快閃記憶體是一種非揮發性的記憶體，目前已廣泛的被作為許多手持裝置、消費性電子產品及資料中心的儲存媒介，其原因是由於具有重量輕薄、高效能、低功耗及防震等等，然而，由於快閃記憶體本身在複寫之前必須先做抹除的特性，這種清除的動作十分耗時，此外，快閃記憶體抹除的次數也是有上限的。
存放舊版本資料的塊會透過一個叫做垃圾回收的元件來做清除，垃圾回收元件透過轉移舊空間當中的有效資料到其他空閒塊，最後抹除掉原先的舊資料塊，來清出更多空閒塊。為了要有效的增進垃圾回收的效能以及延長快閃記憶體的壽命，我們提出一個新穎的資料辨識方法：動態叢集(Enhance Dynamic Clustering)

Flash memory is a non-volatile memory that has been widely used as a storage medium for various mobile devices, consumer electronics and data centers due to lightweight, high performance, low power consumption and shock resistance. However, due to its property, flash memory requires erasure before being overwritten. The erase operations is slow and the most of time-consuming. Furthermore, flash memory can only be erased for a limited number of times. The space occupied by obsolete data is reclaimed from garbage collection process. The garbage collection reclaim a flash block by migrating valid data from the flash block to be cleaned to another free flash block, and then erasing the original block. To improve garbage-collection performance and extend flash memory lifetime, we propose a new data separation method named Enhance Dynamic Clustering (EDC). With this method, data in flash memory are dynamically classified and clustered together according to their data lifetimes. Experimental results show that EDC significantly improved the garbage-collection performance compared to varied state-of-the-art algorithms. The number of erase and extra write operations performed is greatly reduced and flash memory lifetime is prolonged even under various types of host workloads.

[1] L.-P. Chang, “A hybrid approach to nand-flash-based solid-state disks,”
IEEE Trans. Comput., vol. 59, no. 10, pp. 1337–1349, Oct. 2010.
[2] M. T. Inc., “Micron 32gb, 64gb, 128gb, 256gb asynchronous/synchronous
nand features (mt29f64g08ceccb),” 2012.
[3] J.-W. Hsieh, H.-Y. Lin, and D.-L. Yang, “Multi-channel architecture-based
ftl for reliable and high-performance ssd,” IEEE Trans. Comput., vol. 63,
no. 12, pp. 3079–3091, Dec. 2014.
[4] M.-L. Chiang, P. C. H. Lee, and R.-C. Chang, “Using data clustering to improve cleaning performance for plash memory,” Softw. Pract. Exper., vol. 29,
no. 3, pp. 267–290, Mar. 1999.
[5] Z. Qin, Y. Wang, D. Liu, Z. Shao, and Y. Guan, “Mnftl: An efficient flash
translation layer for mlc nand flash memory storage systems,” in Proceedings
of the 48th Design Automation Conference, ser. DAC ’11, 2011, pp. 17–22.
[6] W.-H. Lin and L.-P. Chang, “Dual greedy: Adaptive garbage collection for
page-mapping solid-state disks,” in Proceedings of the Conference on Design,
Automation and Test in Europe, ser. DATE ’12, 2012, pp. 117–122.
[7] D.-H. Bae, J.-W. Chang, S.-M. Park, B.-S. Jeong, S.-W. Kim, and S.-j. Cho,
“An effective data clustering method based on expected update time in flash memory environment,” in Proceedings of the 29th Annual ACM Symposium
on Applied Computing, ser. SAC ’14, 2014, pp. 1492–1497.
[8] P.-C. Huang, Y.-H. Chang, K.-Y. Lam, J.-T. Wang, and C.-C. Huang,
“Garbage collection for multiversion index in flash-based embedded
databases,” ACM Trans. Des. Autom. Electron. Syst., vol. 19, no. 3, pp.
25:1–25:27, Jun. 2014.
[9] T. Hara, “A 146-mm2 8-gb multi-level nand flash memory with 70-nm cmos
technology,” IEEE Solid-State Circuits Society, vol. 41, pp. 161–169, 2006.
[10] Y. Li, “A 16gb 3b/ cell nand flash memory in 56nm with 8mb/s write rate,”
in IEEE Solid-State Circuits Conference, 2008.
[11] D. A. Patterson and J. L. Hennessy, Computer Architecture, Fifth Edition:
A Quantitative Approach, 2011.
[12] A. Kawaguchi, S. Nishioka, and H. Motoda, “A flash-memory based file system,” in Proceedings of the USENIX 1995 Technical Conference Proceedings,
ser. TCON’95, 1995, pp. 13–13.
[13] F.-H. Chen, M.-C. Yang, Y.-H. Chang, and T.-W. Kuo, “Pwl: A progressive
wear leveling to minimize data migration overheads for nand flash devices,”
in Proceedings of the 2015 Design, Automation & Test in Europe Conference
& Exhibition, ser. DATE ’15, 2015, pp. 1209–1212.
[14] “Open ssd firmware,” https://github.com/ClydeProjects/OpenSSD.
[15] L.-P. Chang and C.-D. Du, “Design and implementation of an efficient wearleveling algorithm for solid-state-disk microcontrollers,” ACM Trans. Des.
Autom. Electron. Syst., vol. 15, no. 1, pp. 6:1–6:36, Dec. 2009.
[16] U. T. Repository, “Oltp applications of two financial institutions.” [Online].
Available: http://traces.cs.umass.edu/
[17] S.-W. Lee, D.-J. Park, T.-S. Chung, D.-H. Lee, S. Park, and H.-J. Song, “A
log buffer-based flash translation layer using fully-associative sector translation,” ACM Trans. Embed. Comput. Syst., vol. 6, no. 3, Jul. 2007.
[18] A. Gupta, Y. Kim, and B. Urgaonkar, “Dftl: A flash translation layer employing demand-based selective caching of page-level address mappings,”
SIGARCH Comput. Archit. News, vol. 37, no. 1, pp. 229–240, Mar. 2009.