隨著消費電子產品和行動裝置的蓬勃發展，嵌入式系統中的能源效率設計成為一個反復出現的議題。相變化記憶體(PCM)被認為極具取代DRAM做為主記憶體的潛力。因其有機會達成顯著的電力節省，可高達60個百分點。然而，在考慮使用PCM做為系統的主記憶時，其可擦寫次數(耐用年限)成為一個關鍵的問題，損耗平衡設計是一種常見的用以解決此問題的方法。現有的損耗均衡策略已有注重運行效率和降低開銷，但其仍以將PCM壽命延至最長為主要目的，為此，我們提出了一種關注產品保固年限之實體記憶體頁面管理機制，其專注於保證PCM頁面在保固年限內不發生損壞，從而可最大地減少管理和運行上的開銷，實驗結果顯示，這個基於冷卻過熱頁面的機制可將管理的開銷減至其他先進設計的三分之一，同時具有相同水平的性能。

The thriving growth in mobile consumer electronics keeps the energy efficiency in the embedded system design a recurring theme. PCM main memory has shown its potential in replacing DRAM due to the huge amount of energy reduction, e.g. 65%. When considering the usage of PCM main memory, its write endurance becomes a critical issue, and wear leveling design is a common approach to resolve this issue. Even though the wear leveling design should emphasize on the operation efficiency and overhead reduction, existing wear leveling strategies designed for PCM main memory are usually enforced to prolong the lifetime of PCM in best effort. We propose a warranty-aware page management design to mitigate the operation overhead required for managing the endurance issue in PCM. A cooling-based wear leveling is proposed to guarantee that PCM pages will not live less than warranty period. The experiment results showed the cooling-based design reduced the overhead to one third of that of the state-of-the-art designs while having the same level of performance.

Introduction 6
1.1 Phase changing memory and embedded system . . 6
1.2 Related works . . . . . . . . . . . . . . . . . . . . 7
1.3 Brief summary and contributions . . . . . . . . . . 9
1.4 Paper organization . . . . . . . . . . . . . . . . . 10
2 Background and Research Motivation 11
2.1 Background . . . . . . . . . . . . . . . . . . . . . 11
2.1.1 PCM introduction . . . . . . . . . . . . . 11
2.1.2 Considered system:L4 Microkernel . . . . 12
2.2 Research motivation . . . . . . . . . . . . . . . . . 14
3 Warranty-Aware Page Management 16
1
3.1 Overview . . . . . . . . . . . . . . . . . . . . . . 16
3.2 Page State Evaluation and Classification . . . . . . 17
3.3 Cooling-Based Wear Leveling . . . . . . . . . . . 20
3.4 An Auxiliary Dynamic Wear Leveling — PotentialExploiting Wear Leveling . . . . . . . . . . . . . . 23
4 Performance Evaluation 26
4.1 Experimental Setup . . . . . . . . . . . . . . . . . 26
4.1.1 performance metrics . . . . . . . . . . . . 26
4.1.2 compared methodology . . . . . . . . . . 27
4.1.3 testing platform and trace collection . . . . 29
4.2 Experimental Results . . . . . . . . . . . . . . . . 30
4.2.1 performance . . . . . . . . . . . . . . . . 30
4.2.2 Overhead analysis . . . . . . . . . . . . . 32
5 Implementation Remark 38
5.1 Free space management improvement . . . . . . . 38
5.2 Heuristic parameters . . . . . . . . . . . . . . . . 39
2
6 Conclusion 43
Bibliography 45

[1] The Fiasco Microkernel. http://os.inf.tu-dresden.de/fiasco/.
[2] M. Accetta, R. Baron, W. Bolosky, D. Golub, R. Rashid,
A. Tevanian, and M. Young. Mach: A new kernel foundation
for unix development. 1986.
[3] M. Z. Alexandre P. Ferreira and S. Bock. Increasing PCM
Main Memory Lifetime. 2010.
[4] F. Bellard. Qemu, a fast and portable dynamic translator. In
USENIX Annual Technical Conference, 2005.
[5] C.-H. Chen, P.-C. Hsiu, T.-W. Kuo, C.-L. Yang, and W. C.-Y.
Michael. Age-based pcm wear leveling with nearly zero search
cost. In Proc. of ACM DAC, 2012.
[6] . L. M. Eilert S and G. Crisenza. Phase change memory: A
new memory enables new memory usage models. In Proc. of
IMW, May 2009.
[7] A. Ferreira, M. Zhou, S. Bock, B. Childers, R. Melhem, and
D. Mosse. Increasing pcm main memory lifetime. In Proc. of
IEEE DATE, 2010.
[8] S. K. J. L. J. P. R. B. R. H.-S. Philip Wong, Simone Raoux and
i. K. E. G. Mehdi Ashegh. Phase change memory. Proc. of the
IEEE, 2010.
[9] H. H ¨ artig, M. Hohmuth, J. Liedtke, J. Wolter, and
S. Sch ¨ onberg. The performance of microkernel-based systems.
In Proc. of ACM SOSP, 1997.
[10] J. L. Henning. Spec cpu2006 benchmark descriptions. 2006.
[11] T. W.-C. H. Y. Q. M. Hu Jingtong, Xue Chun Jason and S. E.
Hsing-Mean. Reducing write activities on non-volatile memories in embedded cmps via data migration and recomputation.
In Proc. of ACM DAC, 2010.
[12] L. J. On micro-kernel construction. In Proc. of ACM SOSP,
1995.
[13] D. Y. Z. Y. C.-B. R. Jiang, Lei and J. Yang. Lls: Cooperative integration of wear-leveling and salvaging for pcm main
memory. In Proc. of IEEE DSN, 2011.
[14] J. K. Moinuddin K. Qureshi and M. Franceschini. Enhancing
lifetime and security of pcm-based main memory with startgap wear leveling. MICRO, 2009.
[15] V. S. Moinuddin K. Qureshi and J. A. Rivers. Scalable high
performance main memory system using phase-change memory technology. 2009.
[16] B. Z. Ping Zhou and Y. Z. Jun Yang. A durable and energy efficient main memory using phase change memory technology.
2009.
[17] QNX microkernel. http://www.qnx.com/.
[18] S. V. Qureshi, Moinuddin K and R. J. A. Scalable high performance main memory system using phase-change memory
technology. ACM SIGARCH Computer Architecture News.
[19] C. Sangyeun and L. Hyunjin. Flip-n-write: a simple deterministic technique to improve pram write performance, energy and
endurance. In IEEE MICRO, 2009.
[20] S. K. Schechter Stuart, Loh Gabriel H and B. Doug. Use ecp,
not ecc, for hard failures in resistive memories. In Proc. of
ACM SIGARCH Computer Architecture, 2010.
[21] W. D. H. Seong Nak Hee and L. H.-H. S. Security refresh:
Prevent malicious wear-out and increase durability for phasechange memory with dynamically randomized address mapping. In Proc. of ACM SIGARCH Computer Architecture,
2010.
[22] C. J.-R. P. J. N. P. Yoon Doe Hyun, Muralimanohar Naveen
and M. Erez. Free-p: Protecting non-volatile memory against
both hard and soft errors. In Proc. of IEEE HPCA, 2011.