Metraipolis › archive › dc_7cfa2788046c

FlexSpIM: An Event-Based Digital Compute-In-Memory Accelerator with Flexible Operand Resolution and Layer-Wise Hybrid Stationarity — arXiv:2609.08446

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.08446
License (as archived)
CC0-1.0
Archived
2026-10-16T13:14:41.392Z
SHA-256 of the archived text
adffe55e1e2c5461cae3a6a692884908afb6d74ec66c833be0eac7278d5d2152
Stable URL of this page
https://metraipolis.com/documento/dc_7cfa2788046c

How to cite

FlexSpIM: An Event-Based Digital Compute-In-Memory Accelerator with Flexible Operand Resolution and Layer-Wise Hybrid Stationarity — arXiv:2609.08446 — arXiv (en), https://arxiv.org/abs/2609.08446 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7cfa2788046c (Metraipolis archive dc_7cfa2788046c, sha256 adffe55e1e2c5461cae3a6a692884908afb6d74ec66c833be0eac7278d5d2152)
BibTeX
@misc{dc7cfa2788046c,
  title = {FlexSpIM: An Event-Based Digital Compute-In-Memory Accelerator with Flexible Operand Resolution and Layer-Wise Hybrid Stationarity — arXiv:2609.08446},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.08446},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7cfa2788046c; sha256 adffe55e1e2c5461cae3a6a692884908afb6d74ec66c833be0eac7278d5d2152},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08446. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Compute-in-memory (CIM) accelerators for spiking neural networks (SNNs) offer a promising solution for achieving $\mu$s-level inference latency and ultra-low energy in edge vision applications. However, their limited flexibility at both circuit and system levels restricts their deployment across diverse workloads. This work introduces FlexSpIM, a digital CIM architecture supporting arbitrary operand resolution and shape within a unified storage for weights and neuron states (i.e., membrane potentials). These circuit-level capabilities enable a layer-level hybrid weight- and output-stationary dataflow, maximizing operand reuse and reducing costly on- and off-chip data movement during SNN execution. Measurement results from a fabricated FlexSpIM prototype in 40-nm CMOS demonstrate competitive 1-bit-normalized energy efficiency and higher throughput compared with prior fixed-precision digital CIM-based SNN accelerators, while providing bitwise resolution reconfiguration. Evaluated on the IBM DVS gesture dataset, FlexSpIM achieves 95.8% accuracy while enabling up to 45% energy and 52% latency reductions in large-scale systems compared with fixed stationarity approaches.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-09 in cs.AR).
Categorie arXiv: Hardware Architecture (cs.AR).
Pagina del lavoro: https://arxiv.org/abs/2609.08446 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T13:02:36.889Z dalla pagina https://arxiv.org/catchup/cs.AR/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).