军事知识服务平台
存算一体——重塑芯片架构新势力
CIM/PIM/PNM:An Emerging Force Reshaping Chip Architecture
摘要 存算一体技术通过将计算单元与存储单元深度融合或物理级邻近部署,从架构层面缓解了数据搬运瓶颈带来的压力.大语言模型(LLMs)及智能体(Agentic AI)的持续演进,对计算架构的高带宽、低延迟与高能效比提出了严苛要求.系统梳理了基于静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、闪存(Flash)及新兴非易失性存储器的存算一体技术路径,涵盖存内计算(CIM)、存内处理(PIM)与近存处理(PNM)三大主流范式,综述其研究进展、典型应用案例及面临的技术挑战.分析表明,不同技术路径展现出差异化的性能与能效优势,可通过场景驱动的技术融合、软硬件协同设计及产业链生态协同实现优势互补,为下一代人工智能芯片的架构创新提供有益参考.
Abstract:
Compute-in-Memory(CIM),Processing-in-Memory(PIM),and Processing-Near-Memory(PNM)hold the promise of fundamen-tally resolving the data movement bottleneck by integrating computing logic with memory units or placing them in close physical proximity.A systematic review is presented of CIM,PIM,and PNM technical paths implemented on static random-access memory(SRAM),dynamic random-access memory(DRAM),Flash,and emerging non-volatile memories,covering their research progress,representative use cases,and associated challenges.The analysis reveals that each technical path exhibits distinct performance and energy-efficiency advantages.It is argued that scenario-driven technology fusion,hardware-software co-design,and industry-wide ecosystem collaboration are essential for harnessing complementary strengths across these paths.This work is intended to serve as a valuable reference for architectural innova-tion in next-generation AI chips.
刊 名 中兴通讯技术 ISTICPKU
年,卷(期): 2026, 32(4)
机标分类号: TN911.72 TP368.1 TN402
在线出版日期: 2026年10月21日