IEEE Journal of Solid-State Circuits · 2023 · 19 citations · 38 references
ComputingComputer EngineeringComputer ScienceArtificial IntelligenceComputer ArchitectureEdge ComputingEdge ArchitectureEdge Artificial IntelligenceEdge Data ProcessingEdge DevicesLatency OptimizationMulti-access Edge ComputingEdge IntelligenceEnergy ConsumptionEnergy-aware Edge ComputingEnergy-efficient Artificial IntelligenceEnergy-efficient Edge ComputingEnergy-efficient Edge DesignInference AccuracyMultiply-accumulate Units
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 ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$W$ </tex-math></inline-formula> ), 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 toggling rate in digital multiply-and-accumulate (MAC) circuits, 3) narrow signal margin and high memory readout latency, and 4) redundant MAC computation in digital MAC circuits under input-stationary flow. In addressing these challenges, we developed a number of schemes based on the concept of system-circuit co-design, including 1) a weight-feature aware read (WFAR) scheme; 2) a toggling-aware weight-tuning (TAWT) scheme; 3) a differential charge-accumulating margin-enhanced voltage-sensing amplifier (DCME-VSA); and 4) an input-sparsity aware pre-computing unit (ISAPU). An 8-Mb spin-transfer torque magnetic random access memory (STT-MRAM) nvNMC macro fabricated using foundry-provided 22 nm STT-MRAM achieved read bandwidth of 436 GB/s, MAC computing latency of 20 ns, and energy efficiency of 53.6–190.2 TOPS/W when performing eight-bit input and eight-bit weight MAC operations with 26-bit output and 576 accumulations.
38
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Fully hardware-implemented memristor convolutional neural network
Peng Yao, Huaqiang Wu, Bin Gao et al. · Nature · 2020 · 2.1K citations
Engineering, Computer Engineering, Electrical Engineering +12
Analogue signal and image processing with large memristor crossbars
Can Li, Miao Hu, Yunning Li et al. · Nature Electronics · 2017 · 1.3K citations
Engineering, Computer Engineering, Electrical Engineering +16
Equivalent-accuracy accelerated neural-network training using analogue memory
Stefano Ambrogio, Pritish Narayanan, Hsinyu Tsai et al. · Nature · 2018 · 1.1K citations · Full text