For almost two decades, GPUs (Graphics Processing Units) have been steadily revolutionizing high-performance computing (HPC) and AI. Originally designed for graphics-intensive applications such as gaming and image processing, it didn't take long for HPC professionals to see the potential of low-cost, massively parallel processors able to handle then billions (and now trillions) of floating-point operations per second. In this two-part article, I'll discuss GPU workloads and how they are managed with Univa Grid Engine. First, I'll provide a short primer on GPUs, explain how they are used in HPC and AI, and cover some of the specific challenges when running GPU applications on shared clusters. In part II, I'll focus on some of the specific innovations in Univa Grid Engine that help make GPU applications much easier to deploy and manage at scale.

The Information Sciences Institute (ISI) is a unit of the University of Southern California's highly ranked Viterbi School of Engineering. ISI is one of the nation's largest, most successful university-affiliated computer research institutes. The Video, Image, Speech and Text Analytics (VISTA) group at ISI has spent the past three years advancing the state of research for facial recognition, a technology with significant implications for security and commerce. In order to conduct this research, "We needed a reliable, powerful workload management platform that would enhance performance and have the ability to run complex, diverse workloads across multiple users within the entire ISI organization," said Stephen Rawls, programmer and research analyst. VISTA selected Univa Grid Engine and cites key contributing factors over other vendors: built-in advanced GPU support, detailed documentation, ongoing product upgrades and customer support.

Queen Mary University of London (QMUL) is globally recognized for pushing the boundaries of research and Innovation. Queen Mary's high-performance computing cluster supports a student and research community of over 2,000 users in all disciplines, such as Astronomy, Computational Chemistry, Bioinformatics, Computer Science & Machine Learning, Engineering, Mathematics and Statistics, and Clinical Research. The HPC cluster comprises 5,000 InfiniBand-interconnected cores and 2PB high-performance storage running hundreds of commercial and open-source applications of various types, such as Gaussian, MATLAB, Ansys, Stata, genomics applications, plus Tensorflow for GPUs in singularity containers. QUML's aged job scheduler was running subpar and impacting users who could not run their preferred software like Tensorflow on nVidia Tesla K80 GPUs. Recently having eliminated upgrade offerings that were cost-prohibitive, migration-intensive, lacked support or large installed bases, QMUL selected Univa Grid Engine for its rich features, high performance, large installed base (including universities), expert support, and easiest upgrade path.