公共目录

您目前的位置: 首页» 公共目录» 学术活动

学术报告:Selective Compression Scheme for Read Performance Improvement on Flash Devices

     题:Selective Compression Scheme for Read Performance Improvement on Flash Devices

人:石亮(重庆大学)
       间:2018920日下午16:30

       点:信息工程学院小会议室

主办单位: 首都师范大学信息工程学院

讲座内容简介:

The adoption of NAND flash memory in storage systems has promoted its density and capacity increasing, which results in degraded reliability. To address the reliability issue, low-density parity-check code (LDPC) has been deployed in NAND flash memories due to its strong error correction capability. The drawback of LDPC is that read latency will be amplified to correct data with high raw bit error rate (RBER). To improve read performance, this paper proposes to apply lossless compression to reduce RBER on data pages. However, compression and decompression need time overhead. Compressing all the data pages for RBER reduction will degrade write performance. In addition, the variations of compression ratio lead to variations of RBER reduction, thus varied read latency reduction. In this work, a selective data compression scheme is proposed for read performance improvement. Both compression ratio and read frequency of data are taken into consideration. A Double Queue based selective compression scheme is proposed for the determination of data compression. Data in a flash page with high read frequency and good compressibility are prioritized for compression. Experimental results show that the proposed scheme can improve read performance by 42% on average, without impacting write performance.

讲者简介:

石亮,重庆大学副教授,博士生导师。主要研究方向为存储可靠性技术、高性能存储系统、智能嵌入式存储系统以及非易失性存储系统等。主持了包括国家自然科学基金青年基金,面上基金,华为全球开放基金以及多项中央高校重点项目,参与并完成了2项国家863科技专项和多项华为横向合作项目。在FASTATCMSSTDAC以及TCTOSTCAD等多个国际顶级会议和期刊上发表学术论文70余篇,获得ASPDAC最佳论文提名奖、NVMSA最佳论文奖。目前是多个国际会议和期刊的审稿人和评审委员会成员。