Hybrid Storage Class Memory-Enhanced Machine Learning Inference in Embedded Edge Devices
- 5 May 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Embedded Systems Letters
- Vol. 18 (1) , 15-18
Abstract
With the rapid proliferation of machine learning inference (MLI) tasks on Internet of Things (IoT) devices, the demand for enhanced memory system performance in these devices has become increasingly critical. This letter proposes a hybrid storage class memory (HSCM) optimization method to improve the efficiency of MLI on IoT devices. We conducted an in-depth analysis of memory access characteristics in MLI scenarios and found that the diversity and frequency of data access patterns significantly affect storage performance. Based on these characteristics, we propose a hybrid memory migration management strategy using the Markov model, which can dynamically adjust data migration between different storage levels to adapt to changing access patterns. We designed an acceleration method based on hybrid storage class memory that improves inference speed and energy efficiency by optimizing data access paths and reducing latency. Experiments demonstrate that the proposed method outperforms existing memory systems, providing a new solution for efficient MLI on embedded IoT devices.Keywords
Funding Information
- Zhejiang Provincial Natural Science Foundation of China (ZCLQN25F0202)
- General Research Projects of Zhejiang Provincial Department of Education (Y202353408)
- Fundamental Research Funds for the Provincial Universities of Zhejiang (3090JYN9924001G-017)
- Key Research and Development Program of Zhejiang Province (2024C01025)
This publication has 14 references indexed in Scilit:
- Migration-aware slot-based memory request scheduler to guarantee QoS in DRAM-PCM hybrid memoriesJournal of Systems Architecture, 2024
- Write Intensity based Foresightful Page Migration for Hybrid memories2024
- Achieving DRAM-Like PCM by Trading Off Capacity for LatencyIEEE Transactions on Computers, 2024
- A unified hybrid memory system for scalable deep learning and big data applicationsJournal of Parallel and Distributed Computing, 2023
- Architectural Trade-Off Analysis for Accelerating LSTM Network Using Radix-r OBC SchemeIEEE Transactions on Circuits and Systems I: Regular Papers, 2022
- Challenges in Design, Data Placement, Migration and Power-Performance Trade-offs in DRAM-NVM-based Hybrid Memory SystemsIETE Technical Review, 2022
- A Case Study of a DRAM-NVM Hybrid Memory Allocator for Key-Value StoresIEEE Computer Architecture Letters, 2022
- Low power and high I/O efficiency hybrid memory for Internet of Things edge devicesMicroelectronics Journal, 2022
- A Multi-hashing Index for hybrid DRAM-NVM memory systemsJournal of Systems Architecture, 2022
- NVMain 2.0: A User-Friendly Memory Simulator to Model (Non-)Volatile Memory SystemsIEEE Computer Architecture Letters, 2015