CARLSBAD, Calif., July 16, 2021 – Building on the successes of past collaborations with the San Diego Supercomputer Center (SDSC) located at UC San Diego, GigaIO, the creators of next-generation architecture across the data center for artificial intelligence (AI) and high performance computing (HPC) solutions, is proud to announce that its universal low latency dynamic fabric, FabreX, has been selected as the technology of choice for the new platform of national prototype research (NRP). This National Science Foundation-funded cyber infrastructure ecosystem is an innovative all-in-one system (computing resources, research and education networks, advanced computing devices and other instruments) designed as a test bed to accelerate science and enable transformative discoveries.
âComplex computational and data workflows underlie many of the scientific research challenges we hope to address with the NRP,â says Dr. Frank WÃ¼rthwein, NRP CEO and Acting Director of the San Diego Supercomputer Center . âIn areas as diverse as public health, high energy physics and wildfire response, this research requires us to aggregate disparate computational elements, such as FPGAs, GPUs, x86 processors and systems. storage in highly usable and reconfigurable systems. GigaIO’s FabreX technology dynamically brings these elements together in a high-performance, ultra-low latency interconnect, while allowing separate, interference-free workflows to coexist on the same infrastructure.
For this one-of-a-kind resource, NSF provided SDSC $ 5 million over five years, with matching funding for the operation of the systems. The award will support hardware and deployment at three facilities: on the east coast at the Massachusetts Green High Performance Computing Center (MGHPCC) in Mount Holyoke, MA; in the Midwest at the University of Nebraska-Lincoln (UNL) and on the West Coast at SDSC, as well as five data caches in the Internet backbone2.
GigaIO will contribute to the ability to disaggregate and compose the various components of the HPC subsystem, including a mix of Field Programmable Door Array (FPGA) units, Graphics Processing Units (GPUs) with memory and storage , all connected with its fully integrated system with very low latency. Fabric. With the ability to connect resources across entire racks exclusively in the native language they all âspeakâ, PCIe, GigaIO makes otherwise impossible configurations achievable for scientific experimentation.
“We are delighted that this award recognizes FabreX technology as the composable platform of choice to accelerate the deployment of science in cutting-edge research centers, ultimately leading to its adoption in scientific institutions across the country,” said Alan Benjamin, CEO of GigaIO.
The fundamentally open nature of the GigaIO platform, with standard software orchestration options and open standard Redfish APIs, unlike proprietary composable solutions from other vendors, complements the aspirations of the new research platform as a open system for scientists nationwide. âThe NRP provides resources and capacities for various sciences, as well as the expertise of systems specialists and the user community,â said WÃ¼rthwein. âIt is an open system designed for growth and inclusion, a way for academic institutions to join a national system and, through their participation, to expand and enrich the HPC ecosystem. “
GigaIO’s broader mission is to democratize access to AI and HPC resources by enabling the sharing of expensive computing resources previously trapped and stuck in static data center infrastructure. The wider impact of the PNR reinforces this objective by focusing on four themes: 1) empowering under-represented and / or under-funded researchers by making them âco-ownersâ of the PNR, through the âBring Your Own Resourceâ program ( BYOR) / Bring Your Own Device Program (BYOD) â; 2) the well-being of society, focusing on health and disaster response; 3) STEM education, workforce development and awareness; and 4) improving industrial competitiveness.
“Any campus in the continental United States can be accessed from some of the NRP hardware within about 500 miles,” said Thomas De Fanti, professor emeritus of computer science at the University of Illinois in Chicago and researcher at the Qualcomm Institute at UC San Diego. GigaIO’s FabreX has gained ground in some of these same institutions such as universities, national laboratories and advanced computing centers.
The system deployment will take place at SDSC on the UC San Diego campus, where several science pilots from astrophysics, molecular dynamics, health sciences and more will participate. For example, National Center for Microscopy and Imaging Research Director Mark Ellisman will examine how NRP can enhance NCMIR’s work with NSF and other agencies to create multi-scale wiring models of the brain and the molecular components that make that brain cells are the most energetic. – Known effective information mediators.
âThe success of this project will allow for greater alignment with other key NSF initiatives, such as NeuroNex2,â Ellisman noted, referring to the technology-based and team-based neuroscience project, for which he is the head of group.
Of particular interest to GigaIO’s home state of California, the PNR will also support forest fire science research. SDSC’s director of data science, Ilkay Altintas, for example, is working with researchers to create tools and techniques like WIFIRE for firefighters. The PNR will provide urgent IT resources in support of fire perimeter forecasts that can be used in the field by fire managers to identify where to most effectively deploy firefighting resources to achieve containment of fire. ‘fire.
GigaIO invented a modular, cloud-class universal dynamic infrastructure framework, allowing users to accelerate workloads on demand, using industry-standard PCI Express / soon CXL technology. The company’s patented network technology optimizes the performance of clusters and rack systems and dramatically lowers the total cost of ownership. With the innovative open architecture GigaIO FabreX, data centers can increase or increase the performance of their systems, allowing their existing investment to adapt to changing workloads and business over time. For more information, visit www.gigaio.com.