基本信息
views: 405
![](https://originalfileserver.aminer.cn/sys/aminer/icon/show-trajectory.png)
Bio
Dr. Suns current research includes the development of Application-Aware I/O systems for Big Data applications, the development of data-centric system software/hardware for high-end computing, and the integration of HPC and Cloud Computing. His research is both application and technology driven. For the former, he and his research group have developed a series of software systems for high-end computing. These include the software packages of Hermes: A Heterogeneous-Aware Multi-Tiered Distributed I/O Buffering System; PortHadoop: an extension of Hadoop to support direct HPC data processing under Hadoop environments; IOSIG: I/O Signatures Based Data Access Optimization, PFS-IOC: Server-side I/O-Coordination in Parallel File System; GHS: Grid Harvest Service; Network Bandwidth Predictor (NBP); and HPCM: High Performance Computing Mobility; etc. For the latter, he and his collaborators have made several noticeable contributions in recognizing and modeling the influence of the advancements of hardware and network technology on computing systems. These include the introduction of the memory-bounded speedup model (1990), which is the first work to reveal that memory is the performance constraint for high-end computing and presents a quantitative mathematical formulation for the trade-off between memory and computing, the algorithm-machine combination scalability, the general speedup metric, a model for non-dedicated network computing, and an extended Amdahls law for multicore systems, etc. More recently, he and his associates have introduced the Concurrent Average Memory Access Time (C-AMAT) model and the memory Access Per memory active Cycle (APC) metric for modern memory systems in 2013 and 2011, respectively. These results are vital tools to understand and evaluate modern memory systems and to utilize computer architecture and software for data-intensive applications. His recent Pace Data Transfer architecture (backed by the Sluice Gate Theory) has reduced memory stall time 150 times and suggests a rethinking of memory system design. His group received the ACM/IEEE HPC award and the NSF V-Tech HEC Challenge award in 2008, 2007 and 2006 for its contributions in data access optimization and fault-tolerant computing, respectively; and received different ACM and IEEE research and service awards in 2015, 2016, 2017 and 2019. Dr. Sun is an IEEE Fellow for his Contributions to Memory-Bounded Performance Metrics and Scalable Parallel Computing.
Research Interests
Papers共 409 篇Author StatisticsCo-AuthorSimilar Experts
By YearBy Citation主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
IEEE International Parallel and Distributed Processing Symposiumpp.494-505, (2024)
2024 IEEE International Parallel and Distributed Processing Symposium (IPDPS)pp.494-505, (2024)
International Symposium on High-Performance Computer Architecturepp.1154-1167, (2024)
2023 IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER AIDED DESIGN, ICCADpp.1-9, (2023)
SCpp.58:1-58:15, (2023)
J. Comput. Sci. Technol.no. 1 (2023): 64-79
HPCApp.220-232, (2023)
CHEOPS '23: Proceedings of the 3rd Workshop on Challenges and Opportunities of Efficient and Performant Storage Systemspp.9-16, (2023)
Frontiers of Informaion Technology & Electronic Engineeringno. 5 (2023): 716-730
Load More
Author Statistics
Co-Author
Co-Institution
D-Core
- 合作者
- 学生
- 导师
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn