SSM-RDU: A Reconfigurable Dataflow Unit for Long-Sequence State-Space Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911101059334144 |
|---|---|
| author | Ko, Sho Olukotun, Kunle |
| author_facet | Ko, Sho Olukotun, Kunle |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_22937 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SSM-RDU: A Reconfigurable Dataflow Unit for Long-Sequence State-Space Models Ko, Sho Olukotun, Kunle Hardware Architecture 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. |
| title | SSM-RDU: A Reconfigurable Dataflow Unit for Long-Sequence State-Space Models |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2503.22937 |