In September 2017, University of Science and Technology of China planned to establish an Intelligent Cloud Computing Center at its Suzhou Institute for Advanced Research, aiming to build a high energy-efficient intelligent cloud computing platform with massive data processing capability, and to serve the teaching, research, and enterprises’ technological innovation in big data, artificial intelligence, and other new engineering fields. In October 2018, the first phase of construction was completed and became the Suzhou Branch of Super-computing Center of USTC.

The Center will focus its work on the following fields. 1. Aiming at AI applications, the Center will focus on the design of heterogeneous computing hardware and software system, and study the system’s performance and power consumption in application layer, system layer, and architecture layer, so as to provide optimization methods of software and hardware collaboration in both terminal and cloud computing environments. 2. Based on the domestic intelligent processor, the Center will research and develop a high energy-efficient intelligent computing platform, and promote its application in intelligent endpoint devices, intelligent servers, and cloud computing centers. 3. The Center will build the high energy-efficient computing infrastructure and form an innovation platform for industry, education and research, so as to serve technological innovation, talent training and industrial development in AI.

The Center consists of the Embedded System Laboratory (Suzhou Key Laboratory) and the Joint Laboratory for High Energy-Efficient Intelligent Computing (jointly established with Cambricon), covering an area of more than 600 square meters. The Center has more than 20 staff members and more than 50 graduate students. The research staff mainly come from USTC Suzhou Institute for Advanced Research, USTC, and part-time researchers from outside the University. The Center focuses on the system level design and the optimization of problems. Its research fields include the heterogeneous multi-core architecture for specific areas (including intelligent processor, heterogeneous computing system), the embedded system (including real-time system, reconfigurable computing systems), and the parallel and distributed systems (including high performance computing, cloud computing systems).

Researchers

Faculty of USTC Suzhou Institute for Advanced Research

USTC Faculty

Outside Researchers

Publications

[1].   [TC] Chao Wang, Xi Li, Junneng Zhang, Peng Chen, Yunji Chen, Xuehai Zhou, Ray C.C. Cheung: Architecture Support for Task Out-of-order Execution in MPSoCs, IEEE Transactions on Computers.

[2].   [TCBB] Chao Wang, Xi Li, Peng Chen, Xuehai Zhou, Aili Wang and Hong Yu, “Heterogeneous Cloud Framework for Big Data Genome Sequencing”, IEEE/ACM Transactions on Computational Biology and Bioinformatics. Featured Spotlight Paper.

[3].   [TPDS] Shaoli Liu, Tianshi Chen, Ling Li, Xi Li, Mingzhe Zhang, Chao Wang, Haibo Meng, Xuehai Zhou, and Yunji Chen, FreeRider: Non-local Adaptive Network-on-Chip Routing with Packet-Carried Propagation of Congestion Information, IEEE Transactions on Parallel and Distributed Systems.

[4].  [JPDC] Chao Wang, Xi Li, Peng Chen, and Xuehai Zhou, “A Case Study of Parallel JPEG Encoding on an FPGA,” Journal of Parallel and Distributed Computing.

[5].   [IJE] Chao Wang, Xi Li, Xuehai Zhou, Nadia Nedjah, Aili Wang, “Codem: A Software/Hardware Codesign Flow for Embedded Multicore Systems Supporting Hardware Services”, International Journal of Electronics.

[6].   [JCST] Chao Wang, Xi Li and Xuehai Zhou, “CRAIS: A Crossbar based Interconnection Scheme on FPGA for Big Data”, Journal of Computer Science and Technology.

[7].   [IJHPSA]Huang Wang, Chao Wang, Huaping Chen: XEMU: a cross-ISA full-system emulator on multiple processor architectures. IJHPSA 5(4):  228-239 (2015)

[8].   [IJCSE]Jinhong Zhou, Chao Wang, Xi Li, Xuehai Zhou: Fast approximate hash table using extended counting Bloom filter. IJCSE 11(4): 380-390 (2015)

[9].  [DATE] Chao Wang, Xi Li, Xuehai Zhou, SODA: Software Defined FPGA based Accelerators for Big Data, Design, Automation and Test in Europe, 2015. Best IP Paper Nomination.

[10].    [FPGA] Chao Wang, Xi Li, Qi Guo, Peng Chen and Xuehai Zhou, “RapidPath:  Accelerating Constrained Shortest Path Finding in Graphs on FPGA”, FPGA  2015 {Poster}.

[11].    [CCGRID] Qi Yu, Chao Wang, Xiang Ma, Xi Li and Xuehai Zhou, “A Deep Learning accelerator-based FPGA” 15th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing.

[12].    [Cluster] Xiang Ma, Chao Wang, Qi Yu, Xi Li, Xuehai Zhou: An FPGA-Based Accelerator for Neighborhood-Based Collaborative Filtering Recommendation Algorithms. CLUSTER 2015: 494-495.

[13].    [ICA3PP] Fahui Jia, Chao Wang, Xi Li, Xuehai Zhou: SAKMA: Specialized FPGA-Based Accelerator Architecture for Data-Intensive K-Means Algorithms. ICA3PP (2) 2015: 106-119

[14].   [TPDS] Chao Wang, Xi Li, Junneng Zhang, Aili Wang, Xuehai Zhou:  Hardware Implementation on FPGA for Task-level Parallel Dataflow Execution Engine, IEEE Transactions on Parallel and Distributed Systems.

[15].   [TVLSI] Qi Guo, Xi Li, Chao Wang, Xuehai Zhou: Evaluation and Tradeoffs for Out-of-Order Execution on Reconfigurable Heterogeneous MPSoC. IEEE  Trans. VLSI Syst. 24(1): 79-91

[16].   [ASOC] Chao Wang, Xi Li, Xuehai Zhou, Aili Wang, Nadia Nedjah: Soft  computing in big data intelligent transportation systems. Appl. Soft  Computing. 38: 1099-1108.

[17].   [JSA] Beilei Sun, Xi Li, Bo Wan, Chao Wang, Xuehai Zhou, Xianglan Chen,  Definitions of Predictability for Cyber Physical Systems, Journal of  Systems Architecture.

[18].   [IJPP]Nadia Nedjah, Luiza de Macedo Mourelle, Chao Wang, A Parallel Yet  Pipelined Architecture for Efficient Implementation of the Advanced  Encryption Standard Algorithm on Reconfigurable Hardware, International  Journal of Parallel Programming.

[19].   [IJPP]Nadia Nedjah, Rogério de M. Calazan, Luiza de Macedo Mourelle,  Chao Wang, Parallel Implementations of the Cooperative Particle Swarm  Optimization on Many-core and Multi-core Architectures, International  Journal of Parallel Programming.

[20].   [IJHPSA]Beilei Sun, Xi Li, Chao Wang, Bo Wan and Xuehai Zhou, KUMMS:  optimizing DRAM locality with Kernel-user behaviors, Int. J. High  Performance Systems Architecture.

[21].    [GLSVLSI] Jiachen Song, Xi Li, Beilei Sun, Zhinan Cheng, Chao Wang and  Xuehai Zhou: FCM: Towards Fine-Grained GPU Power Management for Closed  Source Mobile Games, in GLSVLSI 2016.

[22].   [ASAP] Zhinan Cheng, Xi Li, Jiachen Song, Beilei Sun, Xuehai Zhou and  Chao Wang: Display Power Reduction for Mobile Closed-Source Games, 27th  Annual IEEE International Conference on Application-specific Systems,  Architectures and Processors.

[23].    [ICWS] Chao Wang, Xi Li, Qi Yu, Aili Wang, Patrick Hung, Xuehai Zhou:  SOLAR: Services-oriented Learning Architectures, IEEE International  Conference on Web Services.

[24].    [ICWS] Chao Wang, Xi Li, Jinhong Zhou, Aili Wang, Xuehai Zhou:  FairPlay: Services Migration with Lock-free Mechanisms for Load  Balancing in Cloud Architectures, IEEE International Conference on Web  Services (Research Track).

[25].    [SPAA] Chao Wang, Xi Li, Aili Wang and Xuehai Zhou: Brief  Announcement: MIC++: Accelerating Maximal Information Coefficient  Calculation with GPUs and FPGAs, 28th ACM Symposium on Parallelism in  Algorithms and Architectures.

[26].    [ISPA] Shiming Lei, Chao Wang, Xi Li, Haijie Fang and Xuehai Zhou,  SCADIS: A Scalable Accelerator for Data- Intensive String Set Matching  on FPGAs, The 14th IEEE International Symposium on Parallel and  Distributed Processing with Applications.

[27].    [MASCOTS] Zhinan Cheng, Xi Li, Beilei Sun, Jiachen Song, Chao Wang and  Xuehai Zhou, Behavior-Aware Integrated CPU-GPU Power Management For  Mobile Games, Modeling, Analysis, and Simulation On Computer and  Telecommunication Systems. 

[28].    [ICPADS]Yangyang Zhao, Qi Yu, Xuda Zhou, Xuehai Zhou, Chao Wang and Xi  Li, PIE: A Pipeline Energy-efficient Accelerator for Inference Process  in Deep Neural Networks, The 22nd IEEE International Conference on  Parallel and Distributed Systems

[29].   [TPDS] Chao Wang, Xi Li, Yunji Chen, Youhui Zhang, Oliver Diessel,  Xuehai Zhou: Service-oriented Architecture on FPGA-based MPSoC, IEEE  Transactions on Parallel and Distributed Systems.

[30].   [TCBB]Chao Wang, Xi Li, Dong Dai, Aili Wang, and Xuehai Zhou,  Accelerating Computation of Large Biological Datasets using MapReduce  Framework IEEE/ACM Transactions on Computational Biology and  Bioinformatics.

[31].   [TCAD]Chao Wang, Lei Gong, Qi Yu, Xi Li, Yuan Xie, Xuehai Zhou, DLAU: A  Scalable Deep Learning Accelerator Unit on FPGA, IEEE Transactions on  Computer-Aided Design of Integrated Circuits and Systems

High Energy-Efficient Intelligent Computing Infrastructure:

Taking the domestic intelligent chips (Cambricon chips) as the basis, the Center has developed an independent, safe and controllable 100-node energy-efficient intelligent computing cluster system, designed and deployed a super-large capacity distributed storage system, and completed the research and development of several typical demonstration application systems.

Cooperation and Service      

The Center's external cooperation and service include:

1.Efficient artificial intelligence cloud computing;

2.Development and promotion of typical demonstration applications;

3.Collaborative research and academic exchange of research institutions;

4.Artificial intelligence innovation research and development and achievements transformation.

Contact Information

Address: Min Xue Building, No. 188 Renai Road, Suzhou Industrial Park, Suzhou City, Jiangsu Province.

Post code: 215123.

Intelligent Cloud Computing Research Center, USTC Suzhou Institute for Advanced Research

Tel:

Customer Service Department: Gao Wang 18151102111

Embedded System Laboratory: Wang Chao 0512-62888062

Joint Laboratory for High Energy-Efficient Intelligent Computing: Zhu Zongwei

0512-62886872