Fast Incremental Checkpoint Based on Page-Level Rewrite Interval Prediction
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
This paper introduces pagelevel rewrite interval prediction (PRWIP). By recording and analyzing the memory access history at pagelevel, we are able to predict the future memory accesses to any pages. Leveraging this information, this paper proposes a faster incremental checkpoint design by overlapping checkpoint phase withcomputing phase and thus achieves higher performance. Experimental results show that our new incremental checkpoint design can achieve averagely 22% speedup over traditional incremental checkpoint and 14% over the previous stateoftheart work.
Abstract
This paper introduces pagelevel rewrite interval prediction (PRWIP). By recording and analyzing the memory access history at pagelevel, we are able to predict the future memory accesses to any pages. Leveraging this information, this paper proposes a faster incremental checkpoint design by overlapping checkpoint phase withcomputing phase and thus achieves higher performance. Experimental results show that our new incremental checkpoint design can achieve averagely 22% speedup over traditional incremental checkpoint and 14% over the previous stateoftheart work.
참고문헌 (15)
- U. D. Kumar, "Maintenance free operating period–an alternative measure to MTBF and failure rate for specifying reliability?", Reliability Engineering & System Safety, 64(1), pp.127~131 (1999)
- Y. Liang, "Failure prediction in IBM BlueGene", L event logs, 2007, 583~588
- J. Larkin, "Guidelines for efficient parallel I", O on the Cray XT3, Proceedings of 2007Cray Users Group(CUG)Conference : New Frontiers, pp.2007[DOI]
- W. M. W. Hwu, "Checkpoint repair for high-performance out-of-order execution machines", IEEE Transactions on Computers, 100(12), pp.1496~1514 (1987)
- S. Kannan, "Optimizing checkpoints using NVM as virtual memory", Proceedings of 2013 IEEE 27th International Symposium on Parallel and Distributed Processing, pp.29~40 (2013)
- X. Dong, "Hybrid checkpointing using emerging nonvolatile memories for future exascale systems", ACM Transactions on Architecture and Code Optimization (TACO), 8(2) (2011)
- A survey of checkpoint, "restart implementations", E. Roman, 2002
- A. Jaleel, "High performance cache replacement using re-reference interval prediction(RRIP)", ACM SIGARCH Computer Architecture News, 38(3), pp.60~71 (2010)
- A. Jain, "Back to the future : leveraging Belady's algorithm for improved cache replacement", Proceedings of 2016 ACM, 2016, 78~89
- B. D. Payne, "Lares : an architecture for secure active monitoring using virtualization", Proceedings of 2008 IEEE Symposium on Security and Privacy, pp.233~247 (2008)
- J. S. Wang, "A hybrid algorithm based on gravitational search and particle swarm optimization algorithm to solve function optimization problems", Engineering Letters, 25(1), pp.22~29 (2017)
- D. Zhu, "An improved O(Rlog log n+n)time algorithm for computing the longest common subsequence", IAENG International Journal of Computer Science, 44(2), pp.166~171 (2017)
- Y. S. Chen, "Image analysis on a scanned journal page", IAENG International Journal of Computer Science, 44(1), pp.29~40 (2017)
- D. Li, "Distributed Computing and Networking", pp.263~273 (2008), Springer
- X. Dong, "Hybrid checkpointing using emerging nonvolatile memories for future exascale systems", ACM Transactions on Architecture and Code Optimization(TACO), 8(2), pp.1~29 (2011)