Jinho is a senior deep learning architect on the DLSIM team at NVIDIA. He is working on performance modeling and analysis of deep learning workloads on NVIDIA accelerators, and contributes to the NVIDIA MLPerf Inference implementation. Before joining NVIDIA, he worked on server CPU and SoC architectures and microarchitectures at Intel and Arm. He has a Ph.D. in computer engineering from University of Southern California with concentration in computer architecture.