Research Interests

I am a ECE PhD student at Northeastern University.

A NUCAR member
A PROTECT Trainee on Data Management

Dr. Kaeli is my research advisor.

409 Dana Research Center
360 Huntington Ave
Boston, MA 02115

  [Research Interests]

[1] Development and optimizations of GPGPU applications and their performance in HPC.
[2] Workloads analysis and modeling for heterogeneous systems.
[3] Compiler-related

  [Work Experience]

PROTECT at NU's Pop-Up Open Lab Experience 2014
Big Data Management and Analysis of PROTECT(link)

RISE Poster 2014
Advanced Data Management and Modeling Core on PROTECT(link)

Teaching Assistant, GPU Class, Dr. Rafael Ubal

May,2012-Aug,2012 Internship at Mathworks
1) Accelerate PSKDemodulator/Modulator on GPU
2) Accelerate LDPCDecoder for Large Parity Check Matrix on GPU
3) Speedup parfor section in commViterbiSystemGPU demo
4) Accelerate Turbodecoder on Matlab Distributed Computing Server (MDCS)

Vice President, Academic Affairs For Graduate Engineering Bridges(GEB) at NEU


  • Leiming Yu, John Magrath, Ajey Pandey, Matthew Sears, and David Kaeli,
    "Speech Recognition on Modern Graphic Processing Units".
    Boston Area Architecture Workshop. 2015. [pdf]
  • Leiming Yu, Yan Zhang, Xiang Gong, Nilay Roy, Lee Makowski and David Kaeli,
    "High Performance Computing of Fiber Scattering Simulation".
    Proceedings of Workshop on General Purpose Processing Using GPUs. ACM, 2015. [pdf]
  • Yash Ukidave, Fanny Nina Paravecino,Leiming Yu, Charu Kalra, Amir Momeni, Zhongliang Chen, Nick Materise, Brett Daley and David Kaeli,
    "NUPAR: A Benchmark Suite for Modern GPU Architectures".
    ICPE, 2015. [pdf]
  • Leiming Yu, Yash Ukidave, David Kaeli,
    "GPU-accelerated HMM for Speech Recognition".
    HUCAA, 2014 [pdf] [ppt] [hucaa]
  • Yan Zhang,Leiming Yu, David Kaeli, Lee Makowshi,
    "Fast Simulation of X-ray Diffraction Patterns from Cellulose Fibrils using GPUs".
    NEBEC, 2014. [link] [pdf]


Workload Scheduling for Heterogeneous Systems

GPU-accelerated Speech Recognition

Modeling Concurrent Kernel Execution on GPU

Fiber Scattering Simulation On Discovery Cluster  (GPGPU-8)

Hidden Markov Model on GPU  (HUCAA'14, Source Code)

Parallel IIR, as part of NUPAR Benchmark Suite  (ICPE)


  • Computer Architecture, NEU
  • High Performance Computing, NEU
  • Simulation and Performance Evaluation, NEU
  • Combinatorial Optimization, NEU
  • Heterogeneous Parallel Programming, Coursera (pdf)
  • Intro to Parallel Programming, Udacity (pdf)
  • Machine Learning, Coursera
  • Natural Language Processing, Coursera
  • Programming for Everybody (Python), Coursera(pdf)

Top of Page