GigaIO SuperNODE™

The World’s First 32 GPU Single-node AI Supercomputer for Next-Gen AI and Accelerated Computing

A New Era of Disaggregated Computing

Technologies that reduce the number of required node-to-accelerator data communications are crucial to providing the stripped-down horsepower necessary for a robust AI infrastructure.

The GigaIO SuperNODE can connect up to 32 AMD or NVIDIA GPUs to a single node at the same latency and performance as if they were physically located inside the server box. The power of all these accelerators, seamlessly connected by GigaIO’s transformative PCIe memory fabric, FabreX, can now be harnessed to drastically speed up time to results.

The SuperNODE is 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.

“This is an incredible platform for HPC and ML/AI. It is really wild to see 32 GPUs appear on ROCm SMI!”

Nick Malaya
AMD Fellow, HPC

“As AI workloads become more broadly adopted, systems that offer the ability to harness the compute power of multiple GPUs and better manage data saturation at ultra-low latency are essential. And as large language model applications drive demand for more GPU performance, technologies that work to minimize node-to-accelerator traffic are better positioned to provide the necessary performance for a robust AI infrastructure.”

Mark Nossokoff
Research Director

“AMD collaborates with startup innovators like GigaIO in order to bring unique solutions to the evolving workload demands of AI and HPC. The SuperNODE system created by GigaIO and powered by AMD Instinct accelerators offers compelling TCO for both traditional HPC and generative AI workloads.”

Andrew Dieckmann
Corporate Vice President and General Manager,
Data Center and Accelerated Processing

The Challenges Our Customers Tell Us We Solve:

We Significantly Shorten Their LLM Development Time
Developers can focus on model creation without the hassle of scaling across multiple servers, speeding up the deployment of LLMs. “It’s EASY to scale with GigalO!”
By Breaking the 8 GPU Server Limit
We overcome traditional limitations by providing a seamless, scalable computing environment, free from the complexities and high costs of InfiniBand.
We deliver leadership price-performance
Cost-effective, high-performance Al computing, making advanced technology more accessible and more profitable.
We are Ready for Immediate Deployment
Our solution is available now, allowing clients to leverage these benefits without delay.

AMD_BrightTalk_Webinar_Screenshot_042024

See For Yourself

AI Benchmarks

GigaIO SuperNODE Testing, LLaMA 7b Training Runtime Compared on a single node

GigaIO SuperNODE Testing, ResNet50 Performance on a Single Node

gigaio_benchmarks_dl-training-gpt-neox_1_sm

gigaio_benchmarks_dl-training-gpt-neox_2_sm

Check Out The Test Results

SuperNODE In the News

GigaIO’s SuperNODE to Power TensorWave Deployment with AMD MI300X

GigaIO Secures Largest Order for SuperNODE Featuring AMD Instinct MI300X Accelerators

GigaIO Reveals Latest Breakthrough in Single-Node GPU Power

Building Impossible Servers with GigaIO

Crafting A DGX-Alike AI Server Out Of AMD GPUs And PCI Switches

GigaIO’s New SuperNode Takes-off with Record Breaking AMD GPU Performance

One of the most difficult problems of computational fluid dynamics: Concorde during landing [video]

It only takes 32 AMD GPUs and 33 hours to run a 40 billion cell simulation of the Concorde supersonic plane

32 AMD MI210 GPUs Render Massive Simulation; 33 Hours for One Second of Concorde Landing

Así fue la mayor simulación aerodinámica: el Concorde, 32 GPU AMD y 33 horas de trabajo ¡para 1 segundo!

Mit 32 AMD-GPUs: GPU-Server erstellt sehenswerte Strömungssimulation der legendären Concorde

Simulating the Concorde Supersonic Plane: A GPU-Powered Marvel

GigaIO introduces single-node AI supercomputer

GigaIO Introduces 32 GPU Single-Node Supercomputer

GigaIO Unveils 32 GPU Single-Node Supercomputer

GigaIO Unveils SuperNODE: A Powerful 32-GPU Engineered Solution

Made Possible by FabreX

The GigaIO SuperNODE is powered by FabreX, GigaIO’s transformative high-performance AI memory fabric. In addition to enabling unprecedented device-to-node configurations, FabreX is also unique in making possible node-to-node and device-to-device communication across the same high-performance PCIe memory fabric. FabreX can span multiple servers and multiple racks to scale up single-server systems and scale out multi-server systems, all unified via the FabreX software.

Resources normally located inside of a server — including accelerators such as GPUs and FPGAs, storage, and even memory — can now be pooled in accelerator or storage enclosures, where they are available to all of the servers in the system. These resources and servers continue to communicate over the FabreX native PCIe memory fabric for the lowest possible latency and highest possible bandwidth performance, just as they would if they were still plugged into the server motherboard.

AI and Accelerated Computing Challenges
Large Language Model (LLMs) and Generative AI need large numbers of GPUs

Standard server configurations restrict GPUs to what fits inside the server sheet metal

Fixed server architectures result in lower utilization rates of expensive and hard to come by accelerators

Networking fixed configuration GPU servers over legacy networks increases latency thus reducing performance
The Solution: GigaIO SuperNODE
GigaIO SuperNODE™ with FabreX™ Dynamic Memory Fabric

Connects up to 32 AMD Instinct™ MI210 GPUs or 24 NVIDIA A100s and up to 1PB storage to a single off-the-shelf server

Enables lower power, adaptive GPU supercomputing

Delivers the ability to train large models with tools like PyTorch or TensorFlow, scaling via peer-to-peer communication on a single node, instead of MPI over several nodes

Accelerators can be split over several servers, and scale using node-to-node communication for larger data sets
Benefits of GigaIO SuperNODE
Shorten time-to-results with single-node code getting vastly more compute power

Keep code simple: use your existing software without any changes – “It just works”

Secure the ultimate flexibility for any workload: unprecedented power in “BEAST mode,” flexible configurations in “SWARM mode,” or shared resources in “FREESTYLE mode

A single node solution reduces network overhead, cost, latency, and server administration

Save on power consumption (7KW per 32-GPU deployment)

Save on rack space (30% per 32-GPU deployment)

Unprecedented Compute Capability Available Now

Available today for emerging AI and accelerated computing workloads, the SuperNODE engineered solution, part of the GigaPod family, offers both unprecedented accelerated computing power when you need it, and the ultimate in flexibility and in accelerator utilization when your workloads only require a few GPUs.

What will YOU discover?

Resources

SuperNODE – MI300X
Data Sheet