no code implementations • 30 Sep 2023 • Cameron Shinn, Collin McCarthy, Saurav Muralidharan, Muhammad Osama, John D. Owens
We achieve this through a novel analytical model for predicting sparse network performance, and validate the predicted speedup using several real-world computer vision architectures pruned across a range of sparsity patterns and degrees.
no code implementations • 19 Jan 2022 • Zhongyi Lin, Louis Feng, Ehsan K. Ardestani, Jaewon Lee, John Lundell, Changkyu Kim, Arun Kejariwal, John D. Owens
We show that our general performance model not only achieves low prediction error on DLRM, which has highly customized configurations and is dominated by multiple factors but also yields comparable accuracy on other compute-bound ML models targeted by most previous methods.
5 code implementations • NeurIPS 2020 • Weitang Liu, XiaoYun Wang, John D. Owens, Yixuan Li
We propose a unified framework for OOD detection that uses an energy score.
no code implementations • 1 Mar 2020 • Leyuan Wang, John D. Owens
In this paper, we propose a GPU-efficient subgraph isomorphism algorithm using the Gunrock graph analytic framework, GSM (Gunrock Subgraph Matching), to compute graph matching on GPUs.
Distributed, Parallel, and Cluster Computing
no code implementations • 21 Nov 2019 • Weitang Liu, Lifeng Wei, James Sharpnack, John D. Owens
In this paper, we propose a novel architecture that iteratively discovers and segments out the objects of a scene based on the image reconstruction quality.
1 code implementation • 4 Aug 2019 • Carl Yang, Aydin Buluc, John D. Owens
In this paper, we examine the performance challenges of a linear-algebra-based approach to building graph frameworks and describe new design principles for overcoming these bottlenecks.
Distributed, Parallel, and Cluster Computing Mathematical Software
1 code implementation • 23 Feb 2019 • Ahmed Abdelkader, Chandrajit L. Bajaj, Mohamed S. Ebeida, Ahmed H. Mahmoud, Scott A. Mitchell, John D. Owens, Ahmad A. Rushdi
The VoroCrust algorithm is the first provably-correct algorithm for conforming polyhedral Voronoi meshing for non-convex and non-manifold domains with guarantees on the quality of both surface and volume elements.
Graphics Computational Geometry I.3.5
no code implementations • 20 May 2018 • Weitang Liu, Emad Barsoum, John D. Owens
Our model can learn and derive the coordinates of the digits better than its convolution counterpart that lacks a routing-by-agreement algorithm, and can also perform well when testing on the multi-digit moving MNIST and KTH datasets.