arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.19973cs.AR
收藏

STISA:一种基于FPGA的0.16 GOPS/W/PE单次推理SNN加速器,采用算法与硬件协同设计

STISA: A 0.16 GOPS/W/PE Single-Shot Inference FPGA-based SNN Accelerator with Algorithm and Hardware Co-Design

Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University(浙江大学伊利诺伊大学厄巴纳香槟校区联合学院,浙江大学);Singapore University of Technology and Design(新加坡科技设计大学)

Kainan Wang, Chengyi Yang, Lei Liu, Chengting Yu, Yee Sin Ang, Bo Wang, Aili Wang

AI总结:

本研究提出基于FPGA的STISA SNN加速器,通过算法-硬件协同设计,采用TSC、TPOS映射与BMS架构,在多数据集上实现精度、延迟与能效的平衡,能效达0.16 GOPS/W/PE,优于现有同类加速器。

摘要:

脉冲神经网络(SNN)因事件驱动特性在低功耗智能计算领域具有巨大潜力,但时间依赖性导致的高推理延迟和低效硬件利用率限制了其部署。现有加速器难以在时间步长、精度与能效间取得平衡,面向硬件的时间步长压缩技术也未得到充分探索。为应对这些挑战,本研究提出STISA,这是一个统一的算法-硬件协同设计框架,包含:(i)时间拆分压缩(TSC)技术,搭配时间拆分结构(TSS),在保留网络动力学的同时减少时间冗余;(ii)硬件高效的时空并行方案,通过时间优先输出驻留(TPOS)映射与灵活的块多路选择流(BMS)架构协同优化数据流与架构;(iii)联合TSC-TPOS-BMS协同优化框架,具备带宽感知的资源分配策略,可在不同网络架构间实现精度、延迟与能效的平衡。算法层面,TSC将突触操作减少24.44%-51.71%,并在CIFAR-10、CIFAR-100、ImageNet和DVS-CIFAR10上分别达到96.38%、81.10%、68.51%和82.40%的竞争力精度。硬件层面,FPGA原型实现了最高7.99倍加速、30.4%的功耗降低和30.1%的查找表(LUT)减少。与现有最先进的SNN加速器相比,STISA达到0.16 GOPS/W/PE,在受限硬件资源下为实时SNN推理展现出可扩展性与卓越能效。

英文摘要:

Spiking neural networks (SNNs) offer great potential for low-power intelligent computing owing to their event-driven nature, yet their deployment is limited by high inference latency and inefficient hardware utilization caused by temporal dependencies. Existing accelerators struggle to balance timesteps, accuracy, and energy efficiency, while hardware-oriented timestep compression remains underexplored. To address these challenges, this work presents STISA, a unified algorithm-hardware co-design framework featuring: (i) a Temporal Splitter Compression (TSC) technique with a Temporal Split Structure (TSS) to reduce temporal redundancy while preserving network dynamics; (ii) a hardware-efficient spatiotemporal parallelism scheme, which co-optimizes dataflow and architecture through a Temporal-Prioritized Output-Stationary (TPOS) mapping and a flexible Block-Mux Streaming (BMS) architecture; and (iii) a joint TSC-TPOS-BMS co-optimization framework featuring a bandwidth-aware resource allocation strategy to achieve balanced accuracy, latency, and energy efficiency across diverse network architectures. On the algorithmic side, TSC reduces synaptic operations by 24.44%-51.71% while achieving competitive accuracies of 96.38%, 81.10%, 68.51%, and 82.40% on CIFAR-10, CIFAR-100, ImageNet, and DVS-CIFAR10, respectively. On the hardware side, FPGA prototypes deliver up to 7.99 speedup, 30.4% power reduction, and 30.1% LUT reduction. Compared with state-of-the-art SNN accelerators, STISA achieves 0.16 GOPS/W/PE, demonstrating its scalability and superior energy efficiency for real-time SNN inference under constrained hardware resources.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑