xianzhang chen
associate professor
email: xzchen@cqu.edu.cn
xianzhang chen received ph.d. degree from the college of computer science at chongqing university, china in 2017. he obtained his bs and ms degrees in computer science and engineering from southeast university, nanjing, china. he was a research fellow at the national university of singapore, singapore. he is currently an associate professor with chongqing university. his research interests include operating systems, advanced storage systems, and reconfigurable accelerators. dr. chen was a recipient of best paper awards in nvmsa'2015 and iccd'17, ``the editor's pick of 2016" of ieee tc, and the chongqing best ph.d. dissertation award in 2018. he served asp-dac srf’19/20/21, ieee rtcsa’19, ieee isorc’19 and acm sac-cps’19/20/21 as a tpc member.
selected publication (*corresponding author)
journal papers
[1] xianzhang chen*, edwin h.-m. sha, xinxin wang, chaoshu yang, weiwen jiang, qingfeng zhuge. contour: a process variation aware wear-leveling mechanism for inodes of persistent memory file systems. ieee transactions on computers (ieee tc), 2020.
[2] renping liu, xianzhang chen*, duo liu, yingjian ling, weilue wang, yujuan tan, chunhua xiao, chaoshu yang, runyu zhang, liang liang. separable binary convolutional neural network on embedded systems. ieee transactions on computers (ieee tc), 2020, 69(10): 1474-1486.
[3] chaoshu yang, qingfeng zhuge, xianzhang chen*, edwin h.-m. sha, duo liu, and runyu zhang. optimizing synchronization mechanism for block-based file systems using persistent memory. future generation computer systems (fgcs), 2020, 111:288-299.
[4] xianzhang chen, edwin h.-m. sha, qingfeng zhuge*, ting wu, weiwen jiang, and xiaoping zeng. umfs: an efficient user-space file system for non-volatile memory. journal of systems architecture (jsa), 2018, 89:18-29.
[5] xianzhang chen, edwin h.-m. sha*, weiwen jiang, chaoshu yang, ting wu, and qingfeng zhuge. refinery swap: an efficient swap mechanism for hybrid dram-nvm systems. future generation computer systems (fgcs), 2017, 77:52-64.
[6] xianzhang chen, *, , , , and . . ieee transactions on very large scale integration (vlsi) systems (ieee tvlsi), 2016, 24(10): 3094- 3104.
[7] xianzhang chen, edwin h.-m. sha*, qingfeng zhuge, weiwen jiang, junxi chen, and jun chen. a unified framework for designing high performance in-memory and hybrid memory file systems. journal of systems architecture (jsa), 2016, 68:51-64.
[8] edwin h.-m. sha*, xianzhang chen, qingfeng zhuge, liang shi, and weiwen jiang. a. ieee transactions on computers (ieee tc), 2016, 65(10): 2959-2972.
[9] duo liu*, chaoneng xiang, shiming li, jinting ren, renping liu, liang liang, and yong guan, and xianzhang chen*. hinextapp: a context-aware and adaptive framework for app prediction in mobile systems. sustainable computing, 2019, 22: 219-229.
[10] duo liu*, chaoshu yang, shiming li, xianzhang chen*, jinting ren, renping liu, moming duan, yujuan tan, liang liang. fitcnn: a cloud-assisted and low-cost framework for updating cnns on iot devices. future generation computer systems (fgcs), 2019, 91:277-289.
[11] weiwen jiang, edwin h.-m. sha, qingfeng zhuge*, lei yang, hailiang dong, xianzhang chen. on the design of minimal-cost pipeline systems satisfying hard/soft real-time constraints. ieee transactions on emerging topics in computing.
[12] lin wu, qingfeng zhuge*, edwin h.-m. sha, xianzhang chen, linfeng cheng. dwarm: a wear-aware memory management scheme for in-memory file systems. future generation computer systems. 2018, 88:1-15.
[13] edwin h.-m. sha, weiwen jiang, hailiang dong, zhulin ma, runyu zhang, xianzhang chen, and qingfeng zhuge*. towards the design of efficient and consistent index structure with minimal write activities for non-volatile memory. ieee transactions on computers (ieee tc), vol. 67, no. 3, pp. 432-448, 2018.
[14] weiwen jiang, edwin h.-m. sha, xianzhang chen, lin wu, qingfeng zhuge*, synthesizing distributed pipelining systems with timing constraints via optimal functional unit assignment and communication selection. journal of computational science (jocs). 2018, 26: 332-343.
[15] weiwen jiang*, edwin h.-m. sha, xianzhang chen, lei yang, lei zhou, and qingfeng zhuge. optimal functional-unit assignment for heterogeneous systems under timing constraint. ieee transactions on parallel and distributed systems (tpds), vol. 28, no. 9, pp. 2567-2580, 2017.
[16] weiwen jiang, edwin hsing-mean sha, qingfeng zhuge*, lei yang, xianzhang chen, jingtong hu. heterogeneous fpga-based cost-optimal design for timing-constrained cnns. ieee transactions on cad of integrated circuits and systems (tcad) 37(11): 2542-2554, 2018.
[17] lin wu, qingfeng zhuge*, edwin h.-m. sha, xianzhang chen, and linfeng cheng, boss: an efficient data distribution strategy for object storage systems with hybrid devices. ieee access, 2017, 5:23979-23993.
[18] weiwen jiang, qingfeng zhuge*, xianzhang chen, lei yang, juan yi, and edwin h.-m. sha. properties of self-timed ring architectures for deadlock-free and consistent configuration reaching maximum throughput. journal of signal processing systems (jsps), 2016, 84(1): 123-137.
[19] penglin dai, qingfeng zhuge*, xianzhang chen, weiwen jiang, and edwin h.-m. sha. effective file data-block placement for different types of page cache on hybrid main memory architectures. design automation for embedded systems, (daes) 2013, 17: 485-506.
conference papers
[20] jinting ren, xianzhang chen*, duo liu*, moming duan, renping liu, chengliang wang. forseti: an efficient basic-block-level sensitivity analysis framework towards multi-bit faults. design, automation and test in europe (date), virtual conference, feb.2021.
[21] yu liang, jinheng li, xianzhang chen*, rachata ausavarungnirun, riwei pan, tei-wei kuo, chun jason xue. differentiating cache files for fine-grain management to improve mobile performance and lifetime. the 12th usenix workshop on hot topics in storage and file systems (hotstorage), boston, usa, july. 2020.
[22] chaoshu yang, duo liu, runyu zhang, xianzhang chen*, shun nie, fengshun wang, qingfeng zhuge, edwin h.-m. sha. efficient multi-grained wear leveling for inodes of persistent memory file systems. the 57th annual design automation conference (dac), san francisco, usa, july.2020.
[23] renping liu, xianzhang chen*, yujuan tan, runyu zhang, liang liang, duo liu. ssdkeeper: self-adapting channel allocation to improve the performance of ssd devices. the 34th ieee international parallel & distributed processing symposium (ipdps), new orleans, usa, may 2020.
[24] jinting ren, xianzhang chen*, yujuan tan, duo liu, moming duan, liang liang, lei qiao. archivist: a machine learning assisted data placement mechanism for hybrid storage systems. the 37th ieee international conference on computer design (iccd). abu dhabi, uae, nov. 2019: 676-679.
[25] xianzhang chen*, qingfeng zhuge, qiang sun, edwin h.-m. sha, shouzhen gu, chaoshu yang, and chun jason xue. a wear-leveling-aware fine-grained allocator for non-volatile memory. the 56th annual design automation conference (dac), las vegas, usa, jun.2019.
[26] yue xu, hyung gyu lee, yujuan tan, yu wu, xianzhang chen*, liang liang, qiao lei, and duo liu*. tumbler: energy efficient task scheduling for dual-channel solar-powered sensor nodes. the 56th annual design automation conference (dac), las vegas, usa, jun.2019.
[27] chaoshu yang, duo liu, xianzhang chen*, runyu zhang, wenbin wang, moming duan, and yujuan tan. reducing write amplification for inodes of journaling file system using persistent memory. design, automation and test in europe (date), florence, italy, mar.2019.
[28] xianzhang chen*, edwin h.-m. sha, yuansong zeng, chaoshu yang, weiwen jiang, qingfeng zhuge. efficient wear leveling for inodes of file systems on persistent memories. design, automation and test in europe (date), dresden, germany, mar.2018: 1524-1527.
[29] xianzhang chen*, edwin h.-m. sha, ahmad abdullah, qingfeng zhuge, lin wu, chaoshu yang, and weiwen jiang. udorn: a design framework of persistent in-memory key-value database for nvm. ieee non-volatile memory system & applications symposium (nvmsa), hsinchu, china, aug. 2017.
[30] xianzhang chen*, edwin h.-m. sha, weiwen jiang, qingfeng zhuge, junxi chen, jiejie qin, yuansong zeng. the design of an efficient swap mechanism for hybrid dram-nvm systems. the 13th international conference on embedded software (emsoft), pittsburg, usa, oct. 2016.
[31] xianzhang chen*, edwin h.-m. sha, zhilong sun, qingfeng zhuge, weiwen jiang. the design and implementation of an efficient data consistency mechanism for in-memory file systems. ieee international conference on embedded software and systems (icess), chengdu, china, aug. 2016.
[32] xianzhang chen*, edwin h.-m. sha, qingfeng zhuge, penglin dai, and weiwen jiang. optimizing data placement for reducing shift operations on domain wall memories. the 52nd annual design automation conference (dac),san francisco, usa, jun. 2015.
[33] xianzhang chen*, xiaoping li. a dynamic resource balance algorithm for multi-tenant placement problem in saas. international conference on service sciences (icss), shenzhen, china, apr. 2013.
[34] runyu zhang, duo liu*, xianzhang chen*, xiongxiong she, chaoshu yang, yujuan tan, zhaoyan shen, zili shao. loffs: a low-overhead file system for large flash memory on embedded devices. the 57th annual design automation conference (dac), san francisco, usa, july2020.
[35] moming duan, duo liu, xianzhang chen, yujuan tan, jinting ren, lei qiao, liang liang. astraea: self-balancing federated learning for improving classification accuracy of mobile deep learning applications. the 37th ieee international conference on computer design (iccd). abu dhabi, uae, nov. 2019: 246-254.
[36] yujuan tan, baiping wan, zhichao yan, qiuwei deng, xianzhang chen, and duo liu. uimigrate: adaptive data migration for hybrid non-volatile memory systems. design, automation and test in europe (date), florence, italy, mar.2019.
[37] yuansong zeng, edwin h.-m. sha, qingfeng zhuge, xianzhang chen, lin wu, and zhulin ma. an efficient file system for hybrid in-memory nvm and block devices. ieee non-volatile memory system & applications symposium (nvmsa), hakodate, japan, aug. 2018: 43-48.
[38] edwin h.-m. sha, hailiang dong, weiwen jiang, qingfeng zhuge, xianzhang chen, and lei yang. on the design of reliable heterogeneous systems via checkpoint placement and core assignment. acm great lakes symposium on vlsi (glsvlsi), chicago, usa, may. 2018: 475-478.
[39] weiwen jiang, edwin h.-m. sha, qingfeng zhuge, lei yang, hailiang dong and xianzhang chen. on the design of minimal-cost pipeline systems satisfying hard/soft real-time constraints. the 35th ieee international conference on computer design (iccd). boston, usa, nov. 2017. (best paper award)
[40] weiwen jiang, edwin sha, qingfeng zhuge, hailiang dong, xianzhang chen, optimal functional unit assignment and voltage selection for pipelined mpsoc with guaranteed probability on time performance. the acm sigplan/sigbed conference on languages, compilers, tools and theory for embedded systems (lctes), barcelona, spain, jun. 2017.
[41] hailiang dong, edwin h.-m. sha, weiwen jiang, xianzhang chen, runyu zhang, and qingfeng zhuge. towards the design of optimal range assignment for elevator groups under fluctuant traffic loads. the 23rd ieee international conference on embedded and real-time computing systems and applications (rtcsa). hsinchu, china, aug. 2017.
[42] weiwen jiang, edwin h.-m. sha, qingfeng zhuge, xianzhang chen. optimal functional-unit assignment and buffer placement for probabilistic pipelines. the 11th ieee/acm/ifip international conference on hardware/software co-design and system synthesis (codes). pittsburg, usa, oct. 2016.
[43] edwin h.-m. sha, yutong liang, weiwen jiang, xianzhang chen, qingfeng zhuge. optimizing data placement of mapreduce on ceph-based framework under load-balancing constraint. the 22nd ieee international conference on parallel and distributed systems (icpads), wuhan, china, dec. 2016.
[44] edwin h. -m. sha, weiwen jiang, qingfeng zhuge, xianzhang chen, and lei yang. prevent deadlock and remove blocking for self-timed systems. international conference on algorithms and architectures for parallel processing (ica3pp), zhangjiajie, china, nov. 2015.
[45] edwin h.-m. sha, xianzhang chen, qingfeng zhuge, liang shi, and weiwen jiang. designing an efficient persistent in-memory file system. ieee non-volatile memory system & applications symposium (nvmsa), hong kong, china, aug, 2015. (best paper award)
[46] edwin h.-m. sha, weiwen jiang, qingfeng zhuge, lei yang, and xianzhang chen. on the design of high-performance and energy-efficient probabilistic self-timed systems. ieee international conference on high performance computing & communications (hpcc), new york, usa, aug. 2015.
[47] edwin h.-m. sha, yang jia, xianzhang chen, qingfeng zhuge, weiwen jiang, and jiejie qin. the design and implementation of an efficient user-space in-memory file system. ieee non-volatile memory system & applications symposium (nvmsa), daegu, korea, aug. 2016.
[48] weiwen jiang, edwin h.-m. sha, xianzhang chen, qingfeng zhuge, lin wu. optimal functional assignment and communication selection under timing constraint for self-timed pipelines. ieee international conference on embedded software and systems (icess), chengdu, china, aug. 2016.
[49] edwin h.-m. sha, jun chen, xianzhang chen, weiwen jiang, qingfeng zhuge. the design and implementation of a high-performance hybrid memory file system. international conference on advanced cloud and big data (cbd), chengdu, china, aug. 2016.
[50] zhixiang liu, edwin h.-m. sha, xianzhang chen, weiwen jiang, and qingfeng zhuge. performance optimization for in-memory file systems on numa machines. the 17th international conference on parallel and distributed computing, applications and technologies (pdcat), guangzhou, china, dec. 2016.
projects
[1] pi. non-volatile memory oriented performance and endurance optimizations, chongqing postdoctoral science foundation (first-class).
[2] pi. performance and endurance optimizations for non-volatile memory based storage systems, national natural science foundation of china.
[3] pi. design and optimizations for non-volatile main memory based file systems, china postdoctoral science foundation (first-class).
professional activities
member, china computer federation (ccf)
member, ccf technical committee of embedded systems
member, ccf technical committee of system software
member, acm/ieee
peer reviewers of international conferences, e.g., isvlsi、acm sac-cps、ieee rtcsa, asp-dac，etc., and international journals, e.g., ieee tc，ieee tpds、ieee tcad, acm tos, etc.
