基本信息

崔慧敏  女  研究员 博导  中国科学院计算技术研究所
电子邮件: cuihm@ict.ac.cn
通信地址: 北京市海淀区科学院南路6号
邮政编码: 100190

研究领域

崔慧敏研究员关注异构环境下的编程和编译方向,具体的研究领域包括:异构编程模型,异构编译优化,数据中心编程与编译技术等。

在异构编程方面,她关注于领域专用的编程与编译优化技术,包括面向AI领域、通信领域的编译优化,旨在解决异构为程序员带来的编程困扰,并充份发挥领域专用芯片的处理潜力。在数据中心编程与编译技术方面,她关注于解决混合负载场景下的编译优化策略,旨在解决数据中心深度软件栈环境下各层次间的协同优化。

招生信息

   
招生专业
081201-计算机系统结构
招生方向
并行编程,并行编译,异构编译

教育背景

2006-09--2011-09   中国科学院计算技术研究所   博士
2001-09--2004-02   清华大学   硕士
1997-09--2001-07   清华大学   学士

工作经历

工作简历
2019-10~现在, 中科院计算所, 研究员
2012-10~2019-10,中国科学院计算技术研究所, 副研究员
2011-09~2012-10,中国科学院计算技术研究所, 助理研究员

教授课程

编译原理(研讨课)

出版信息

   
发表论文
[1] 张忠诚, Ou, Yan, 刘颖, 王晨曦, Zhou, Yongbin, Wang, Xiaoyu, Zhang, Yuyang, Ouyang, Yucheng, Wang,Ying, xue jingling, 崔慧敏, 冯晓兵. OCCAMY:Elastically Sharing an On-chip Vector Co-processor Across Multiple Cores. Architectural Support for Programming Languages and Operating Systems (ASPLOS)null. 2023, [2] Wu, Zhikun, Shang, Honghui, Wu, Yangjun, Zhang, Zhongcheng, Liu, Ying, Zhang, Yuyang, Ouyang, Yucheng, Cui, Huimin, Feng, Xiaobing. OpenCL-accelerated first-principles calculations of all-electron quantum perturbations on HPC resources. FRONTIERS IN CHEMISTRY[J]. 2023, 11: http://dx.doi.org/10.3389/fchem.2023.1156891.
[3] 张忠诚, 欧焱, 刘颖, 王晨曦 王晨曦, 周永彬, 王晓宇, 张玉洋, 欧阳玉成, 单嘉豪, 王颖, Jingling Xue, 崔慧敏, 冯晓兵. Occamy: Elastically Sharing a SIMD Co-processor across Multiple CPU Cores. ASPLOSnull. 2023, [4] 陈磊, 赵家程, Wang, Chenxi, Ting Cao, John Zigman, Haris Volos, Onur Multu, 吕方, 冯晓兵, Xu, Guoqing Harry, 崔慧敏. Unified Holistic Memory Management Supporting Multiple Big Data Processing Frameworks over Hybrid Memories. ACM Transactions on Computer Systems (TOCS)[J]. 2022, https://dl.acm.org/doi/10.1145/3511211.
[5] 陈磊, 赵家程, 王晨曦, 曹婷, JOHN ZIGMAN, 吕方, 冯晓兵, 崔慧敏. Unified Holistic Memory Management Supporting Multiple Big Data Processing Frameworks over Hybrid Memories. TOCS[J]. 2022, [6] Chen, Lei, Zhao, Jiacheng, Wang, Chenxi, Cao, Ting, Zigman, John, Volos, Haris, Mutlu, Onur, Lv, Fang, Feng, Xiaobing, Xu, Guoqing Harry, Cui, Huimin. Unified Holistic Memory Management Supporting Multiple Big Data Processing Frameworks over Hybrid Memories. ACM TRANSACTIONS ON COMPUTER SYSTEMS[J]. 2021, 39(1-4): [7] 崔慧敏. Accelerating All-Electron Ab initio Simulation of Raman Spectra for Biological Systems. SC. 2021, [8] 崔慧敏. Fang Lv, Hao Li, Lei Wang, Ying Liu, Huimin Cui, Jingling Xue, Xiaobing Feng, Referee: A Pattern-Guided Approach for Auto Design in Compiler-Based Analyzers. SANER. 2020, [9] Wu, Mingchuan, Liu, Ying, Cui, Huimin, Wei, Qingfu, Li, Quanfeng, Li, Limin, Lv, Fang, Xue, Jingling, Feng, Xiaobing, ASSOC COMP MACHINERY. Bandwidth-Aware Loop Tiling for DMA-Supported Scratchpad Memory. PACT '20: PROCEEDINGS OF THE ACM INTERNATIONAL CONFERENCE ON PARALLEL ARCHITECTURES AND COMPILATION TECHNIQUESnull. 2020, 97-109, [10] 崔慧敏. Chunwei Xia, Jiacheng Zhao, Huimin Cui, Xiaobing Feng, Jingling Xue, DNNTune: Automatic Benchmarking DNN Models for Mobile-cloud Computing. TACO. 2020, [11] Lv, Fang, Li, Hao, Wang, Lei, Liu, Ying, Cui, Huimin, Xue, Jingling, Feng, Xiaobing, Kontogiannis, K, Khomh, F, Chatzigeorgiou, A, Fokaefs, ME, Zhou, M. Referee: A Pattern-Guided Approach for Auto Design in Compiler-Based Analyzers. PROCEEDINGS OF THE 2020 IEEE 27TH INTERNATIONAL CONFERENCE ON SOFTWARE ANALYSIS, EVOLUTION, AND REENGINEERING (SANER '20)null. 2020, 1-12, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000568240800001.
[12] Yu, Feng, Zhao, Jiacheng, Cui, Huimin, Feng, Xiaobing, Xue, Jingling, ASSOC COMP MACHINERY. VTensor: Using Virtual Tensors to Build a Layout-Oblivious AI Programming Framework. PACT '20: PROCEEDINGS OF THE ACM INTERNATIONAL CONFERENCE ON PARALLEL ARCHITECTURES AND COMPILATION TECHNIQUESnull. 2020, 345-346, [13] Wang, Chenxi, Cui, Huimin, Cao, Ting, Zigman, John, Volos, Haris, Mutlu, Onur, Lv, Fang, Feng, Xiaobing, Xu, Guoqing Harry. Panthera: Holistic Memory Management for Big Data Processing over Hybrid Memories. PROCEEDINGS OF THE 40TH ACM SIGPLAN CONFERENCE ON PROGRAMMING LANGUAGE DESIGN AND IMPLEMENTATION (PLDI '19)null. 2019, 347-362, http://dx.doi.org/10.1145/3314221.3314650.
[14] Xia, Chunwei, Zhao, Jiacheng, Cui, Huimin, Feng, Xiaobing, Xue, Jingling. DNNTune: Automatic Benchmarking DNN Models for Mobile-cloud Computing. ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION[J]. 2019, 16(4): http://dx.doi.org/10.1145/3368305.
[15] 崔慧敏. Chenxi Wang, Huimin Cui, Ting Cao, John Zigman, Haris Volos, Onur Mutlu, Fang Lv, Xiaobing Feng, Guoqing Harry Xu, Panthera: Holistic Memory Management for Big Data Processing over Hybrid Memories. PLDI. 2019, [16] Liu, Ying, Huang, Lei, Wu, Mingchuan, Cui, Huimin, Lv, Fang, Feng, Xiaobing, Xue, Jingling, Amaral, JN, Kulkarni, M. PPOpenCL: A Performance-Portable OpenCL Compiler with Host and Kernel Thread Code Fusion. PROCEEDINGS OF THE 28TH INTERNATIONAL CONFERENCE ON COMPILER CONSTRUCTION (CC '19)null. 2019, 2-16, http://dx.doi.org/10.1145/3302516.3307350.
[17] 吴艳霞, 梁楷, 刘颖, 崔慧敏. 深度学习FPGA加速器的进展与趋势. 计算机学报[J]. 2019, 42(11): 2461-2480, http://lib.cqvip.com/Qikan/Article/Detail?id=7100202304.
[18] 崔慧敏. On Retargetting the AI Programming Framework to New Hardwares. The 15th Annual IFIP International Conference on Network and Parallel Computing (NPC 2018). 2018, [19] Hu, Danqi, Lv, Fang, Wang, Chenxi, Cui, HuiMin, Wang, Lei, Liu, Ying, Feng, XiaoBing. NVM Streaker: a fast and reconfigurable performance simulator for non-volatile memory-based memory architecture. JOURNAL OF SUPERCOMPUTING[J]. 2018, 74(8): 3875-3903, https://www.webofscience.com/wos/woscc/full-record/WOS:000441875100024.
[20] Xia, Chunwei, Zhao, Jiacheng, Cui, Huimin, Feng, Xiaobing, IEEE. Characterizing DNN Models for Edge-Cloud Computing. 2018 IEEE INTERNATIONAL SYMPOSIUM ON WORKLOAD CHARACTERIZATION (IISWC)null. 2018, 82-83, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000462185400010.
[21] Zhao, Jiacheng, Cui, Huimin, Zhang, Yalin, Xue, Jingling, Feng, Xiaobing, ACM. Revisiting Loop Tiling for Datacenters: Live and Let Live. INTERNATIONAL CONFERENCE ON SUPERCOMPUTING (ICS 2018)null. 2018, 328-340, http://dx.doi.org/10.1145/3205289.3205306.
[22] 王晨曦, 吕方, 崔慧敏, 曹婷, John Zigman, 庄良吉, 冯晓兵. 面向大数据处理的基于Spark的异质内存编程框架. 计算机研究与发展[J]. 2018, 55(2): 246-264, http://lib.cqvip.com/Qikan/Article/Detail?id=7000473978.
[23] Wang Lei, Zhuang Liangji, Chen Junhang, Cui Huimin, Lv Fang, Liu Ying, Feng Xiaobing, Assoc Comp Machinery. LazyGraph: Lazy Data Coherency for Replicas in Distributed Graph-Parallel Computation. PPOPP'18: PROCEEDINGS OF THE 23RD PRINCIPLES AND PRACTICE OF PARALLEL PROGRAMMINGnull. 2018, 276-289, http://dx.doi.org/10.1145/3178487.3178508.
[24] Wang Lei, Zhuang Liangji, Chen Junhang, Cui Huimin, Lv Fang, Liu Ying, Fen Xiaobing. LazyGraph: Lazy Data Coherency for Replicas in Distributed Graph-Parallel Computation. ACM SIGPLAN NOTICESnull. 2018, 53(1): 276-289, [25] Song, YuGeng, Cui, HuiMin, Feng, XiaoBing. Parallel Incremental Frequent Itemset Mining for Large Data. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY[J]. 2017, 32(2): 368-385, http://sciencechina.cn/gw.jsp?action=detail.jsp&internal_id=5940444&detailType=1.
[26] 李登辉, 赵家程, 崔慧敏, 冯晓兵. 数据中心中DVFS对程序性能影响模型的设计. 软件学报[J]. 2017, 28(4): 845-859, http://lib.cqvip.com/Qikan/Article/Detail?id=671917930.
[27] 崔慧敏, 王蕾, 冯晓兵, 刘颖, 黄磊, 吕方. 异构架构下基于放松重用距离的多平台数据布局优化. 软件学报[J]. 2016, 2168-2184, http://lib.cqvip.com/Qikan/Article/Detail?id=669734296.
[28] 吴承勇, 崔慧敏. 异构集群下的MapReduce编程环境. 科技创新导报[J]. 2016, 13(9): 170-170, http://lib.cqvip.com/Qikan/Article/Detail?id=669805511.
[29] Wang, Lei, Yang, Fan, Zhuang, Liangji, Cui, Huimin, Lv, Fang, Feng, Xiaobing. Articulation Points Guided Redundancy Elimination for Betweenness Centrality. ACM SIGPLAN NOTICES[J]. 2016, 51(8): 73-86, https://www.webofscience.com/wos/woscc/full-record/WOS:000393580200008.
[30] Zhao, Jiacheng, Cui, Huimin, Xue, Jingling, Feng, Xiaobing. Predicting Cross-Core Performance Interference on Multicore Processors with Regression Analysis. IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS[J]. 2016, 27(5): 1443-1456, https://www.webofscience.com/wos/woscc/full-record/WOS:000374238100016.
[31] 何文婷, 崔慧敏, 冯晓兵. 异构大数据编程环境Hadoop+. 集成技术[J]. 2016, 60-71, http://lib.cqvip.com/Qikan/Article/Detail?id=669150872.
[32] 何文婷, 崔慧敏, 冯晓兵. HDAS:异构集群上Hadoop+框架中的动态亲和性调度. 高技术通讯[J]. 2016, 26(4): 333-343, http://lib.cqvip.com/Qikan/Article/Detail?id=669860044.
[33] 崔慧敏. A Collaborative Divide-and-Conquer K-Means Clustering Algorithm for Processing Large Data.. 2014, [34] Lv, Fang, Cui, HuiMin, Wang, Lei, Liu, Lei, Wu, ChengGang, Feng, XiaoBing, Yew, PenChung. Dynamic I/O-Aware Scheduling for Batch-Mode Applications on Chip Multiprocessor Systems of Cluster Platforms. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY[J]. 2014, 29(1): 21-37, https://www.webofscience.com/wos/woscc/full-record/WOS:000330317300003.
[35] 刘颖, 吕方, 王蕾, 陈莉, 崔慧敏, 冯晓兵. 异构并行编程模型研究与进展. 软件学报[J]. 2014, 25(7): 1459-1475, http://lib.cqvip.com/Qikan/Article/Detail?id=50166787.
[36] 吕方, 崔慧敏, 霍玮, 冯晓兵. 面向并发性能下降的调度策略的综述. 计算机研究与发展[J]. 2014, 51(1): 17-30, http://lib.cqvip.com/Qikan/Article/Detail?id=48242828.
[37] 王文文, 武成岗, 白童心, 王振江, 远翔, 崔慧敏. 二进制翻译中标志位的模式化翻译方法. 计算机研究与发展[J]. 2014, 51(10): 2336-2347, http://lib.cqvip.com/Qikan/Article/Detail?id=662435627.
[38] 郑亚松, 王达, 叶笑春, 崔慧敏, 徐远超, 范东睿. MALK:一种高效处理大规模键值的MapReduce框架. 计算机研究与发展[J]. 2014, 51(12): 2711-2723, http://lib.cqvip.com/Qikan/Article/Detail?id=663245478.
[39] 王蕾, 崔慧敏, 陈莉, 冯晓兵. 任务并行编程模型研究与进展. 软件学报[J]. 2013, 24(1): 77-90, http://lib.cqvip.com/Qikan/Article/Detail?id=44331446.
[40] 杨扬, 崔慧敏, 冯晓兵. 面向GPU的循环合并. 高技术通讯[J]. 2013, 23(3): 257-262, http://lib.cqvip.com/Qikan/Article/Detail?id=45283321.
[41] Zhao Jiacheng, Cui Huimin, Xue Jingling, Feng Xiaobing, Yan Youliang, Yang Wensen, IEEE. An Empirical Model for Predicting Cross-Core Performance Interference on Multicore Processors. 2013 22ND INTERNATIONAL CONFERENCE ON PARALLEL ARCHITECTURES AND COMPILATION TECHNIQUES (PACT)null. 2013, 201-212, [42] Cui, Huimin, Yi, Qing, Xue, Jingling, Feng, Xiaobing. Layout-Oblivious Compiler Optimization for Matrix Computations. ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION[J]. 2013, 9(4): http://dx.doi.org/10.1145/2400682.2400694.
[43] 赵家程, 崔慧敏, 冯晓兵. 基于统计学习分析多核间性能干扰. 软件学报[J]. 2013, 24(11): 2558-2570, http://lib.cqvip.com/Qikan/Article/Detail?id=47595029.
[44] Cui, Huimin, Xue, Jingling, Wang, Lei, Yang, Yang, Feng, Xiaobing, Fan, Dongrui. Extendable Pattern-Oriented Optimization Directives. ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION[J]. 2012, 9(3): [45] 冯晓兵. A Highly Parallel Reuse Distance Analysis Algorithm on GPUs. IPDPS. 2012, [46] Yang, Yang, Cui, HuiMin, Feng, XiaoBing, Xue, JingLing. A Hybrid Circular Queue Method for Iterative Stencil Computations on GPUs. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY[J]. 2012, 27(1): 57-74, http://lib.cqvip.com/Qikan/Article/Detail?id=40704186.
[47] 杨杨, 崔慧敏, 冯晓兵, 薛京灵. A Hybrid Circular Queue Method for Iterative Stencil Computations on GPUs. 计算机科学技术学报:英文版[J]. 2012, 27(1): 57-74, http://lib.cqvip.com/Qikan/Article/Detail?id=40704186.
[48] 冯晓兵. Automatic Library Generation for BLAS3 on GPUs. IPDPS. 2011, [49] Cui, Huimin, Xue, Jingling, Wang, Lei, Yang, Yang, Feng, Xiaobing, Fan, Dongrui, IEEE. Extendable Pattern-Oriented Optimization Directives. 2011 9TH ANNUAL IEEE/ACM INTERNATIONAL SYMPOSIUM ON CODE GENERATION AND OPTIMIZATION (CGO)null. 2011, 107-118, [50] Cui, HuiMin, Wang, Lei, Fan, DongRui, Feng, XiaoBing. Landing Stencil Code on Godson-T. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY[J]. 2010, 25(4): 886-894, http://lib.cqvip.com/Qikan/Article/Detail?id=34470262.
[51] Wang Lei, Cui Huimin, Duan Yuelu, Lu Fang, Feng Xiaobing, Yew PenChung, ACM. An Adaptive Task Creation Strategy for Work-Stealing Scheduling. CGO 2010: THE EIGHTH INTERNATIONAL SYMPOSIUM ON CODE GENERATION AND OPTIMIZATION, PROCEEDINGSnull. 2010, 266-+, [52] 崔慧敏, 王蕾, 范东睿, 冯晓兵. Landing Stencil Code on Godson-T. 计算机科学技术学报(英文版)[J]. 2010, 886-894, http://lib.cqvip.com/Qikan/Article/Detail?id=34470262.
[53] 谢海斌, 武成岗, 崔慧敏, 李晶. 二进制翻译中的X86浮点栈处理. 计算机研究与发展[J]. 2007, 44(11): 1946-1954, http://lib.cqvip.com/Qikan/Article/Detail?id=25904276.
[54] 高琳, 石学林, 蒋弘山, 崔慧敏, 武成岗, 张兆庆, 乔如良, 冯晓兵. 代码翻译中PERFORM和GOTO语句复合结构的变换. 软件学报[J]. 2004, 15(4): 475-486, http://lib.cqvip.com/Qikan/Article/Detail?id=9392750.
[55] 崔慧敏, 戴桂兰, 王生原, 张素琴. 动态编译技术研究. 计算机科学[J]. 2004, 31(7): 113-117, http://lib.cqvip.com/Qikan/Article/Detail?id=10670964.