Polyhedral parallel code generation for CUDA

@article{Verdoolaege2013PolyhedralPC,
  title={Polyhedral parallel code generation for CUDA},
  author={Sven Verdoolaege and Juan Carlos Juega and Albert Cohen and Jos{\'e} Ignacio G{\'o}mez and Christian Tenllado and Francky Catthoor},
  journal={TACO},
  year={2013},
  volume={9},
  pages={54:1-54:23}
}
This article addresses the compilation of a sequential program for parallel execution on a modern GPU. To this end, we present a novel source-to-source compiler called PPCG. PPCG singles out for its ability to accelerate computations from any static control loop nest, generating multiple CUDA kernels when necessary. We introduce a multilevel tiling strategy and a code generation scheme for the parallelization and locality optimization of imperfectly nested loops, managing memory and exposing… CONTINUE READING

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 159 CITATIONS

Domain-Specific Optimization and Generation of High-Performance GPU Code for Stencil Computations

  • Proceedings of the IEEE
  • 2018
VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Implementing and Evaluating Candidate-Based Invariant Generation

  • IEEE Transactions on Software Engineering
  • 2016
VIEW 9 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

VOBLA: a vehicle for optimized basic linear algebra

VIEW 12 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2008
2019

CITATION STATISTICS

  • 43 Highly Influenced Citations

  • Averaged 26 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 13 REFERENCES

OpenACC: Directives for accelerators

OpenACC
  • http://www.openacc-standard.org.
  • 2011
VIEW 12 EXCERPTS
HIGHLY INFLUENTIAL

High Performance Compilers for Parallel Computing

M. WOLFE
  • Addison Wesley.
  • 1996
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Outer-loop vectorization - revisited for short SIMD architectures

  • 2008 International Conference on Parallel Architectures and Compilation Techniques (PACT)
  • 2008
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL