I am a senior from Shanghaitech U, a leader of GeekPie HPC team, looking for a master position in US. My interesting field consists of HPC, Mlsys, AI+HPC, and AI4Science. Currently, I am working on a AI training job scheduler in HPC, and a new NeRF in cloud rendering envirnment.
I am available for any suitable master/PhD position in US (visa required).
Feb 18, 2023 · 3 min read · Paper Summary This paper provides a portable high-performance symmetric-indefinite linear system solver features OpenMP's innovative dataflow-based task scheduling and Aasen's method to avoid communication. This work is now available as a part of the...
Join discussionFeb 18, 2023 · 1 min read · Paper Summary This study investigates how to use IO500 and the Ellexus Mistral tool to analyze precise performance characteristics in order to tune IO performance on Astra, an ARM-based Sandia machine with an all flash, Lustre-based storage array. Th...
Join discussionFeb 18, 2023 · 2 min read · Paper Summary This work introduces PerfScope, an online performance bug inference tool for production cloud computing systems that does not need source code and consumes very little system resources. This effort may reduce the search scope for bug-re...
Join discussionJan 30, 2023 · 2 min read · Paper Summary This paper presents an algorithm to determinate a global state of a distributed system during the computation where the processors in the system do not share a common clock or memory by taking distributed snapshots. This global state ca...
Join discussionOct 21, 2022 · 2 min read · Google Scholar has been one of the biggest academic search engines, and the personal profile on Google Scholar can easily show the citations, authors, published year, and publication information. But it does not offer an iframe for users to demonstra...
Join discussion