Publications of Torsten Hoefler

Tal Ben-Nun, Lukas Gianinazzi, Torsten Hoefler, Yishai Oltchik:

Maximum Flows in Parametric Graph Templates

(In Algorithms and Complexity - 13th International Conference, Jun. 2023)

Abstract

Execution graphs of parallel loop programs exhibit a nested, repeating structure. We show how such graphs that are the result of nested repetition can be represented by succinct parametric structures. This parametric graph template representation allows us to reason about the execution graph of a parallel program at a cost that only depends on the program size. We develop structurally-parametric polynomial-time algorithm variants of maximum flows. When the graph models a par- allel loop program, the maximum flow provides a bound on the data movement during an execution of the program. By reasoning about the structure of the repeating subgraphs, we avoid explicit construction of the instantiation (e.g., the execution graph), potentially saving an ex- ponential amount of memory and computation. Hence, our approach enables graph-based dataflow analysis in previously intractable settings.

Documents

download article:

download slides:

BibTeX

@inproceedings{,
  author={Tal Ben-Nun and Lukas Gianinazzi and Torsten Hoefler and Yishai Oltchik},
  title={{Maximum Flows in Parametric Graph Templates}},
  year={2023},
  month={Jun.},
  booktitle={Algorithms and Complexity - 13th International Conference},
  source={http://www.unixer.de/~htor/publications/},
}


serving: 44.212.94.18:40650	© Torsten Hoefler