The Institute for Digital Research and Education (IDRE) is a cooperative of faculty and technologists working to advance the existing body of computing knowledge and expertise at UCLA. An interdisciplinary research institute with an emphasis on the integration of high performance computing, applied algorithmic research and development, computer science, and informatics, IDRE is central to UCLA’s data science initiatives. 

The IDRE mission is to lead a campus-wide effort on innovative research and education on the use and development of advanced cyberinfrastructure methods, tools, and services. This involves bringing together researchers working in domain, computational, data, and information sciences, and digital scholarship and creative activities. IDRE’s vision is to sustain UCLA as a world leader in the innovative use, application, and development of computational, data, and information sciences, and digital technologies that drive cultural and societal change. IDRE supports research and innovative scholarship that takes advantage of new technologies and encourages collaboration between faculty from different departments and disciplines at UCLA, the opening of new research questions, and the enrichment of the learning environment. The goal of this campus-wide collective is to make UCLA a world leader in high-performance computing and visualization research and education. 

IDRE programs are focused on the challenges and opportunities associated with four areas critical to advancing innovative research and scholarship: Computational Science, Data Science, Information Science, and Digital Scholarship and Creative Activities. Through the IDRE Research Technology Group (RTG), IDRE provides services and support aligned with the four program areas. IDRE’s unique computational capability includes High Performance Computing resources and expertise, Grid and Cloud Access Services, Cluster Services, the Grid Portal, and UCLA’s data center system.

For more information, please visit the IDRE site.

High-Performance Computing
UCLA has a longstanding commitment to enabling high-performance computing (HPC) for the campus. For general (non-PHI) usage, the UCLA Institute for Digital Research and Education (IDRE) supports scientific computing, providing expertise in multicore/GPU programming; code optimization for using HPC resources and code clinics; scaling and analysis of parallel code; optimization of serial codes; efficient serial and/or parallel algorithms use; parallelization or porting on different platforms; debugging; profiling; scientific visualization with large datasets; and grid computing. IDRE’s staff provides domain-specific support to facilitate computational and data-specific requirements to ensure smooth integration with existing campus resources. IDRE is responsible for maintaining the campus research cyber-infrastructure, including the shared Hoffman2 Cluster, consisting of 1,347 nodes (22,804 64-bit cores, 50TB RAM) with an Ethernet network and Infiniband interconnect, capable of 150 TFLOPS (>200 with GPUs). Hoffman2 is the largest and most powerful cluster in the UC system. The cluster is also an endpoint on the Globus Online service using a 10Gb network interconnected backbone, thus providing researchers a facility for fast and reliable data movement between Hoffman2 and most leadership-class facilities across the United States. Notably, Drs. Douglas Bell and Alex Bui serve on IDRE’s Executive Committee, ensuring close linkage between the campus and CTSI. For sensitive (PHI) data requiring restricted access, UCLA Health has set up an HPC equivalent framework in the Microsoft Azure cloud through the Hoffman2 and Dawson 2 computing clusters.

Hoffman2 Computing Cluster
Hoffman2 Computing Cluster is a project of the Institute for Digital Research and Education (IDRE) Cluster Hosting Program and is managed and operated by the IDRE Research Technology Group. UCLA’s Shared Hoffman2 Cluster has 1300+ 64-bit nodes and over 21,000 cores with an arrangement of over 50TB of memory. Each node has 1GB Ethernet network and a DDR, QDR, FDR, or EDR Infiniband interconnect. The cluster includes a job scheduler, compilers for C, C++, Fortran 77, 90 and 95 on the current Shared Cluster architecture, applications and software libraries that offer languages, compilers and software specific to Chemistry, Chemical Engineering, Engineering, Mathematics, Visualization, Programming and an array of miscellaneous software. Hoffman2 is currently the largest and most powerful shared cluster in the University of California system. 

Additional Hoffman2 resources for researchers include complete system administration for contributed cores, cluster access through dual, redundant 10Gb network interconnects to the campus backbone, the capability to run large parallel jobs that can take advantage of the cluster’s InfiniBand interconnect, and web access to the Hoffman2 Cluster through the UCLA Grid Portal, as well as access to a Panasas parallel file system and a NetApp storage system. Current HPC storage capacity is 2.5 petabytes augmented by 250TB of flash-based storage for home and scratch directories and over 2PB of backup storage.

The cluster is also an end point on the Globus Online service using the 100GB network interconnect backbone, thus providing researchers a facility for fast and reliable data movement between Hoffman2 and most leadership class facilities across the USA.

For more information, please see the Hoffman2 system overview.

Last updated
December 5, 2023