Oops! Something went wrong while submitting the form. Make sure you filled out all required fields.
An Arc exclusive, “Simultaneous Multi-Virtual GPU” allows for superior performance and much higher utilization by dynamically allocating resources at run-time, shifting execution capabilities and GPU cores from under-utilized or idle resources.
Arc’s proprietary hypervisor stack was developed to allow users unparalleled control over the GPUs in their system. This stack is in constant development to continue innovation in GPU virtualization and is an ideal solution for training large workloads (artificial intelligence, machine, learning, deep learning).
Thanks to our unique ability to utilize the efficiencies of "Simultaneous Multi-Virtual GPU" we're able to train heavy workloads much faster than the standard straight pass through approach. Training a NeRF-SH neural network model took the industry standard configuration 9h 15m 11s with four Nvidia A100-SXM4 (40 GM) GPUs. It took our exclusive configuration only 8h 27m 34s with four ARC A100 (40 GB) GPUs, thanks to our hypervisor stack, Hyperborea™.
On-Premises or In the Cloud
Hyperborea is utilized in Arc’s GPU cloud service and can also be licensed for your cloud or on-premise environments. It's easily integrated and extremely powerful. Stop relying on legacy software. Gain a competitive advantage by taking your computing to the next level with Arc Compute!
Arc Compute’s hypervisor stack eliminates multiple costly virtualization fees, so you can spend less and charge more. Our cloud providers save 40-50 percent on average, vastly increasing their margins.
Thanks to Hyperborea’s architecture, applications can achieve speeds of up to 200 frames per second, worldwide.
With up to 64 virtual machines per GPU, and support coming for 256+, you can support greater user densities in your cloud deployments.
In addition to enterprise GPUs, Hyperborea supports a wide range of consumer NVIDIA, Intel, and AMD GPUs. Who wants to pay more for the same thing?
Hyperborea supports a wide range of operating systems including Ubuntu, Centos, PopOS, and Windows.
LibVF.IO is Arc Compute’s open source IOMMU parser and VFIO allocation library. Visit libvf.io for more details.
Thule is Arc Compute’s open mediated device driver, which we call the “nouveau of mdev drivers”. Thule supports AMD, NVIDIA and Intel hardware.
DDMAM performs host mediated vtg_balloon like API calls, allowing VRAM to be allocated at run-time, using hardware enforced IOMMU to maintain address separation.