Zhengji Zhao

Zhengji Zhao is an HPC Architect and Performance Engineer at NERSC's Advanced Technologies Group (ATG). Before joining ATG, she was an HPC consultant at NERSC (2007 - 2022). She has broad experience in HPC, including supporting materials science and chemistry applications, participating in system procurements, developing workload analysis tools, and porting applications to many core and GPU systems using parallel programming models such as MPI, OpenMP, OpenACC, and CUDA Fortran. In recent years, she has worked on bringing transparent checkpoint capabilities to NERSC’s production workloads and developing checkpoint/restart standards for HPC production workloads. Her current research is focused on power analysis and benchmarking for NERSC future system procurements. Her publications include the work of developing the reduced density matrix (RDM) method for electronic structure calculations, a highly accurate alternative to the wavefunction-based computational chemistry methods, the award-winning development work of the linear scaling 3D fragment (LS3DF) method for large-scale electronic structure calculations (the best poster award in SC07, and the ACM Gordon Bell prize for Algorithm Innovation in SC08). In addition, she has served on the program committee for several HPC conference series, such as SC, CUG, WACCPD, IXPUG, and Future Computing, and as the lead organizer for the workshop series on checkpointing (e.g., SuperCheck-SC22). She received her Ph.D. in computational physics and an M.S. in computer science from New York University, NY, USA; an M.S. in theoretical physics from Peking University, Beijing, China; and a B.S. in theoretical physics from Jilin University, Changchun, China. Before coming to the US, she was a faculty member at Peking University, teaching classical and modern physics to undergraduates majoring in physics and chemistry (1991 - 1996). Honors and Awards - WACCPD19 Best Paper Award (with Hongzhang Shan and Marcus Wagner) - SC08 ACM Gordon Bell Prize for Algorithm Innovation (with Lin-Wang Wang, Byounghak Lee, Hongzhang Shan, Juan Meza,… more authors » - SC07 Best Poster Award (with Lin-Wang Wang and Juan Meza)