Iterative optimization in the polyhedral model

Pouchet, Louis-Noël; Bastoul, Cédric; Cohen, Albert; Cavazos, John

doi:10.1145/1375581.1375594

Cited by 79 publications

(16 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, it is possible to represent a sequence of different program transformations in the form of one transformation in the polyhedral model. The polyhedral model can be used for parts of the program wherein the execution control flow is statically predictable [15].…”

Section: Overview Of Polyhedral Modelmentioning

confidence: 99%

Locality-Conscious Nested-Loops Parallelization

Parsa¹

2014

ETRI J

View full text Add to dashboard Cite

To speed up data-intensive programs, two complementary techniques, namely nested loops parallelization and data locality optimization, should be considered. Effective parallelization techniques distribute the computation and necessary data across different processors, whereas data locality places data on the same processor. Therefore, locality and parallelization may demand different loop transformations. As such, an integrated approach that combines these two can generate much better results than each individual approach. This paper proposes a unified approach that integrates these two techniques to obtain an appropriate loop transformation. Applying this transformation results in coarse grain parallelism through exploiting the largest possible groups of outer permutable loops in addition to data locality through dependence satisfaction at inner loops. These groups can be further tiled to improve data locality through exploiting data reuse in multiple dimensions.

show abstract

Section: Overview Of Polyhedral Modelmentioning

confidence: 99%

Locality-Conscious Nested-Loops Parallelization

Parsa¹

2014

ETRI J

View full text Add to dashboard Cite

show abstract

“…To ensure that two statements are fusible, we can build a Parametric Integer Program [7] with sufficient constraints for the existence of a semantics-preserving multidimensional schedule [14], [12], in conjunction with the constraints imposed by Definition 1. If this PIP has a solution, then the two statements are fusible.…”

Section: A Loop Fusion and Fusibility Of Statementsmentioning

confidence: 99%

“…In addition, we also require the class identifier to reflect the order in which classes are executed, to model code motion. A general framework for this purpose has been developed by Pouchet [12] in the context of multi-level partitions using arbitrary scheduling coefficients. However in the context of the present work we limit ourselves to the modeling of fusible statements at the outer loop level only, a restriction of the general case.…”

Section: B Modeling Program Partitioningmentioning

confidence: 99%

See 1 more Smart Citation

Combined Iterative and Model-driven Optimization in an Automatic Parallelization Framework

Pouchet¹,

Bondhugula

Bastoul

et al. 2010

2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis

Self Cite

View full text Add to dashboard Cite

Today's multi-core era places significant demands on an optimizing compiler, which must parallelize programs, exploit memory hierarchy, and leverage the ever-increasing SIMD capabilities of modern processors. Existing model-based heuristics for performance optimization used in compilers are limited in their ability to identify profitable parallelism/locality trade-offs and usually lead to sub-optimal performance.To address this problem, we distinguish optimizations for which effective model-based heuristics and profitability estimates exist, from optimizations that require empirical search to achieve good performance in a portable fashion. We have developed a completely automatic framework in which we focus the empirical search on the set of valid possibilities to perform fusion/code motion, and rely on model-based mechanisms to perform tiling, vectorization and parallelization on the transformed program. We demonstrate the effectiveness of this approach in terms of strong performance improvements on a single target as well as performance portability across different target architectures.

show abstract

“…Their framework is parameterized with respect to the search algorithm and includes numerous search strategies. Pouchet et al [37] use decoupling heuristics and a genetic algorithm in the setting of a polyhedral model to search for high-performance loop nestings. In this paper we use analytic models to quickly discard unprofitable choices then use empirical testing to narrow in on the best.…”

Section: Loop Restructuring Compilersmentioning

confidence: 99%

Automating the generation of composed linear algebra kernels

Belter

Jessup

Karlin

et al. 2009

Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis

View full text Add to dashboard Cite

Memory bandwidth limits the performance of important kernels in many scientific applications. Such applications often use sequences of Basic Linear Algebra Subprograms (BLAS), and highly efficient implementations of those routines enable scientists to achieve high performance at little cost. However, tuning the BLAS in isolation misses opportunities for memory optimization that result from composing multiple subprograms. Because it is not practical to create a library of all BLAS combinations, we have developed a domain-specific compiler that generates them on demand. In this paper, we describe a novel algorithm for compiling linear algebra kernels and searching for the best combination of optimization choices. We also present a new hybrid analytic/empirical method for quickly evaluating the profitability of each optimization. We report experimental results showing speedups of up to 130% relative to the GotoBLAS on an AMD Opteron and up to 137% relative to MKL on an Intel Core 2.

show abstract

Iterative optimization in the polyhedral model

Cited by 79 publications

References 74 publications

Locality-Conscious Nested-Loops Parallelization

Locality-Conscious Nested-Loops Parallelization

Combined Iterative and Model-driven Optimization in an Automatic Parallelization Framework

Automating the generation of composed linear algebra kernels

Contact Info

Product

Resources

About