Welcome to my homepage! I (Eric, or Zhiqiang) am a performance and latency sensitive computer systems designer and builder, with experiences of designing/building or leading teams to build scalable systems like high performance parallel data processing platforms for big data, large scale (PBs) data storage systems, blockchain system for high throughput and low latency transaction processing.
I received his PhD degree from the Department of Computer Science and Engineering of The Hong Kong University of Science and Technology in 2014 and the bachelor’s degree in Computer Science from Fudan University in 2009.
Projects and products I ever worked on
Some of the systems and projects I ever worked on are as follows.
Industrial projects and products
- Data Thinker (D-thinker): A general, efficient and easy-to-use distributed big data processing engine that is several times faster Spark and 10s of times faster than Hadoop, supporting Java, Python, C/C++, puc, c0/Layer Zero and etc. [Product page] [Homepage]
- D-store: A scalable, fault-tolerant and easy-to-use distributed large scale data storage system with various underlying storage modules like HDFS and Ceph, supporting data synchronization over WAN.
- GLAD: A high-speed parallel genome analysis system making genome analysis easy and fast on D-thinker. Accelerating analysis by 10s of times on server clusters without requiring much changes to original sequential pipeline implementations. [Product page] [Whitepaper of one workflow on GLAD]
- ThinkBox/Genes’ Mind Big Data Appliance: a high-performance big data storage processing hardware and software integrated appliance system. [Product page]
- Layer Zero (L0): A general-purpose substrate for cloud computing. [Zhiqiang’s PhD Thesis: download here or from HKUST Library]
- VOLUME (Virtual On-Line Unified Memory Environment): A distributed virtual memory that unifies the physical memory and disk resources on many compute nodes and form a system-wide data substrate to support large-scale in-memory computation. [CloudCom’13 paper]
- DVM: A distributed virtual machine that comprises a large number of physical hosts. [TC paper] [VEE’12 paper]
- MRlite: A lightweight and efficient parallelization framework for MapReduce-style computation. [CLOUD COMPUTING 2010 paper] [mrcc]
- CCMR: A cloud computing testbed for systems research and scientific computing at HKUST. [Homepage (archive)] [a short description in Section 4 of DVM paper]