About Me

Profile Image

I am a Ph.D. candidate in Computer Science and Engineering at the University of Michigan, Ann Arbor where I am advised by Professor Valeria Bertacco. I am member of the Computer Engineering Lab (CE Lab) and also affiliated with the Applications Driving Architectures (ADA) center. I received my bachelor’s degree from Addis Ababa Institute of Technology, Addis Ababa.
My research interest is generally in the area of computer architecture, particularly focusing on the acceleration of data-centered applications. I am currently working on addressing bottlenecks in the execution of irregular workloads on GPGPUs via a custom memory subsytem. Priorly, I have been working on alleviating communication bottleneck in graph analytics by making use of in-network computation and specialized logic units in processing-in-memory based architecture.

Social

Resume

Education

Ph.D. Computer Science and Engineering

University of Michigan, Ann Arbor, MI

Sept 2018 - Present


B.Sc. Electrical and Computer Engineering

Addis Ababa University, Addis Ababa, Ethiopia

Sept 2012 - May 2017

Publications

  • All
  • GraphVine
  • MessageFusion

[1] Leul Belayneh, Valeria Bertacco. GraphVine: Exploiting Multicast for Scalable Graph Analytics. Design, Automation & Test in Europe Conference & Exhibition (DATE), Grenoble, France, 2020.

[2] Leul Belayneh, Abraham Addisie, Valeria Bertacco. MessageFusion: On-path Message Coalescing for Energy Efficient and Scalable Graph Analytics. International Symposium on Low Power Electronics and Design (ISLPED), Lausanne, Switzerland, 2019.

GraphVine

image

MessageFusion

image

Projects

  • MultiScape: Multicast for Scalable PageRank Execution

    Implemented an HMC-based graph processing system which utilizes multicast to reduce the inter-cube communication bottleneck present in PageRank execution. Extended version of this project, which targets multiple graph-based algorithms, is currently on submission. A C++-based in-house cycle accuarate simulator, comprised of Booksim and CasHMC, models the system.

  • Processing in Network Solution for Scalable Graph Analytics

    Leveraged a compute-capable interconnect to perform reduction operation, which in turn reduces inter-cube communication traffic present in graph analytics. A C++-based simulator is used to model the accelerator.

  • Software-based teaching aid for Signal Processing and Digital Communication

    Delivered an easy-to-use software tool for education support in IoT at Addis Ababa Institute of Technology.

Contact

2260 Hayward St, MI 48109, USA

leulb@umich.edu