# CaMDN: Enhancing Cache Efficiency for Multi-tenant DNNs on Integrated NPUs

arXiv: https://arxiv.org/abs/2505.06625 · HTML: https://mlsanity.com/paper/2505.06625/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 39 references that are in the map.
- First posted on arXiv 10 May 2025.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Gemmini: Enabling Systematic Deep-Learning Architecture Evaluation via Full-Stack Integration](https://mlsanity.com/paper/1911.09925/) (2019)
- [PREMA: A Predictive Multi-task Scheduling Algorithm For Preemptible Neural Processing Units](https://mlsanity.com/paper/1909.04548/) (2019)
- [CoSA: Scheduling by Constrained Optimization for Spatial Accelerators](https://mlsanity.com/paper/2105.01898/) (2021)
- [MAGMA: An Optimization Framework for Mapping Multiple DNNs on Multiple Accelerator Cores](https://mlsanity.com/paper/2104.13997/) (2021)
- [VELTAIR: Towards High-Performance Multi-tenant Deep Learning Services via Adaptive Compilation and Scheduling](https://mlsanity.com/paper/2201.06212/) (2022)
- [OmniBoost: Boosting Throughput of Heterogeneous Embedded Devices under Multi-DNN Workload](https://mlsanity.com/paper/2307.03290/) (2023)
- [DREAM: A Dynamic Scheduler for Dynamic Real-time Multi-model ML Workloads](https://mlsanity.com/paper/2212.03414/) (2022)
- [MoCA: Memory-Centric, Adaptive Execution for Multi-Tenant Deep Neural Networks](https://mlsanity.com/paper/2305.05843/) (2023)
- [Deep Reinforcement Learning based Online Scheduling Policy for Deep Neural Network Multi-Tenant Multi-Accelerator Systems](https://mlsanity.com/paper/2404.08950/) (2024)
- [Cohmeleon: Learning-Based Orchestration of Accelerator Coherence in Heterogeneous SoCs](https://mlsanity.com/paper/2109.06382/) (2021)

## Abstract (arXiv)

With the rapid development of DNN applications, multi-tenant execution, where multiple DNNs are co-located on a single SoC, is becoming a prevailing trend. Although many methods are proposed in prior works to improve multi-tenant performance, the impact of shared cache is not well studied. This paper proposes CaMDN, an architecture-scheduling co-design to enhance cache efficiency for multi-tenant DNNs on integrated NPUs. Specifically, a lightweight architecture is proposed to support model-exclusive, NPU-controlled regions inside shared cache to eliminate unexpected cache contention. Moreover, a cache scheduling method is proposed to improve shared cache utilization. In particular, it includes a cache-aware mapping method for adaptability to the varying available cache capacity and a dynamic allocation algorithm to adjust the usage among co-located DNNs at runtime. Compared to prior works, CaMDN reduces the memory access by 33.4% on average and achieves a model speedup of up to 2.56× (1.88× on average).