GigaIO’s New 32 GPU AI Supercomputer Unveiled

Largest CFD simulations ever for the Concorde, flying for one second at 300km/h (186 m/h), using 40 billion cells of resolution

GigaIO, the computer hardware company staking it’s claim on the emerging AI markets with new configuration possibilities like the Composable Disaggregated Infrastructure (CDI), has achieved new supercomputing heights with the first ever 32 GPU single-node supercomputer. Headquartered in Carlsbad, California, GigaIO democratizes AI and HPC (High Performance Computing) architectures by delivering the elasticity of the cloud at a fraction of the TCO (Total Cost of Ownership). Essentially, compiling resources into shared pools to create high power computing and storage for data centers at a fraction of the cost.

In September of 2021 a press release indicated that they had raised $14.7 Mn in Series B funding through Impact Venture Capital. Now, they’re making good on their claim of being the “Leader in Next-Generation Architecture for Artificial Intelligence and High-Performance Computing”.

The company configured 32 AMD Instinct MI210 accelerators to a single server utilizing the company’s transformative FabreX ultra-low latency PCIe memory fabric. Available today, the 32-GPU engineered solution, called SuperNODE, offers a simplified system capable of scaling multiple accelerator technologies such as GPUs and FPGAs without the latency, cost, and power overhead required for multi-CPU systems.

Dr. Moritz Lehmann, a German physicist, was able to test FluidX3D on GigaIO SuperNODE and the results of a Computational Fluid Dynamics (CFD) simulation can be found on YouTube. A 40 billion cell simulation of the Concorde supersonic plane.

“AMD collaborates with startup innovators like GigaIO in order to bring unique solutions to the evolving workload demands of AI and HPC,” said Andrew Dieckmann, corporate vice president and general manager, Data Center and Accelerated Processing, AMD. “The SuperNODE system created by GigaIO and powered by AMD Instinct accelerators offers compelling TCO for both traditional HPC and generative AI workloads.”

With the emerging artificial intelligence market on the horizon, scalable integration and optimization are concepts that are attracting speculative investors who want to get in on the ground floor of these burgeoning technologies.