TReCiM: Lower Power and Temperature-Resilient Multibit 2FeFET-1T Compute-in-Memory Design

Abstract

Compute-in-memory (CiM) emerges as a promising solution to solve hardware challenges in artificial intelligence (AI) and the Internet of Things (IoT), particularly addressing the "memory wall" issue. By utilizing nonvolatile memory (NVM) devices in a crossbar structure, CiM efficiently accelerates multiply-accumulate (MAC) computations, the crucial operations in neural networks and other AI models. Among various NVM devices, Ferroelectric FET (FeFET) is particularly appealing for ultra-low-power CiM arrays due to its CMOS compatibility, voltage-driven write/read mechanisms and high ION/IOFF ratio. Moreover, subthreshold-operated FeFETs, which operate at scaling voltages in the subthreshold region, can further minimize the power consumption of CiM array. However, subthreshold-FeFETs are susceptible to temperature drift, resulting in computation accuracy degradation. Existing solutions exhibit weak temperature resilience at larger array size and only support 1-bit. In this paper, we propose TReCiM, an ultra-low-power temperature-resilient multibit 2FeFET-1T CiM design that reliably performs MAC operations in the subthreshold-FeFET region with temperature ranging from 0 to 85 degrees Celcius at scale. We benchmark our design using NeuroSim framework in the context of VGG-8 neural network architecture running the CIFAR-10 dataset. Benchmarking results suggest that when considering temperature drift impact, our proposed TReCiM array achieves 91.31% accuracy, with 1.86% accuracy improvement compared to existing 1-bit 2T-1FeFET CiM array. Furthermore, our proposed design achieves 48.03 TOPS/W energy efficiency at system level, comparable to existing designs with smaller technology feature sizes.

arXiv comment9 pages, 9 figures, to be published in the 43st ICCAD (ACM/IEEE International Conference on Computer-Aided Design) proceedings

References in corpus (10)

• Training and Inference with Integers in Deep Neural Networks
• A Ferroelectric Compute-in-Memory Annealer for Combinatorial Optimization Problems
• FeBiM: Efficient and Compact Bayesian Inference Engine Empowered with Ferroelectric In-Memory Computing
• COSIME: FeFET based Associative Memory for In-Memory Cosine Similarity Search
• SEE-MCAM: Scalable Multi-bit FeFET Content Addressable Memories for Energy Efficient Associative Search
• CorrectNet: Robustness Enhancement of Analog In-Memory Computing for Neural Networks by Error Suppression and Compensation
• Improving Realistic Worst-Case Performance of NVCiM DNN Accelerators through Training with Right-Censored Gaussian Noise
• Low Power and Temperature-Resilient Compute-In-Memory Based on Subthreshold-FeFET
• HyCiM: A Hybrid Computing-in-Memory QUBO Solver for General Combinatorial Optimization Problems with Inequality Constraints
• Triangle Counting Accelerations: From Algorithm to In-Memory Computing Architecture