# ThRIve: Thermally Robust CNN Inference via Low-Rank Adaptation in Heterogeneous PIM Architectures

arXiv: https://arxiv.org/abs/2607.17091 · HTML: https://mlsanity.com/paper/2607.17091/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 59 references that are in the map.
- First posted on arXiv 19 Jul 2026.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting](https://mlsanity.com/paper/1904.00310/) (2019)
- [PUMA: A Programmable Ultra-efficient Memristor-based Accelerator for Machine Learning Inference](https://mlsanity.com/paper/1901.10351/) (2019)
- [Benchmarking the Performance of Bayesian Optimization across Multiple Experimental Materials Science Domains](https://mlsanity.com/paper/2106.01309/) (2021)
- [DNN+NeuroSim V2.0: An End-to-End Benchmarking Framework for Compute-in-Memory Accelerators for On-chip Training](https://mlsanity.com/paper/2003.06471/) (2020)
- [AccelTran: A Sparsity-Aware Accelerator for Dynamic Inference with Transformers](https://mlsanity.com/paper/2302.14705/) (2023)
- [Processing Data Where It Makes Sense: Enabling In-Memory Computation](https://mlsanity.com/paper/1903.03988/) (2019)
- [GraphR: Accelerating Graph Processing Using ReRAM](https://mlsanity.com/paper/1708.06248/) (2017)
- [PANTHER: A Programmable Architecture for Neural Network Training Harnessing Energy-efficient ReRAM](https://mlsanity.com/paper/1912.11516/) (2019)
- [Multi-Objective Optimization of ReRAM Crossbars for Robust DNN Inferencing under Stochastic Noise](https://mlsanity.com/paper/2109.05437/) (2021)
- [The Landscape of Compute-near-memory and Compute-in-memory: A Research and Commercial Overview](https://mlsanity.com/paper/2401.14428/) (2024)
- [Examining the Role and Limits of Batchnorm Optimization to Mitigate Diverse Hardware-noise in In-memory Computing](https://mlsanity.com/paper/2305.18416/) (2023)
- [PIM-DRAM: Accelerating Machine Learning Workloads using Processing in Commodity DRAM](https://mlsanity.com/paper/2105.03736/) (2021)
- [PIM-QAT: Neural Network Quantization for Processing-In-Memory (PIM) Systems](https://mlsanity.com/paper/2209.08617/) (2022)
- [FARe: Fault-Aware GNN Training on ReRAM-based PIM Accelerators](https://mlsanity.com/paper/2401.10522/) (2024)
- [Modelling Resistive and Phase Change Memory with Passive Selector Arrays -- A Matlab Tool](https://mlsanity.com/paper/1910.05836/) (2019)
- [An Algorithm-Hardware Co-design Framework to Overcome Imperfections of Mixed-signal DNN Accelerators](https://mlsanity.com/paper/2208.13896/) (2022)

## Abstract (arXiv)

Processing-In-Memory (PIM) has emerged as a promising technology for accelerating machine learning (ML) workloads. Specifically, non-volatile memory-based PIM architectures have enabled effective ML acceleration due to their ability to perform energy-efficient matrix-vector multiplication operations. However, these devices suffer from non-idealities such as thermal noise. This noise alters the stored values in the memory cells which correspond to actual model weights, compromising the inference accuracy. In this work, we introduce ThRIve, a noise-aware training methodology that leverages low-rank adaptation to enable thermally robust inference on heterogeneous PIM architectures. ThRIve selectively stores these low-rank noise-aware parameters on a hardware that is less susceptible to thermal noise, enabling robustness against temperature-induced noise variations. ThRIve mitigates the effects of thermal-noise and prevent the drop in inference accuracy across the entire operating temperature range. Experimental results demonstrate that ThRIve-enabled architectures maintain consistent inference accuracy, with the mean accuracy staying within 2% of the ideal (i.e., noise-free) accuracy, and the variation in accuracy across the entire operating temperature range remaining within 2% of the mean. The proposed methodology achieves accuracy and robustness comparable to thermally-resilient Static Random-Access Memory (SRAM)-based PIM systems, while delivering up to 5.4x reduction in energy-delay product (EDP) during CNN model inferencing.