CORTEXA
← Browse
arxivcs.ARcs.AI2026-07-17

Mitigating Compiler Fusion-Induced Power Bursts in Mobile NPU Inference as the Battery Depletes

Ryoga Yuzawa, Masayoshi Tomizuka

Mobile devices increasingly rely on real-time NPU inference for camera and perception workloads. Under low-voltage conditions, however, a single inference can induce an instantaneous voltage droop in the power-delivery network, causing the power management integrated circuit to invoke dynamic voltage and frequency scaling (DVFS) and increase latency. We present a measurement study of this effect on a commercial smartphone. We show that aggressive operator fusion in a mobile NPU compiler can create monolithic superlayers whose concentrated execution produces large peak-current bursts. These bursts shift the DVFS-onset voltage upward and reduce the low-voltage operating margin. We further evaluate a practical black-box mitigation: a measurement-guided, pre-compilation graph rewrite that inserts barriers at selected peak-to-average power ratio hot spots to prevent harmful superlayer merging in the vendor NPU compiler. On Snapdragon 8 Gen 3 with MobileNetV4 at 768 x 768 resolution on ImageNet-1k, this method reduces peak current from 3.12 A to 1.94 A with 3.76% latency overhead, preserves stable latency deeper into the low-voltage regime, and shifts the inferred DVFS margin by approximately 173 mV.

View free PDFSource page

Related papers

arxivcs.ARcs.AI2026-07-06

Is Your NPU Ready for LLMs? Dissecting the Hidden Efficiency Bottlenecks in Mobile LLM Inference

Guanyu Cai, Ruiming Tian, Lang Yang, Zhouhong Ren, Jinliang Yuan, Lingkun Li, et al.

Deploying Large Language Models (LLMs) on mobile devices enhances privacy and reduces latency, but is severely bottlenecked by hardware inefficiency. We present the first comprehensive, cross-layer measurement study of mobile LLM inference, uniquely spanning five mainstream frame…

View free PDFSource page
arxivcs.LGcs.AIcs.ARcs.PF2026-07-10Cited by 1

On-Device Adaptive Battery Power Prediction for Electric Vehicles

Avik Bhatnagar, Anton Paule, Tobias Schuermann, Sebastian Reiter, Oliver Bringmann

Adaptive power management in Electric Vehicles (EVs) requires accurate power prediction. Although deep learning models have emerged as highly effective for time-series forecasting in this domain, their performance is prone to degradation when exposed to data with distributions di…

View free PDFSource page
arxivcs.IRcs.AIcs.ARcs.LG2026-07-11

Adaptive Model Compression (AMC): Saliency-Driven Resource Allocation for Ultra-Low-Power Transformer Inference

Jiayin Hu, Kai Yuan, Vanessa Hu, Xuetao Yin, Jianhua Li, Sean Suchter

Deploying large-scale transformer models on resource-constrained edge devices remains a challenge due to the high energy and memory overhead inherent in static inference, which processes simple and complex tokens with uniform intensity. To address this, we propose Adaptive Model…

View free PDFSource page
arxivcs.CVcs.AIcs.ARcs.DCcs.LG2026-07-01

Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers

Aravind Pradeep, Samira Nazari, Mahdi Taheri, Christian Herglotz

Vision Transformers achieve strong image classification accuracy but process all image regions with nearly the same computation, even when many regions are redundant or uninformative. Recent adaptive inference methods reduce this cost by selectively compressing tokens or terminat…

View free PDFSource page
arxivcs.ARcs.AIcs.DC2026-07-19

ThAME: 3D Memory-Enabled Heterogeneous Accelerator for LLM Mixture of Experts

Pratyush Dhingra, Pramit Kumar Pal, Janardhan Rao Doppa, Partha Pratim Pande

Mixture of Experts (MoE) architectures have emerged as a dominant paradigm for scaling Large Language Models (LLMs). However, MoE inference on conventional hardware is constrained by three fundamental bottlenecks. These encompass the massive memory bandwidth required to fetch non…

View free PDFSource page
arxiveess.SYcs.AIcs.AR2026-06-29

Model Predictive Current Control with Harmonic Correction for Single-Phase AC-DC EV Charging

Changhong Li, Bharathkumar Hegde, Biswajit Basu, Shreejith Shanker

The increasing integration of Electric Vehicles (EVs) has imposed a growing harmonic challenge on the power grid. For AC/DC Power Factor Correction (PFC) in single-phase On-Board Chargers (OBCs), Model Predictive Current Control (MPCC) improves the current quality by predicting a…

View free PDFSource page