Felix, qui, quod amat, defendere fortiter audet
Home -> Publications
Home
  Publications
    
edited volumes
  Awards
  Research
  Teaching
  Miscellaneous
  Full CV [pdf]
  BLOG






  Events








  Past Events





Publications of Torsten Hoefler
Tiziano De Matteis, Lukas Gianinazzi, Johannes de Fine Licht, Torsten Hoefler:

 Streaming Task Graph Scheduling for Dataflow Architectures

(Jun. 2023)

Publisher Reference

Abstract

Dataflow devices represent an avenue towards saving the control and data movement overhead of Load-Store Architectures. Various dataflow accelerators have been proposed, but how to efficiently schedule applications on such devices remains an open problem. The programmer can explicitly implement both temporal and spatial parallelism, and pipelining across multiple processing elements can be crucial to take advantage of the fast on-chip interconnect, enabling the concurrent execution of different program components. This paper introduces canonical task graphs, a model that enables streaming scheduling of task graphs over dataflow architectures. We show how a task graph can be statically analyzed to understand its steady-state behavior, and we use this information to partition it into temporally multiplexed components of spatially executed tasks. Results on synthetic and realistic workloads show how streaming scheduling can increase speedup and device utilization over a traditional scheduling approach.

Documents

Publisher URL: https://doi.org/10.1145/3588195.3592999    


Recorded talk (best effort)

 

BibTeX

@inproceedings{,
  author={Tiziano De Matteis and Lukas Gianinazzi and Johannes de Fine Licht and Torsten Hoefler},
  title={{Streaming Task Graph Scheduling for Dataflow Architectures}},
  year={2023},
  month={Jun.},
  source={http://www.unixer.de/~htor/publications/},
}


serving: 44.210.151.5:51802© Torsten Hoefler