Integrated Loop Optimizations for Data Locality Enhancement of Tensor Contraction Expressions

@article{Sahoo2005IntegratedLO,
  title={Integrated Loop Optimizations for Data Locality Enhancement of Tensor Contraction Expressions},
  author={S. Sahoo and S. Krishnamoorthy and Rajkiran Panuganti and P. Sadayappan},
  journal={ACM/IEEE SC 2005 Conference (SC'05)},
  year={2005},
  pages={13-13}
}
A very challenging issue for optimizing compilers is the phase ordering problem: In what order should a collection of compiler optimizations be performed? We address this problem in the context of optimizing a sequence of tensor contractions. The pertinent loop transformations are loop permutation, tiling, and fusion; in addition, the placement of disk I/O statements crucially affects performance. The space of possible combinations is exponentially large. We develop novel pruning strategies… Expand
Efficient search‐space pruning for integrated fusion and tiling transformations
Integrated compiler optimizations for tensor contractions
Hypergraph Partitioning for Automatic Memory Hierarchy Management
Automatic transformation and optimization of applications on gpus and gpu clusters
...
1
2
...