Abstract
In Chapter 2, we introduced the main concepts and techniques of dependence analysis in terms of a single loop. In Chapter 4, we develop a formal structure for doing dependence analysis in a perfect loop nest, and then go on to study general programs and general methods in later chapters. The current chapter forms a bridge between Chapter 2 and the rest of the book. Here, we study the major changes that happen as we move from a single loop to a more general program: index and iteration variables become index and iteration vectors; dependence distances become dependence (distance) vectors; and there is usually more than one unknown integer parameter in the general solution of the dependence equation(s). The main difficulty we face now is that we are required to seek integer solutions to a system of linear inequalities in more than one variable (Step 5, Algorithm 1.1).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Rights and permissions
Copyright information
© 1997 Kluwer Academic Publishers
About this chapter
Cite this chapter
(1997). Double Loops. In: Dependence Analysis. Loop Transformation for Restructuring Compilers, vol 3. Springer, Boston, MA. https://doi.org/10.1007/978-0-585-28122-3_3
Download citation
DOI: https://doi.org/10.1007/978-0-585-28122-3_3
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-7923-9809-7
Online ISBN: 978-0-585-28122-3
eBook Packages: Springer Book Archive