GigaIO Fabrex™: The Highest Performance, Lowest Latency Rack-Scale Network on the PlanetAnand
You just spent a lot on a rack of servers and multiple GPUs to solve your computational problems.
You don’t know it yet, but your GPUs are mostly left untouched even with finely tuned models and servers, so you end up wasting space, energy, and well.. your power bills.
With FabreX, you can now increase utilisation and eliminate over provisioning of resources, which helps reduce cooling expenses. On top of that, you’re also able to save space with fewer power-consuming servers and accelerators for the exact same performance.
You must be wondering…
What is GigaIO™?
GigaIO™ provides Composable Disaggregated Infrastructure solutions, which comes in both hardware and software.
The hardware consists of:
- FabreX Top of Rack (TOR) Switch
256Gb per second with 140 nanosecond port-to-port latency, FabreX™ PCIe Network Delivers Lower Latency and Higher Bandwidth than InfiniBand in one of the test conducted in GigaIO lab.
- FabreX PCIe Gen4 Adapter
GigaIO™ FabreX™ Network Adapter Card enables non-blocking low-latency PCIe Gen4 which gives AI/ML, HPC, and Data Analytics users the flexibility to create exactly the system they need for optimised performance and reduced total cost of ownership.
- Accelerator Pooling Appliance
The GigaIO™ Gen4 Accelerator Pooling Appliance is the industry’s highest performing PCIe accelerator appliance fully supporting PCIe Gen4 with up to 1Tb/sec bandwidth into and out of the box. Support up to 8 double-width PCIe Gen 4.0 x16 accelerator cards with up to 300W delivered to every slot; and 2 PCIe Gen 4.0 x16 low-profile slots.
Besides GPUs, it also supports FPGAs, IPUs, DPUs, thin-NVMe-servers and specialty AI chips.
The software offered:
- FabreX Software
A Linux-based, resource-efficient software layers engine that drives the performance and dynamic composability of GigaIO’s Software-Defined HardwareTM (SDH).
It integrates with Bright Cluster Manager that supports popular HPC workload schedulers such as SLURM, PBS Pro & OpenPBS, LSF, Altair Grid Engine, Kubernetes.
For infrastructure integration it supports Bright Cluster Manager VMware vSphere integration and Supermicro SuperCloud Composer.
What solution does GigaIO™ offer?
Through an all-new architecture, GigaIO™ offers a hyper-performance network that enables a unified, software-driven composable infrastructure.
In other words, GigaIO™ allows CPU, GPU Accelerator, and NVMe drives that are installed in any server or in an external chassis to be shared among multiple servers. As a result, you no longer have to detach drives from the initial physical server to be reinstalled in another server.
Namely, GigaIO™ FabreX enables you to connect 32 GPUs with only 1 server. Not only does this reduce the total cost of ownership (TCO), the infrastructure management is simpler too. Additionally, the low latency interconnection also provides superior performance.
What do we mean by reducing TCO?
By implementing GigaIO solution, you can:
- Spend less to get the same performance and capacity as compared to other solutions.
- Get ROI (Return on Investment) faster because it allows the customer to do exactly the same things but with lower cost. The GigaIO solution enables you to achieve ROI in half the standard time.
- Do more things with GigaIO, for example, GigaIO supports orchestration of ANY Compute, Acceleration (CPUs, GPUs, FPGAs, ASICs), Storage, Memory (3D-XPoint) or Networking resource for any workload using an Enterprise-Class, Easy-To-Use and Open Standards high-performance network.
How does it work?
FabreX is the only fabric which enables complete disaggregation and composition of all the resources in your server rack. Besides composing resources to servers, FabreX can also compose your servers over PCIe (and CXL in the future), without the cost, complexity and latency hit from having to switch to Ethernet or InfiniBand within the rack.
With any workload that needs more than one server and more resources (storage, GPUs, FPGAs, etc.), FabreX is exactly what you need. Typical workloads centre around the use of GPU and FPGA accelerators, including AI/ML/DL, visualisation, High Performance Computing and Data Analytics.
For more use cases visit our solutions page.
In Robust HPC, we use GigaIO’s FabreX universal dynamic fabric to enable true rack-scale computing, breaking the limits of the server box to enable the entire rack the unit of compute.
Resources such as GPU, FGPAs, ASICs and NVMe are connected via low latency FabreX switches (less than 110ns with non-blocking ports) and can be configured in various ways depending on your needs.
Long story short, you get the flexibility and agility of the cloud, but with the security and cost control of your own on-prem infrastructure.
Get in touch with Robust HPC – an authorised reseller of GigaIO in Southeast Asia, to know more about how organisations use GigaIO and find the right use case to address your computing needs.