Answers are grounded in this paper and cite their sources.
The rapid proliferation of intelligent sensors has led to increased latency and privacy risks when processing data on a remote server. This work proposes a spin-transfer torque magnetic random access memory (STT-MRAM) compute-in-memory (CIM) macro to enhance inference efficiency for an artificial intelligence (AI) model on the edge device. A sparsity-adaptive design is presented, featuring coupled-1T1M (c-1T1M) computing cells to eliminate bit-level activation computing power overhead and suppress pattern-dependent deviations in the result. An activation-aware voltage comparator array (AA-VCA) reduces power consumption by up to56×and improves sensing margin by13×. At the system level, a hybrid-granularity sparsity workflow accelerates inference and aligns well with compact analog CIM architectures. In addition, a hardware-implemented variational autoencoder (VAE) is deployed to enhance processing capabilities. The test chip is fabricated in 28-nm CMOS with 60-nm MTJ, achieving energy efficiencies of 712 TOPS/W for image classification and 492.8 TOPS/W for anomaly detection, along with an accuracy of 96.3% and an$F1$score of 0.97.
No takes yet. Share an insight, caveat, or question.
Cui et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: