APIM: An Antiferromagnetic MRAM-Based Processing-In-Memory System for Efficient Bit-Level Operations of Quantized Convolutional Neural Networks

Quantized convolutional neural network (QCNN) is an attractive approach that reduces hardware overheads, especially for energy-constrained systems. However, existing QCNNs still require nontrivial hardware resources and memory capacity in order not to compromise model accuracy. To address this issue, we propose an antiferromagnetic magnetic random-access memory (ARAM)-based processing-in-memory (PIM) system, leveraging bit-level sparsity. Three optimization techniques are proposed to optimize hardware resource utilization while preserving CNN accuracy. First, the ARAM-based memory subsystem allows dynamic adaptation of variable bit-width across CNN layers. Second, the bit-level accelerator employs the bit-fusion format engineered for processing data from the ARAM subsystem. Third, a customized data path within the RISC-V core guarantees efficient instruction processing to the ARAM-based memory subsystem and bit-level accelerator, enabling optimal bit-level data transmission and computation. Experimental results demonstrate that this design remarkably reduces data movement by 50%–83% across existing CNNs. Compared to state-of-the-art designs, it enhances throughput and latency by an average of <inline-formula> <tex-math notation="LaTeX">$5\times $ </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">$10\times $ </tex-math></inline-formula>, respectively. In addition, this design achieves speedups between <inline-formula> <tex-math notation="LaTeX">$1.63\times $ </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">$2.96\times $ </tex-math></inline-formula>, outstripping other designs in AlexNet, VGG16, and ResNet18 benchmarks.