FuseFlow: A Fusion-Centric Compilation Framework for Sparse Deep Learning on Streaming Dataflow

@inproceedings{lacouture2026fuseflow,
  author    = {Lacouture, Rubens and Zhang, Nathan and Sharma, Ritvik and Siracusa, Marco and Kjolstad, Fredrik and Olukotun, Kunle and Hsu, Olivia},
  title     = {{FuseFlow}: A Fusion-Centric Compilation Framework for Sparse Deep Learning on Streaming Dataflow},
  booktitle = {Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2},
  year      = {2026},
  month     = mar,
  pages     = {798--820},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  doi       = {10.1145/3779212.3790165},
  url       = {https://doi.org/10.1145/3779212.3790165},
  keywords  = {sparse machine learning, Einsum, tensor compiler, kernel fusion, spatial dataflow accelerator}
}

Rubens Lacouture, Nathan Zhang, Ritvik Sharma, Marco Siracusa, Fredrik Kjolstad, Kunle Olukotun, and Olivia Hsu. FuseFlow: A Fusion-Centric Compilation Framework for Sparse Deep Learning on Streaming Dataflow. ASPLOS, 2026.