{"ID":2837863,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.00059","arxiv_id":"2512.00059","title":"SafeCiM: Investigating Resilience of Hybrid Floating-Point Compute-in-Memory Deep Learning Accelerators","abstract":"Deep Neural Networks (DNNs) continue to grow in complexity with Large Language Models (LLMs) incorporating vast numbers of parameters. Handling these parameters efficiently in traditional accelerators is limited by data-transmission bottlenecks, motivating Compute-in-Memory (CiM) architectures that integrate computation within or near memory to reduce data movement. Recent work has explored CiM designs using Floating-Point (FP) and Integer (INT) operations. FP computations typically deliver higher output quality due to their wider dynamic range and precision, benefiting precision-sensitive Generative AI applications. These include models such as LLMs, thus driving advancements in FP-CiM accelerators. However, the vulnerability of FP-CiM to hardware faults remains underexplored, posing a major reliability concern in mission-critical settings. To address this gap, we systematically analyze hardware fault effects in FP-CiM by introducing bit-flip faults at key computational stages, including digital multipliers, CiM memory cells, and digital adder trees. Experiments with Convolutional Neural Networks (CNNs) such as AlexNet and state-of-the-art LLMs including LLaMA-3.2-1B and Qwen-0.3B-Base reveal how faults at each stage affect inference accuracy. Notably, a single adder fault can reduce LLM accuracy to 0%. Based on these insights, we propose a fault-resilient design, SafeCiM, that mitigates fault impact far better than a naive FP-CiM with a pre-alignment stage. For example, with 4096 MAC units, SafeCiM reduces accuracy degradation by up to 49x for a single adder fault compared to the baseline FP-CiM architecture.","short_abstract":"Deep Neural Networks (DNNs) continue to grow in complexity with Large Language Models (LLMs) incorporating vast numbers of parameters. Handling these parameters efficiently in traditional accelerators is limited by data-transmission bottlenecks, motivating Compute-in-Memory (CiM) architectures that integrate computatio...","url_abs":"https://arxiv.org/abs/2512.00059","url_pdf":"https://arxiv.org/pdf/2512.00059v1","authors":"[\"Swastik Bhattacharya\",\"Sanjay Das\",\"Anand Menon\",\"Shamik Kundu\",\"Arnab Raha\",\"Kanad Basu\"]","published":"2025-11-23T01:06:01Z","proceeding":"cs.AR","tasks":"[\"cs.AR\",\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\",\"Convolutional Neural Network\"]","has_code":false}