651 66902

WONG Weng Fai

Associate Professor
IT Coordinator, Computing Facilities

  • Dr.Eng.Sc. (University of Tsukuba, 1993)
  • M.Sc. (National University of Singapore, 1991)
  • B.Sc. (1st Class Honours, National University of Singapore, 1989)

Weng-Fai works in the systems area with particular interest in the interface between the hardware and software stacks, and how they can be mutually co-optimized. He has worked on optimizing software and applications for novel hardware including FPGAs, GPUs, non-volatile memory, and specialized bus interfaces. These days, his focus is on approximate computing, including precision analysis, variable precision arithmetic, and approximation of deep learning networks using approximate hardware accelerators.



  • Embedded Systems

  • Compilers and Runtime Systems

  • Computer Architecture

  • Programming Languages

  • Computer Architecture

  • Memory


Machine Learning for Compilation

This project aims to enhance compiler optimization using machine learning. It utilizes graph convolutional neural networks (GCN) to predict optimization efficacy for code fragments. Key objectives include developing effective graph embeddings, selecting appropriate GCN models, and creating a compiler optimization recommender system.

Operating System Support for Large Memory Systems

This project tackles performance limitations in large server systems with extensive memory. It proposes OS-level solutions to optimize memory access for both traditional Non-Uniform Memory Access (NUMA) systems and emerging disaggregated memory architectures. The goal is to improve performance, power efficiency, and cost-effectiveness for data centers.




  • S. Rajadurai, J. Bosboom, W.F. Wong, and S. Amarasinghe, "Gloss: Seamless Live Reconfiguration and Reoptimization of Stream Programs." Accepted by The 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems ASPLOS 2018. Williamsburg, VA. U.S.A. Mar 2018.
  • N.M. Ho, and W.F. Wong, "Exploiting half precision arithmetic in Nvidia GPUs," Accepted by 2017 IEEE High Performance Extreme Computing Conference HPEC 2017. Waltham, MA, U.S.A. Sep 2017. Best Paper Finalist
  • J. Zhou, Y. Zhang, and W.F. Wong. "Fault Tolerant Stencil Computation on Cloud-based GPU Spot Instances." Accepted for publication by IEEE Transactions on Cloud Computing.
  • C. Wang, and W.F. Wong. "TreeFTL: An Efficient Workload-adaptive Algorithm for RAM Buffer Management of NAND Flash-based Devices". IEEE Transactions on Computers. Vol. 65, No. 8, pp. 2618-2630. Aug 2016.
  • W.T. Tang, W.J. Tan, R.S.M Goh, S.J. Turner, and W.F. Wong, "A Family of Bit-Representation-Optimized Formats for Fast Sparse Matrix-Vector Multiplication on the GPU". IEEE Transactions on Parallel and Distributed Systems. Vol. 26, No. 9, pp. 2373-2385. Sep 2015.
  • P. Roy, J. Wang, and W.F. Wong, "PAC : Program Analysis for Approximation-aware Compilation". Proceedings of 2015 ACM International Conference on Compilers, Architecture, and Synthesis for Embedded Systems CASES. pp. 69-78. Amsterdam, The Netherlands. Oct 2015.



Computer Organisation
Advanced Operating Systems