NUCLEUS:
In Progress
asdf
Arthur P. Feeney
I am a PhD student in the department of Electrical Engineering and Computer Science at the University of California Irvine. I work at the intersection of high‑performance computing and machine learning, with a focus on building scalable systems for scientific workloads.
My research interests include GPU programming, performance engineering, and machine learning for science. I enjoy designing algorithms and software that make large‑scale problems and data analysis faster, more efficient, and easier to use.
AlloyMoE: GPU Kernels for Mixture of Experts
In Progress
This project is looking at developing performant and memory efficient GPU kernels for MoE modules.
BERN-NN-IBF: Enhancing Neural Network Bound Propagation Through Implicit Bernstein Form and Optimized Tensor Operations
IEEE TCAD 2024
This paper explores methods to perform efficient bounds-propagation on neural networks.
BubbleML: A Multi-Physics Dataset and Benchmarks for Machine Learning
NeurIPS 2023 (Spotlight)
This paper creates a challenging multiphase, multiphysics dataset for PDE Surrogates and does analysis of current limitations.
Mosaic Flows
Supercomputing '23
This paper extended Mosaic Flows to scale training and inference to distributed GPUs. This greatly improved the training time.