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 spans the area of computer architecture, particularly focusing on the acceleration of data-centered applications. I am currently working on addressing the inefficient execution of irregular workloads on GPUs via a custom memory subsystem. Priorly, I have been working on alleviating interconnect traffic bottlenecks in processing-in-memory based graph execution [ISLPED' 19, DATE'20].

Social

Resume

Check out our recent video from the ADA Symposium

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

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

Projects

  • Exploiting Power-Law for Graph Prefetching

    Irregular workloads, particularly graph analytics, benefits less from conventional prefetching mechanisms. In this work, we applied software-based prefetching that targets vertices with significant outgoing edges in power-law graphs (i.e. top 20%). LLVM-based selective insertion of prefetches minimizes unwanted prefetching,thus alleviating cache pollution.

  • Multicast for Scalable Graph Analytics

    In most graph workloads, a source vertex sends out similar vertex-update messages to its neighboring vertices. GraphVine [DATE’20] exploits multicasting to combine similar messages into a multicast packet which alleviates network traffic.

  • Processing in Network Solution for Scalable Graph Analytics

    Commutative and associative reduction operations in graph analytics, allows distributed computation via compute-capable routers. Hence, MessageFusion [ISLPED’19] coalesces vertex-update messages traversing to a same destination so as to reduce overall network traffic.

  • 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