Open Access iconOpen Access

ARTICLE

crossmark

Characterization of Memory Access in Deep Learning and Its Implications in Memory Management

Jeongha Lee1, Hyokyung Bahn2,*

1 Institute of Artificial Intelligence and Software, Ewha University, Seoul, 03760, Korea
2 Department of Computer Science and Engineering, Ewha University, Seoul, 03760, Korea

* Corresponding Author: Hyokyung Bahn. Email: email

Computers, Materials & Continua 2023, 76(1), 607-629. https://doi.org/10.32604/cmc.2023.039236

Abstract

Due to the recent trend of software intelligence in the Fourth Industrial Revolution, deep learning has become a mainstream workload for modern computer systems. Since the data size of deep learning increasingly grows, managing the limited memory capacity efficiently for deep learning workloads becomes important. In this paper, we analyze memory accesses in deep learning workloads and find out some unique characteristics differentiated from traditional workloads. First, when comparing instruction and data accesses, data access accounts for 96%–99% of total memory accesses in deep learning workloads, which is quite different from traditional workloads. Second, when comparing read and write accesses, write access dominates, accounting for 64%–80% of total memory accesses. Third, although write access makes up the majority of memory accesses, it shows a low access bias of 0.3 in the Zipf parameter. Fourth, in predicting re-access, recency is important in read access, but frequency provides more accurate information in write access. Based on these observations, we introduce a Non-Volatile Random Access Memory (NVRAM)-accelerated memory architecture for deep learning workloads, and present a new memory management policy for this architecture. By considering the memory access characteristics of deep learning workloads, the proposed policy improves memory performance by 64.3% on average compared to the CLOCK policy.

Keywords


Cite This Article

APA Style
Lee, J., Bahn, H. (2023). Characterization of memory access in deep learning and its implications in memory management. Computers, Materials & Continua, 76(1), 607-629. https://doi.org/10.32604/cmc.2023.039236
Vancouver Style
Lee J, Bahn H. Characterization of memory access in deep learning and its implications in memory management. Comput Mater Contin. 2023;76(1):607-629 https://doi.org/10.32604/cmc.2023.039236
IEEE Style
J. Lee and H. Bahn, "Characterization of Memory Access in Deep Learning and Its Implications in Memory Management," Comput. Mater. Contin., vol. 76, no. 1, pp. 607-629. 2023. https://doi.org/10.32604/cmc.2023.039236



cc This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 705

    View

  • 329

    Download

  • 1

    Like

Share Link