A Novel Data Race Detection Approach based on Buddy Memory Allocator
Zhengyang Liu, Hua Zhang
Available Online November 2016.
- 10.2991/aiea-16.2016.88How to use a DOI?
- Data race, Memory model, Dynamic analysis, Computer security.
As a common problem of multi-core parallel programs, the problem of data race has been paid more and more attention in recent years. In this paper, a dynamic detection approach for data race problem detection is proposed. By introducing a new metadata storage based on the buddy memory allocator, the metadata access performance is improved significantly. A specific implementation of the approach based on LLVM compiler infrastructure is made. The experimental results show that the proposed approach can reduce the time cost of dynamic race detection and achieve 2x-5x performance on the Olden benchmark.
- © 2016, 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/).
Cite this article
TY - CONF AU - Zhengyang Liu AU - Hua Zhang PY - 2016/11 DA - 2016/11 TI - A Novel Data Race Detection Approach based on Buddy Memory Allocator BT - Proceedings of the 2016 International Conference on Artificial Intelligence and Engineering Applications PB - Atlantis Press SP - 491 EP - 495 SN - 2352-538X UR - https://doi.org/10.2991/aiea-16.2016.88 DO - 10.2991/aiea-16.2016.88 ID - Liu2016/11 ER -