Abstract
This research proposes a phase-change memory (PCM) based main memory system with an effective combination of a superblock-based adaptive buffering structure and its associated set divisible last-level cache (LLC). To achieve high performance similar to that of dynamic random-access memory (DRAM) based main memory, the superblock-based adaptive buffer (SABU) is comprised of dual DRAM buffers, i.e., an aggressive superblock-based pre-fetching buffer (SBPB) and an adaptive sub-block reusing buffer (SBRB), and a set divisible LLC based on a cache space optimization scheme. According to our experiment, the longer PCM access latency can typically be hidden using our proposed SABU, which can significantly reduce the number of writes over the PCM main memory by 26.44%. The SABU approach can reduce PCM access latency up to 0.43 times, compared with conventional DRAM main memory. Meanwhile, the average memory energy consumption can be reduced by 19.7%.
Similar content being viewed by others
References
Kim S, Chandra D, Solihin Y. Fair cache sharing and partitioning in a chip multiprocessor architecture. In Proc. the 13th International Conference on Parallel Architectures and Compilation Techniques, September 2004, pp.111-122.
Choi I S, Jang S I, Oh C H, Weems C C, Kim S D. A dynamic adaptive converter and management for PRAM-based main memory. Microprocessors and Microsystems, 2013, 37(6/7): 554–561.
Jang S I, Yoon S K, Park K, Park G H, Kim S D. Data classification management with its interfacing structure for hybrid SLC/MLC PRAM main memory. The Computer Journal, 2014, DOI 10.1093/comjnl/bxu133.
Dhiman G, Ayoub R, Rosing T. PDRAM: A hybrid PRAM and DRAM main memory system. In Proc. the 46th ACM/IEEE Design Automation Conference, July 2009, pp.664-669.
Yoon S K, Bian M Y, Kim S D. An integrated memory-disk system with buffering adapter and non-volatile memory. Design Automation for Embedded Systems, 2014, 17(3/4): 609–626.
Qureshi M K, Srinivasan V, Rivers J A. Scalable high performance main memory system using phase-change memory technology. ACM SIGARCH Computer Architecture News, 2009, 37(3): 24–33.
Jung K S, Park J W, Weems C C, Kim S D. A superblock based memory adapter using decoupled dual buffers for hiding the access latency of nonvolatile memory. In Proc. the World Congress on Engineering and Computer Science, October 2011, pp.802-807.
Lee B C, Ipek E, Mutlu O, Burger D. Architecting phase change memory as a scalable dram alternative. ACM SIGARCH Computer Architecture News, 2009, 37(3): 2–13.
Joo Y, Park S. A hybrid PRAM and STT-RAM cache architecture for extending the lifetime of PRAM caches. IEEE Computer Architecture Letters, 2013, 12(2): 55–58.
Wang Z, Shan S, Cao T, Gu J, Xu Y, Mu S, Xie Y, Jiménez D A. WADE: Write-back-aware dynamic cache management for NVM-based main memory system. ACM Transactions on Architecture and Code Optimization, 2013, 10(4): Article No. 51.
Fedorov V V, Qiu S, Narasimha Reddy A L, Gratz P V. ARI: Adaptive LLC-memory traffic management. ACM Transactions on Architecture and Code Optimization, 2013, 10(4): Article No. 46.
Saito S, Oikawa S. Exploration of non-volatile memory management in the OS kernel. In Proc. the 3rd International Conference on Networking and Computing, December 2012, pp.302-306.
Kim J K, Lee H G, Choi S, Bahng K I. A PRAM and NAND flash hybrid architecture for high-performance embedded storage subsystems. In Proc. the 8th ACM International Conference on Embedded Software, October 2008, pp.31-40.
Byna S, Chen Y, Sun X H. A taxonomy of data pre-fetching mechanisms. In Proc. International Symposium on Parallel Architectures, Algorithms, and Networks, May 2008, pp.19-24.
Nesbit K, Smith J E. Data cache pre-fetching using a global history buffer. IEEE Micro, 2005, 25(1): 90–97.
Henning J L. SPEC CPU2006 benchmark descriptions. ACM SIGARCH Computer Architecture News, 2006, 34(4): 1–17.
Henning J L. SPEC CPU2006 memory footprint. ACM SIGARCH Computer Architecture News, 2007, 35(1): 84–89.
Woo S C, Ohara M, Torrie E, Singh J P, Gupta A. The SPLASH-2 programs: Characterization and methodological considerations. ACM SIGARCH Computer Architecture News, 1995, 23(2): 24–36.
Bienia C, Kumar S, Li K. PARSEC vs. SPLASH-2: A quantitative comparison of two multithreaded benchmark suites on chip-multiprocessors. In Proc. IEEE International Symposium on Workload Characterization, September 2008, pp.47-56.
Binkert N, Beckmann B, Black G et al. The gem5 simula-tor. ACM SIGARCH Computer Architecture News, 2011, 39(2): 1–7.
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was supported by an Industry-Academy Joint Research program between Samsung Electronics and Yonsei University.
Rights and permissions
About this article
Cite this article
Bian, MY., Yoon, SK., Kim, JG. et al. A Unified Buffering Management with Set Divisible Cache for PCM Main Memory. J. Comput. Sci. Technol. 31, 137–146 (2016). https://doi.org/10.1007/s11390-016-1617-7
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11390-016-1617-7