English

SSM-RDU: A Reconfigurable Dataflow Unit for Long-Sequence State-Space Models

Hardware Architecture 2025-08-12 v2

Abstract

Long-sequence state-space models (SSMs) such as Hyena and Mamba replace the quadratic complexity of self-attention with more efficient FFT and scan operations. However, modern accelerators like GPUs are poorly suited to these non-GEMM workloads due to rigid execution models and specialization for dense matrix operations. This paper proposes architectural extensions to a baseline Reconfigurable Dataflow Unit (RDU) that efficiently support FFT-based and scan-based SSMs. By introducing lightweight interconnect enhancements within compute tiles, the extended RDU enables spatial mapping of FFT and scan dataflows with less than 1% area and power overhead. The resulting architecture achieves a 5.95X speedup over the GPU and a 1.95X speedup over the baseline RDU for Hyena, and a 2.12X and 1.75X speedup over the GPU and baseline RDU, respectively, for Mamba.

Keywords

Cite

@article{arxiv.2503.22937,
  title  = {SSM-RDU: A Reconfigurable Dataflow Unit for Long-Sequence State-Space Models},
  author = {Sho Ko and Kunle Olukotun},
  journal= {arXiv preprint arXiv:2503.22937},
  year   = {2025}
}
R2 v1 2026-06-28T22:38:46.296Z