Skip to content

Publications

If you use the Snitch cluster or its extensions in your work, you can cite us:

Snitch: A Tiny Pseudo Dual-Issue Processor for Area and Energy Efficient Execution of Floating-Point Intensive Workloads

@ARTICLE{zaruba2021snitch,
  author={Zaruba, Florian and Schuiki, Fabian and Hoefler, Torsten and Benini, Luca},
  journal={IEEE Transactions on Computers}, 
  title={Snitch: A Tiny Pseudo Dual-Issue Processor for Area and Energy Efficient Execution of Floating-Point Intensive Workloads}, 
  year={2021},
  volume={70},
  number={11},
  pages={1845-1860},
  doi={10.1109/TC.2020.3027900}
}

Stream Semantic Registers: A Lightweight RISC-V ISA Extension Achieving Full Compute Utilization in Single-Issue Cores

@ARTICLE{schuiki2021ssr,
  author={Schuiki, Fabian and Zaruba, Florian and Hoefler, Torsten and Benini, Luca},
  journal={IEEE Transactions on Computers}, 
  title={Stream Semantic Registers: A Lightweight RISC-V ISA Extension Achieving Full Compute Utilization in Single-Issue Cores}, 
  year={2021},
  volume={70},
  number={2},
  pages={212-227},
  doi={10.1109/TC.2020.2987314}
}

Sparse Stream Semantic Registers: A Lightweight ISA Extension Accelerating General Sparse Linear Algebra

@ARTICLE{scheffler2023sparsessr,
  author={Scheffler, Paul and Zaruba, Florian and Schuiki, Fabian and Hoefler, Torsten and Benini, Luca},
  journal={IEEE Transactions on Parallel and Distributed Systems}, 
  title={Sparse Stream Semantic Registers: A Lightweight ISA Extension Accelerating General Sparse Linear Algebra}, 
  year={2023},
  volume={34},
  number={12},
  pages={3147-3161},
  doi={10.1109/TPDS.2023.3322029}
}

A High-Performance, Energy-Efficient Modular DMA Engine Architecture

@ARTICLE{benz2024idma,
  author={Benz, Thomas and Rogenmoser, Michael and Scheffler, Paul and Riedel, Samuel and Ottaviano, Alessandro and Kurth, Andreas and Hoefler, Torsten and Benini, Luca},
  journal={IEEE Transactions on Computers}, 
  title={A High-Performance, Energy-Efficient Modular DMA Engine Architecture}, 
  year={2024},
  volume={73},
  number={1},
  pages={263-277},
  doi={10.1109/TC.2023.3329930}
}

MiniFloat-NN and ExSdotp: An ISA Extension and a Modular Open Hardware Unit for Low-Precision Training on RISC-V Cores

@INPROCEEDINGS{bertaccini2022minifloat,
  author={Bertaccini, Luca and Paulin, Gianna and Fischer, Tim and Mach, Stefan and Benini, Luca},
  booktitle={2022 IEEE 29th Symposium on Computer Arithmetic (ARITH)}, 
  title={MiniFloat-NN and ExSdotp: An ISA Extension and a Modular Open Hardware Unit for Low-Precision Training on RISC-V Cores}, 
  year={2022},
  volume={},
  number={},
  pages={1-8},
  doi={10.1109/ARITH54963.2022.00010}
}

Soft Tiles: Capturing Physical Implementation Flexibility for Tightly-Coupled Parallel Processing Clusters

@INPROCEEDINGS{paulin2022softtiles,
  author={Paulin, Gianna and Cavalcante, Matheus and Scheffler, Paul and Bertaccini, Luca and Zhang, Yichao and Gürkaynak, Frank and Benini, Luca},
  booktitle={2022 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)}, 
  title={Soft Tiles: Capturing Physical Implementation Flexibility for Tightly-Coupled Parallel Processing Clusters}, 
  year={2022},
  volume={},
  number={},
  pages={44-49},
  doi={10.1109/ISVLSI54635.2022.00021}
}

SARIS: Accelerating Stencil Computations on Energy-Efficient RISC-V Compute Clusters with Indirect Stream Registers

@misc{scheffler2024saris,
  title={SARIS: Accelerating Stencil Computations on Energy-Efficient
         RISC-V Compute Clusters with Indirect Stream Registers},
  author={Paul Scheffler and Luca Colagrande and Luca Benini},
  year={2024},
  eprint={2404.05303},
  archivePrefix={arXiv},
  primaryClass={cs.MS},
  url={https://arxiv.org/abs/2404.05303}
}