GPU Temperature Simulation-Based Testing for In-Vehicle Deep Learning Frameworks

• URL: http://arxiv.org/abs/2509.15815v2
• Date: Fri, 26 Sep 2025 05:30:39 GMT
• Title: GPU Temperature Simulation-Based Testing for In-Vehicle Deep Learning Frameworks
• Authors: Yinglong Zou, Juan Zhai, Chunrong Fang, Zhenyu Chen,
• Abstract summary: We propose ThermalGuardian, the first automotive deep learning framework testing method under temperature-varying environments.<n>Specifically, ThermalGuardian generates test input models using model mutation rules targeting temperature-sensitive operators, simulates GPU temperature fluctuations based on Newton's law of cooling, and controls GPU frequency based on real-time GPU temperature.
• Score: 19.182583346025634
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning models play a vital role in autonomous driving systems, supporting critical functions such as environmental perception. To accelerate model inference, these deep learning models' deployment relies on automotive deep learning frameworks, for example, PaddleInference in Apollo and TensorRT in AutoWare. However, unlike deploying deep learning models on the cloud, vehicular environments experience extreme ambient temperatures varying from -40{\deg}C to 50{\deg}C, significantly impacting GPU temperature. Additionally, heats generated when computing further lead to the GPU temperature increase. These temperature fluctuations lead to dynamic GPU frequency adjustments through mechanisms such as DVFS. However, automotive deep learning frameworks are designed without considering the impact of temperature-induced frequency variations. When deployed on temperature-varying GPUs, these frameworks suffer critical quality issues: compute-intensive operators face delays or errors, high/mixed-precision operators suffer from precision errors, and time-series operators suffer from synchronization issues. The above quality issues cannot be detected by existing deep learning framework testing methods because they ignore temperature's effect on the deep learning framework quality. To bridge this gap, we propose ThermalGuardian, the first automotive deep learning framework testing method under temperature-varying environments. Specifically, ThermalGuardian generates test input models using model mutation rules targeting temperature-sensitive operators, simulates GPU temperature fluctuations based on Newton's law of cooling, and controls GPU frequency based on real-time GPU temperature.

Related papers

• Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL [30.357975264905978]
  We propose a hierarchical reinforcement learning framework that learns to control sampling temperature during generation.<n>At each decoding step, the model selects a temperature based on its hidden state and samples the next token from the resulting distribution.<n>Temperature and token policies are jointly optimized from downstream rewards using a coordinate ascent scheme.
  arXiv  Detail & Related papers  (2026-02-13T15:42:59Z)
• Temperature as a Meta-Policy: Adaptive Temperature in LLM Reinforcement Learning [47.83947232413507]
  Temperature controls the trade-off between exploration and exploitation in large language models (LLMs)<n>High temperatures encourage diverse but noisy outputs, while low temperatures produce focused outputs but may cause premature convergence.<n>We propose Temperature Adaptive Meta Policy Optimization (TAMPO), a new framework that recasts temperature control as a learnable meta-policy.
  arXiv  Detail & Related papers  (2026-02-12T09:59:58Z)
• Exploring the Impact of Temperature Scaling in Softmax for Classification and Adversarial Robustness [8.934328206473456]
  This study delves into the often-overlooked parameter within the softmax function, known as "temperature"<n>Our empirical studies, adopting convolutional neural networks and transformers, reveal that moderate temperatures generally introduce better overall performance.<n>For the first time, we discover a surprising benefit of elevated temperatures: enhanced model robustness against common corruption, natural perturbation, and non-targeted adversarial attacks like Projected Gradient Descent.
  arXiv  Detail & Related papers  (2025-02-28T00:07:45Z)
• Adaptive Decoding via Latent Preference Optimization [55.70602730588745]
  We introduce Adaptive Decoding, a layer added to the model to select the sampling temperature dynamically at inference time. Our method outperforms all fixed decoding temperatures across a range of tasks that require different temperatures.
  arXiv  Detail & Related papers  (2024-11-14T18:31:39Z)
• Temperature-Centric Investigation of Speculative Decoding with Knowledge Distillation [76.5894260737116]
  This paper delves into the effects of decoding temperatures on speculative decoding's efficacy. We first highlight the challenge of decoding at higher temperatures, and demonstrate KD in a consistent temperature setting could be a remedy. Building upon these findings, we take an initial step to further the speedup for speculative decoding, particularly in a high-temperature generation setting.
  arXiv  Detail & Related papers  (2024-10-14T04:17:45Z)
• Machine Learning Framework for High-Resolution Air Temperature Downscaling Using LiDAR-Derived Urban Morphological Features [0.0]
  This study presents a data-driven framework for downscaling air temperature using datasets generated by UrbClim. To extract urban morphological features, first a three-dimensional building model was created using LiDAR data and deep learning models. The framework successfully estimated air temperatures at higher resolutions, enabling the identification of local air temperature patterns at street level.
  arXiv  Detail & Related papers  (2024-08-31T12:59:21Z)
• The impact of internal variability on benchmarking deep learning climate emulators [2.3342885570554652]
  Full-complexity Earth system models (ESMs) are computationally very expensive, limiting their use in exploring the climate outcomes of multiple emission pathways.<n>More efficient emulators that approximate ESMs can directly map emissions onto climate outcomes, and benchmarks are being used to evaluate their accuracy on standardized tasks and datasets.<n>We investigate a popular benchmark in datadriven climate emulation, ClimateBench, on which deep learning-based emulators are currently achieving the best performance.
  arXiv  Detail & Related papers  (2024-08-09T18:17:17Z)
• To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO [68.69840111477367]
  We present a principled framework for learning a small yet generalizable temperature prediction network (TempNet) to improve LFMs. Our experiments on LLMs and CLIP models demonstrate that TempNet greatly improves the performance of existing solutions or models.
  arXiv  Detail & Related papers  (2024-04-06T09:55:03Z)
• Real-Time 2D Temperature Field Prediction in Metal Additive Manufacturing Using Physics-Informed Neural Networks [1.9116784879310036]
  Accurately predicting the temperature field in metal additive manufacturing processes is critical to preventing overheating, adjusting process parameters, and ensuring process stability. We introduce a physics-informed neural network framework specifically designed for temperature field prediction in metal AM. We validate the proposed framework in two scenarios: full-field temperature prediction for a thin wall and 2D temperature field prediction for cylinder and cubic parts, demonstrating errors below 3% and 1%, respectively.
  arXiv  Detail & Related papers  (2024-01-04T18:42:28Z)
• Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training [58.20089993899729]
  This paper proposes TempBalance, a straightforward yet effective layerwise learning rate method. We show that TempBalance significantly outperforms ordinary SGD and carefully-tuned spectral norm regularization. We also show that TempBalance outperforms a number of state-of-the-art metrics and schedulers.
  arXiv  Detail & Related papers  (2023-12-01T05:38:17Z)
• Physics-constrained deep learning postprocessing of temperature and humidity [0.0]
  We propose to achieve physical consistency in deep learning-based postprocessing models. We find that constraining a neural network to enforce thermodynamic state equations yields physically-consistent predictions.
  arXiv  Detail & Related papers  (2022-12-07T09:31:25Z)
• Object Detection in Thermal Spectrum for Advanced Driver-Assistance Systems (ADAS) [0.5156484100374058]
  Object detection in thermal infrared spectrum provides more reliable data source in low-lighting conditions and different weather conditions. This paper is about exploring and adapting state-of-the-art object and vision framework on thermal vision with seven distinct classes for advanced driver-assistance systems (ADAS) The trained network variants on public datasets are validated on test data with three different test approaches. The efficacy of trained networks is tested on locally gathered novel test-data captured with an uncooled LWIR prototype thermal camera.
  arXiv  Detail & Related papers  (2021-09-20T21:38:55Z)
• Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of Adverse Weather Conditions for 3D Object Detection [60.89616629421904]
  Lidar-based object detectors are critical parts of the 3D perception pipeline in autonomous navigation systems such as self-driving cars. They are sensitive to adverse weather conditions such as rain, snow and fog due to reduced signal-to-noise ratio (SNR) and signal-to-background ratio (SBR)
  arXiv  Detail & Related papers  (2021-07-14T21:10:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.