Yuning Xia

I am a PhD student in the Department of Computer Science at Rice University, where I work on HPCToolkit. My PhD advisor is Prof. John Mellor-Crummey.

My research is primarily in high-performance computing. I'm especially interested in how we can build efficient, scalable and robust performance infrastructure that can make it easier to analyze and optimize datacenter scale machine learning systems.

Previously, I worked on DeepSpeed Inference with Prof. Minjia Zhang at UIUC. I have an M.Eng. in Electrical and Computer Engineering from Cornell University, where I was supervised by Prof. Udit Gupta on ML inference optimization. I have a B.Eng. in Software Engineering from Tongji University.

I was a research intern at ByteDance (Summer 2025), working on fast and accurate GPU performance modeling.

Beyond research, I worked at HongShan aka Sequoia Capital China with early-stage founders.

Email  /  GitHub  /  GitLab  /  LinkedIn

Research

I'm interested in distributed systems, systems for machine learning, program analysis and compilers.

Extended Top-Down Performance Analysis of GPU-Accelerated Applications on Intel Ponte Vecchio GPU Architecture

Miscellanea

Design and source code from Jon Barron's website