Combined selection of tile sizes and unroll factors using iterative compilation

Kisuki, Toru; Knijnenburg, Peter M. W.; O’Boyle, Michael

doi:10.1109/pact.2000.888348

Cited by 116 publications

(138 citation statements)

References 11 publications

Supporting

Mentioning

135

Contrasting

Order By: Relevance

“…In recent years, considerable research has addressed iterative compilation and its benefits have been reported in several publications [22], [10], [11], [15], [19], [1]. Iterative compilation has been shown to regularly outperform the most aggressive compilation settings of commercial compilers, and it has often been comparable to hand-optimized library functions [39], [16], [33], [38].…”

Section: Related Workmentioning

confidence: 99%

Predictive Modeling in a Polyhedral Optimization Space

Park

Cavazos²,

Pouchet³

et al. 2013

Int J Parallel Prog

View full text Add to dashboard Cite

Abstract-Significant advances in compiler optimization have been made in recent years, enabling many transformations such as tiling, fusion, parallelization and vectorization on imperfectly nested loops. Nevertheless, the problem of finding the best combination of loop transformations remains a major challenge. Polyhedral models for compiler optimization have demonstrated strong potential for enhancing program performance, in particular for compute-intensive applications. But existing static cost models to optimize polyhedral transformations have significant limitations, and iterative compilation has become a very promising alternative to these models to find the most effective transformations. But since the number of polyhedral optimization alternatives can be enormous, it is often impractical to iterate over a significant fraction of the entire space of polyhedrally transformed variants. Recent research has focused on iterating over this search space either with manually-constructed heuristics or with automatic but very expensive search algorithms (e.g., genetic algorithms) that can eventually find good points in the polyhedral space.In this paper, we propose the use of machine learning to address the problem of selecting the best polyhedral optimizations. We show that these models can quickly find high-performance program variants in the polyhedral space, without resorting to extensive empirical search. We introduce models that take as input a characterization of a program based on its dynamic behavior, and predict the performance of aggressive high-level polyhedral transformations that includes tiling, parallelization and vectorization. We allow for a minimal empirical search on the target machine, discovering on average 83% of the searchspace-optimal combinations in at most 5 runs. Our end-to-end framework is validated using numerous benchmarks on two multi-core platforms.

show abstract

Section: Related Workmentioning

confidence: 99%

Predictive Modeling in a Polyhedral Optimization Space

Park

Cavazos²,

Pouchet³

et al. 2013

Int J Parallel Prog

View full text Add to dashboard Cite

show abstract

“…array padding and tiling and unrolling factors for a loop [12]), where all choices are legal. A notable exception to this is [13].…”

Section: Iterative Optimisationmentioning

confidence: 99%

Iterative Collective Loop Fusion

Ashby

O’Boyle

2006

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Naive code generation from high-level languages that encourage modularity can give rise to large numbers of simple loops for arraybased programs. Collective loop fusion and array contraction can be used on such codes to improve temporal locality and performance. The problem is typically formalised using a loop dependence graph (LDG), with solutions denoted by fusion partitions. Much previous work has concentrated on approaches to the abstract formulation. We present our technique called iterative collective loop fusion based on empirically evaluating different transformations, and show how it can provide speedups over existing approaches of up to 1.38. We also give results showing that applying such techniques to high-level languages can provide speedups of up to 2.45 over the original code, and outperforms an equivalent code in Fortran.

show abstract

“…For operational properties, determining the order or the configuration to apply optimizations has recently been experimentally explored by Triantafyllis et al [6], Cooper et al [7], and Kisuki et al [8]. The interaction and ordering property was formally explored by Whitfield and Soffa [9].…”

Section: Related Researchmentioning

confidence: 99%

Developing a Foundation for Code Optimization

Soffa

2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Although optimization technology has been successful over the past 40 years, recent trends are emerging that demand we reconsider the paradigm that we are using for code optimization. In particular, the trends toward dynamic optimization, writing embedded system software in high level languages and the lack of significant performance improvement from current optimization research are forcing us to rethink what we know and do not know about optimization. A number of problems dealing with both semantic and application properties of optimizations have always existed but have been mostly ignored. The challenge in optimization today is to explore properties of optimizations and develop a framework for better understanding and use of optimizations. Fortunately, research is starting to explore properties, including proving the soundness of optimizations, proving the correctness of optimizations, specifications of optimizations, and the predictability of profits of optimizations. Not only must we understand the properties, but we also need to integrate the properties into a framework. Only then can we address the problems of the developing trends.

show abstract

Combined selection of tile sizes and unroll factors using iterative compilation

Cited by 116 publications

References 11 publications

Predictive Modeling in a Polyhedral Optimization Space

Predictive Modeling in a Polyhedral Optimization Space

Iterative Collective Loop Fusion

Developing a Foundation for Code Optimization

Contact Info

Product

Resources

About