aliasing works in C, determining the safety of parallelization is difficult. To help the compiler, Solaris Studio C offers pragmas and additional pointer qualifications to provide aliasing information known to the programmer that the compiler cannot determine. See Chapter 5, Type-Based Alias Analysis for more information.

The following example illustrates how to enable and control parallelized C:

% cc -fast -xO4 -xautopar example.c -o example

This compiler command generates an executable called example, which can be executed normally. To find out how to take advantage of multiprocessor execution, see B.2.80 -xautopar.