Availability

I am currently working full time for NVIDIA Research.

Consulting

I am available for part-time consulting on topics related to computer architecture, high performance computing, accelerator platforms, and CUDA/OpenCL development. Email me for details.

Faculty Position Search

I am currently open to faculty positions with universities that emphasize using fundamental research to drive new discoveries and education in fields related to parallel and heterogeneous computer architecture as well as dynamic compilation for such systems. In particular, I would like to explore the implications of new technologies expected to be available in the 2020-2025 timeframe on architecture, compilers, and execution models. I will give preference to full time faculty positions in the California Bay Area. However, I am open to any offers.

Bio

Research Bio

Saturday, November 5th, 2011

Gregory Diamos is a recent Ph.D. graduate of the Computer Architecture and Systems Lab at the Georgia Institute of Technology, where he studied under the direction of Professor Sudhakar Yalamanchili. He is currently a Research Scientist at NVIDIA, where he is exploring the design of highly power efficient parallel processors and programming systems for such processors. He received his B.S., M.S., and Ph.D. in Electrical Engineering from the Georgia Institute of Technology in 2006, 2008, and 2011 respectively, where he focused on architecture techniques for controlling PVT variations, runtime scheduling techniques, and dynamic compilation for heterogeneous processors.

His current research interests seek to create an industry shift from sequential and irregular parallel computing models to structured and hierarchical parallel models, which have the potential to provide forward scalability as Moores Law continues. His research is directed toward designing microarchitectures, runtimes, and compilers that leverage the structured properties of hierarchical models to improve efficiency. He is also interested in discovering new mappings of highly unstructured algorithms from important problem domains such as graph partitioning, scheduling, finite automata, and relational algebra onto these models.