Quantifying the Influences of Data Prefetching Using Artificial Neural Networks

DOI

10.2991/acaai-18.2018.40How to use a DOI?

Keywords

cache misses; data prefetching; artificial neural networks

Abstract

Data prefetching has been widely used in modern cache subsystems. Actually, an aggressive prefetching may bring negative yields unexpectedly, in which a new proposed prefetching strategy normally needs to be evaluated before being applied in the real design. In the last decade, prior researchers prefer to utilize the cycle-accurate simulations or trace-driven simulations to study the prefetching behaviors. However, as the increasing complexity of hardware components, the huge time-consuming simulation-based methods would never be appropriate for performance evaluations. This paper proposes a method of modeling prefetching influences on cache misses using artificial neural networks, which has an average error of 8% compared to gem5 cycle-accurate simulations, and the performance prediction process can be sped up by 30 times on average.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Kecheng Ji
AU  - Li Liu
PY  - 2018/03
DA  - 2018/03
TI  - Quantifying the Influences of Data Prefetching Using Artificial Neural Networks
BT  - Proceedings of the 2018 International Conference on Advanced Control, Automation and Artificial Intelligence (ACAAI 2018)
PB  - Atlantis Press
SP  - 170
EP  - 172
SN  - 1951-6851
UR  - https://doi.org/10.2991/acaai-18.2018.40
DO  - 10.2991/acaai-18.2018.40
ID  - Ji2018/03
ER  -