Stardust: Compiling Sparse Tensor Algebra to a Reconfigurable Dataflow Architecture

Olivia Hsu; Alexander Rucker; Tian Zhao; Varun Desai; Kunle Olukotun; Fredrik Kjolstad

doi:10.1145/3696443.3708918

CGO · March 2025

Stardust: Compiling Sparse Tensor Algebra to a Reconfigurable Dataflow Architecture

Olivia Hsu Alexander RuckerTian ZhaoVarun DesaiKunle Olukotun Fredrik Kjolstad

IEEE/ACM International Symposium on Code Generation and Optimization

Read PDF DOI

Topics Sparse tensor algebra Accelerators & dataflow

Related software

SAM: The Sparse Abstract Machine A streaming-dataflow abstract machine and intermediate representation for compiling sparse tensor algebra to reconfigurable and fixed-function dataflow accelerators.

Cite this paper

BibTeX

@inproceedings{hsu2025stardust,
  author    = {Hsu, Olivia and Rucker, Alexander and Zhao, Tian and Desai, Varun and Olukotun, Kunle and Kjolstad, Fredrik},
  title     = {{Stardust}: Compiling Sparse Tensor Algebra to a Reconfigurable Dataflow Architecture},
  booktitle = {Proceedings of the 23rd ACM/IEEE International Symposium on Code Generation and Optimization},
  year      = {2025},
  month     = mar,
  pages     = {628--643},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  doi       = {10.1145/3696443.3708918},
  url       = {https://doi.org/10.1145/3696443.3708918},
  keywords  = {sparse tensor algebra, DSLs, compilers, dataflow, reconfigurable architectures, parallel patterns}
}

Citation

Olivia Hsu, Alexander Rucker, Tian Zhao, Varun Desai, Kunle Olukotun, and Fredrik Kjolstad. Stardust: Compiling Sparse Tensor Algebra to a Reconfigurable Dataflow Architecture. CGO, 2025.

All publications