Adapting Fourier-Motzkin Elimination to Compute Bounds in Multilevel Tiling
نویسندگان
چکیده
This work focuses on the complexity of computing exact loop bounds in Multilevel Tiling. Conventional tiling techniques implement tiling using first strip-mining and afterwards loop interchange. Multilevel tiling has typically been implemented applying tiling level by level. We present a new way to implement Multilevel Tiling that deals with all levels simultaneously, performing a loop interchange transformation only once. Our algorithm computes exact loop bounds, that is, loops in the generated code never execute empty iterations. We evaluate the complexity of this algorithm and show that it is proportional to the complexity of performing an interchange in the original loop nest; the complexity of our algorithm depends doubly exponentially only on the number of loops (space dimensions) in the original loop nest rather than in the number of loops in the final tiled code. The algorithm is based on the Fourier-Motzkin elimination, that generates redundant bounds. We also present an implementation of the technique that reduces the number of redundant bounds in the tiled code.
منابع مشابه
An Efficient Code Generation Technique for Tiled Iteration Spaces
This paper presents a novel approach for the problem of generating tiled code for nested for-loops, transformed by a tiling transformation. Tiling or supernode transformation has been widely used to improve locality in multi-level memory hierarchies, as well as to efficiently execute loops onto parallel architectures. However, automatic code generation for tiled loops can be a very complex comp...
متن کاملIntroducing Non-linear Parameters to the Polyhedron Model
A mathematical model based on polyhedra (the so-called “polyhedron model”) serves as a foundation for model based loop program transformation like automatic parallelization. One of the restrictions present in the current polyhedron model is the requirement that the coefficients of variables must be numeric constants. This has been hindering some recent developments which require parametric coef...
متن کاملCombinatorial properties of Fourier-Motzkin elimination
Fourier-Motzkin elimination is a classical method for solving linear inequalities in which one variable is eliminated in each iteration. This method is considered here as a matrix operation and properties of this operation are established. In particular, the focus is on situations where this matrix operation preserves combinatorial matrices (defined here as (0, 1,−1)-matrices).
متن کاملComputing the Maximum Volume Inscribed Ellipsoid of a Polytopic Projection
We introduce a novel scheme based on a blending of Fourier-Motzkin elimination (FME) and adjustable robust optimization techniques to compute the maximum volume inscribed ellipsoid (MVE) in a polytopic projection. It is well-known that deriving an explicit description of a projected polytope is NP-hard. Our approach does not require an explicit description of the projection, and can easily be g...
متن کاملEla Combinatorial Properties of Fourier - Motzkin Elimination
Fourier-Motzkin elimination is a classical method for solving linear inequalities in which one variable is eliminated in each iteration. This method is considered here as a matrix operation and properties of this operation are established. In particular, the focus is on situations where this matrix operation preserves combinatorial matrices (defined here as (0, 1,−1)-matrices).
متن کامل