Heterogeneous Computing

Contact Information
Heterogeneous Computing

Gregory Diamos

Resume (CV) : January, 2014


I am currently working full time for Baidu's Silicon Valley AI Lab.


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.


Research Bio

Gregory Diamos is a Senior Researcher at Baidu's Silicon Valley AI Lab under the direction of Professor Andrew Ng, where he is exploring the design of deep neural network algorithms and their mapping onto high performance computing systems. Before joining Baidu, he contributed to the development of new compilation, processor architecture, and systems software technologies for the Pascal and Volta GPUs at NVIDIA.

Gregory is a 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 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 processors, systems software, 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, machine and statistical learning onto these models.