Weile Wei

HPC Performance Engineer

Phone: +1 510 495 8134

About

Weile Wei is an HPC Performance Engineer at NERSC, where he works on benchmarking runtime systems, researching C++ parallel algorithms, modernizing software engineering practices, and exploring future programming models. Before joining NERSC, he was a Research Scientist at Meta, focusing on software infrastructure performance optimization and scaling. Weile has a Ph.D. in Computer Science from Louisiana State University, where he studied distributed GPU memory optimization, HPX runtime system, performance portabilities, and asynchronous task-based programming.

Publications

Huber, Joseph, Weile Wei, Giorgis Georgakoudis, Johannes Doerfert, and Oscar Hernandez. "A case study of LLVM-based analysis for optimizing SIMD code generation." In OpenMP: Enabling Massive Node-Level Parallelism: 17th International Workshop on OpenMP, IWOMP 2021, Bristol, UK, September 14–16, 2021, Proceedings 17, pp. 142-155. Springer International Publishing, 2021. [Publication | Arxiv]
Wei, Weile, Eduardo D'Azevedo, Kevin Huck, Arghya Chatterjee, Oscar Hernandez, and Hartmut Kaiser. "Memory reduction using a ring abstraction over gpu rdma for distributed quantum monte carlo solver." In Proceedings of the Platform for Advanced Scientific Computing Conference, pp. 1-9. 2021. [Publication | Arxiv]
Wei, Weile, Arghya Chatterjee, Kevin Huck, Oscar Hernandez, and Hartmut Kaiser. "Performance analysis of a quantum Monte Carlo application on multiple hardware architectures using the HPX runtime." In 2020 IEEE/ACM 11th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems (ScalA), pp. 77-84. IEEE, 2020. [Publication | Arxiv]
Kaiser, Hartmut, Patrick Diehl, Adrian S. Lemoine, Bryce Adelstein Lelbach, Parsa Amini, Agustín Berge, John Biddiscombe et al. "Hpx-the c++ standard library for parallelism and concurrency." Journal of Open Source Software 5, no. 53 (2020): 2352. [Publication]