Overview

Overview:


The Center for Advanced Computer Systems (ACS) of the Institute of Computing Technology, Chinese Academy of Sciences was established on the basis of Laboratory for Advanced Computer System since September 2011. In November 2013, it became a scientific research entity of the Institute of Computing Technology.


The center is mainly engaged in software and hardware co-design for emerging workloads such as big data and artificial intelligence, open source chips, open source computer systems, and benchmark science and engineering. There are five laboratories: Frontier System Laboratory, Software System Laboratory, Architecture Laboratory, Data System Laboratory, Data Computing Laboratory.


At present, the center has nearly 50 permanent staff, including 7 professors/researchers, 12 associate professors/researchers. It has nearly 150 students studying or visiting. The center recruits postdoctoral fellows, staff and visiting students all the year round. The center is responsible for the theoretical and experimental teaching of the two core courses (Principles of Computer Organization and Operating System) at the University of Chinese Academy of Sciences. In recent years, the center has mainly undertaken the Strategic Pilot Projects of the Chinese Academy of Sciences, the Projects of National Natural Science Foundation of China, and the National Key Research and Development Program of China.


Divisions:


Software System Laboratory:


Taking the goal of “theories, open source systems and tools that have impacts on the international academia and industry”, the Software System Laboratory continues to carry out basic research and publish high-impact papers. The representative works that have been completed include cluster/cloud operating systems, data center node operating systems, big data benchmarks, and BenchCouncil artificial intelligence benchmarks. More than 90 students or engineers have studied or worked here, and graduate representatives include tenured associate professors of top American universities and architects of Internet giants at home and abroad.


Ongoing Projects:


1)Research on abstractions, ISA, micro architecture, and system for emerging workloads such as big data and artificial intelligence

2)Open source computer systems and open source chips: open-source planet-scale computers for emerging and future applications, open source chip design methodologies and tools based on observation-reference-fusion-feedback loop

3)Basic theories, methods and tools of benchmark science and engineering: develop benchmark science and engineering independent of metrology


Main Staffs:


Jianfeng Zhan, Professor/Researcher

(zhanjianfeng@ict.ac.cn, homepage: http://www.benchcouncil.org/zjf.html

Lei Wang, Senior Engineer

(wanglei_2011@ict.ac.cn, homepage: https://www.benchcouncil.org/wl.html

Wanling Gao, Associate Professor

(gaowanling@ict.ac.cn, homepage: https://www.benchcouncil.org/wlgao

Chunjie Luo, Associate Professor

(luochunjie@ict.ac.cn, homepage: https://www.benchcouncil.org/cjluo.html


Frontier System Laboratory:


The main research direction of our lab is open-source chip ecology and cloud computing data center with software and hardware collaboration. The team has carried out a series of advanced researches in RISC-V processor design, agile design methods for processors, etc., and has formed a certain influence at home and abroad. Besides, the team has long-term cooperation with Huawei, Alibaba, Tencent, Meituan and other corporations, focusing on software and hardware optimization technology in the cloud computing data center. With the support of the Ministry of Science and Technology's Key R&D Program, the Ministry of Science and Technology's International Key Cooperation Project, the National Natural Science Foundation of China, and other enterprises, we have published more than 40 papers in top international conferences and journals, such as FOCS, HPCA, ISCA, SIGCOMM, and SIGMETRICS. We have won the first prize for outstanding papers at the Institute of Computing Technology twice.


Ongoing Projects:


(1) Xiangshan – An Open-Source High-Performance RISC-V Processor. It has better performance than any other open-source RISC-V processors all over the world. Further, it draws lots of attention and is under support of domestic and foreign companies, in which 16 companies collaboratively develop under the foundation of Xiangshan. This research will accelerate the construction of RISC-V ecology.

(2) One Student One Chip Initiative. The project guides students to design a tape-out open-source processor by combing EE with CS. It can help students improve their capacity of implementing software and hardware systems and learn how to design chips. Meanwhile the project trains talents to be transferred to the high-performance processor "Xiangshan", open source EDA, open source IP and other teams and communities, which will continue to cultivate excellent reserve forces for advanced research and development of CS in China.

(3) The Information Superbahn Measurement and Control System. The Information Superbahn is a new information infrastructure proposed by ICT. The measurement and control system are the core of the Information Superbahn, which provides low-latency and high-throughputs services by some control mechanisms such as labelling and regulation.

(4) An Open-Source EDA project. It builds an open-source EDA software tool to achieve automated 28nm-chip design, which can automate chip design process so as to reduce the cost of designing chips.


Main Staffs:


Professor Yungang Bao(baoyg@ict.ac.cn, Homepage: http://acs.ict.ac.cn/baoyg/

Senior Engineer Dan Tang(tangdan@ict.ac.cn, Homepage : http://www.ict.cas.cn/sourcedb_2018_ict_cas/cn/jssrck/202007/t20200721_5638886.html

Associate Professor Sa Wang (wangsa@ict.ac.cn,Homepage :https://sooner.github.io/

Associate Professor Di Zhao,(zhaodi@ict.ac.cn,Homepage:http://www.ict.cas.cn/sourcedb_2018_ict_cas/cn/jssrck/201803/t20180309_4971421.html

Associate Professor Kan Shi(shikan@ict.ac.cn)

Associate Professor Biwei Xie(xiebiwei@ict.ac.cn)

Research Assistant He Li(lihe@ict.ac.cn)



Architecture Laboratory:


The predecessor of the laboratory was the Advanced System research Group of the National Intelligent Computer research and development Center established in 2003. In 2011, it was transferred to the Advanced Computer System research center. The research interests of this laboratory is based on the high-performance computer architecture, including system software/hardware and algorithm optimization. At present, the main research interests are memory system accessing, controlling and optimization, computer system hardware acceleration, network structure on cloud service data center, software/hardware network protocol stack and secure computer architecture, etc.


Ongoing Projects:


(1)Message Interfaced Memory System

(2) SERVE Cloud Platform for Agile Chip Development

(3) C10m user-space network stack QStack

(4) DASICS (Dynamic in-Address Space Isolation by Code Segments)

(5) Memory access pattern optimization engine on Storage system


Main Staffs:


Mingyu Chen Professor cmy@ict.ac.cn Homepage:http://asg.ict.ac.cn/cmy

Ke Zhang Professor zhangke@ict.ac.cn

Yuhang Liu Assistant Professor liuyuhang@ict.ac.cn

Wenli Zhang,Senior Engineer zhangwl@ict.ac.cn

Yisong Chang,Senior Engineer changyisong@ict.ac.cn

Ke Liu Associate Professor liuke@ict.ac.cn

Tianyue Lu,Research Assistant lutianyue@ict.ac.cn

Yangyang Zhao,Engineer zhaoyangyang@ict.ac.cn


Data System Laboratory:


The research goal of Data System Laboratory is building high-performance data storage systems. Currently, the Lab focuses on research over the storage software/hardware stack, including the design and implementation of the prototype systems. The systems should not only meet the data I/O requirements of datacenter applications such as cloud computing, big data, AI, and emerging applications, but also deal with the challenges brought by hardware breakthroughs including storage and network devices and CPU. Representative works include distributed storage system QWin, high-performance key-value store systems HiKV and LightKV, open-source SSD controller based on RISC-V, vectorize SQL engine VEE for big data analytics.

The Lab has a good academic environment and outputs excellent research fruits. We have published many high-quality papers at top-ranking academic conferences and transactions including ATC, ICDCS, SC, MSST, PACT, ICS, IPDPS, TPDS, and TACO. The Lab owns over 50 Grant patents for invention and over 10 Computer Software Copyrights. The Lab got one Second Prize of China Science and Technology Progress Awards and one Outstanding Achievements Awards (Group) from Chinese Academy of Sciences. Over 30 students got their Ph.D or Master degrees from the Lab, and they got job offers from big corporations such as Huawei, Tencent, Google (at Mountain View), Twitter (at San Francisco), or went aboard for pursuing Ph.D degree, or started up a new company. The lab’s research works were supported by National Key Research and Development Program of China, National Basic Research Program of China (973 Program), National High-Technology Research and Development Program of China (863 Program), National Science Foundation of China, Strategic Priority Research Program of the Chinese Academy of Sciences. The lab also collaborates with many companies such as Huawei, Ali, Baidu, Ant Financial, and SenseTime. The Lab's home page is http://acs.ict.ac.cn/storage/.


Ongoing Projects:


(1)FuYao (扶摇): a distributed storage system with preticable tail latency for hybrid workloads in datacenters

(2)TianChi (天池): a high-performance distributed memory pool

(2)Wukong (悟空): an open source SSD controller based on RSIC-V


Main Staffs:


Jin Xiong (Professor)

(xiongjin@ict.ac.cn, http://acs.ict.ac.cn/storage/people_ssg/professor/202203/t20220318_21110.html

Dejun Jiang (Associate Professor)

(jiangdejun@ict.ac.cn,http://acs.ict.ac.cn/storage/people_ssg/professor/202203/t20220318_21111.html

Liuying Ma (Engineer)

(maliuying@ict.ac.cn, http://acs.ict.ac.cn/storage/people_ssg/engineer/202203/t20220329_25106.html

Mi Zhang (Assistant Professor)

(zhangmi@ict.ac.cn, http://acs.ict.ac.cn/storage/people_ssg/engineer/202203/t20220329_25105.html


Data Computing Laboratory:


Focusing on database systems, big data processing, and cloud computing, the lab consists of the database system group and the cloud computing group.

Database System Group: Directed by Prof. Shimin Chen, the group focuses on new database system research with two driving forces: new hardware technologies, and new application demands. From the hardware perspective, we exploit NVM, many-core processors, and software-hardware co-designs, to optimize core data structures and algorithms, transaction processing, and data analysis. From the application perspective, we aim to support a variety of data models (such as JSON, graphs, and time series), and exploit AI to optimize data structure designs and database performance. We publish in top-tier conferences and journals, including SIGMOD/VLDB/TODS/VLDB Journal. Previous and current projects are from MOST and NSFC, and companies, such as Alibaba and Meituan. Moreover, we organize the HardBD&Active workshop, whose theme is hardware acceleration for big data processing, in the ICDE conferences, and teach the graduate “big data system and large-scale data analysis” course and undergraduate “database systems” course in UCAS.

Cloud Computing Group: Directed by Prof. Yuzhong Sun, the group focuses on large-scale or data-center efficient computing of a large amount of tasks by designing better resource and task scheduling strategies. With the popularity of cloud computing, our group works on virtualization issues for virtual machines and dockers, e.g., efficient delivery algorithms, quick start-up techniques, and energy-minimized migration methods of dockers in the K8S framework. Moreover, in light of the interesting challenges of deep learning training and learning in cloud computing, we also start new research on efficient large-scale distributed deep learning training, e.g., better overlapping of training computing and communication, better compression algorithms to reduce the amount of intermediate data. We have published 50+ peer-reviewed papers and filed 30+ patents. Our research has been financially supported by MOST and NSFC, and Alibaba or other companies.


Main staff:

Shimin Chen (Professor)

Yuzhong Sun (Professor)

Zhiyi Wang (Engineer)