Combined selection of tile sizes and unroll factors using iterative compilation
Authors:
- P.M.W. KnijnenburgPKP.M.W. Knijnenburg
- M.F.P. O'BOyleMOM.F.P. O'BOyle
- 8 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 1089795X,p. 237-246
Abstract
Loop tiling and unrolling are two important program transformations to exploit locality and expose instruction level parallelism, respectively. In this paper, we address the problem of how to select tile sizes and unroll factors simultaneously. We approach this problem in an architecturally adaptive manner by means of iterative compilation, where we generate many versions of a program and decide upon the best by actually executing them and measuring their execution time. We evaluate several iterative strategies. We compare the levels of optimization obtained by iterative compilation to several well-known static techniques and show that we outperform each of them on a range of benchmarks across a variety of architectures. Finally, we show how to quantitatively trade-off the number of profiles needed and the level of optimization that can be reached.Keywords
This publication has 10 references indexed in Scilit:
- Combining optimization for cache and instruction-level parallelism2002
- Calpa: a tool for automating selective dynamic compilation2002
- Combined selection of tile sizes and unroll factors using iterative compilation2002
- A tile selection algorithm for data locality and cache interference1999
- A Comparison of Compiler Tiling Algorithms1999
- Combining Loop Transformations Considering Caches and SchedulingInternational Journal of Parallel Programming, 1998
- Automatically Tuned Linear Algebra Software1998
- Optimizing matrix multiply using PHiPAC1997
- Tile size selection using cache organization and data layout1995
- The cache performance and optimizations of blocked algorithms1991