← 返回 JSSC 论文列表JSSC 2024第1期Memory22nmEmerging MemoryNeural Network Accelerator
An 8b-Precision 8-Mb STT-MRAM Near-Memory-Compute Macro Using Weight-Feature and
提出一种基于STT-MRAM的8位精度近存计算宏，采用系统-电路协同设计解决能效和延迟问题。
22nm STT-MRAM, 436GB/s读取带宽, 20ns计算延迟, 53.6-190.2 TOPS/W能效
近存计算STT-MRAM能效优化人工智能边缘计算
▸权重特征感知读取方案(WFAR)
▸切换感知权重调谐方案(TAWT)
▸差分电荷累积增强电压敏感放大器(DCME-VSA)
Abstract
Nonvolatile near-memory-compute (nvNMC)
macros are promising candidates for edge artificial intelligence
(AI) devices requiring high energy efficiency, short wakeup-
to-compute latency, and robust inference accuracy with high
precision of inputs (IN), weights ( W ), and outputs (OUT).
Nonetheless, the practical application of nvNMC macros
is hindered by inherent design challenges: 1) high energy
consumption in reading repetitious weight data, 2) low energy
efficiency due to high bitstream toggli