Dedicated GPU Servers

GPUs = Intensive computing power to speed up parallel task processing

GPU Servers Provide Faster Processing for Complex Computations

GPU Servers

Resource-intensive applications with a large number of parallel tasks — such as image processing, bioinformatics, and big data — typically run very slowly on a conventional CPU. A graphical processing unit (GPU) processes the same tasks more rapidly, thanks to its massive parallel architecture. While originally designed to handle computation only for computer graphics, GPUs have since been adapted with programming languages, such as CUDA, to perform computations in all types of applications.

See plans

Solving Today’s Complex Challenges with the Power of NVIDIA Tesla P100 GPUs

Video Encoding

Video Encoding

Accelerate video encoding by processing parallel workloads.

3D Rendering

3D Rendering

Generate your animations and images by harnessing the GPU’s computing power.

App Testing and Development

App Testing and Development

Leverage the GPU’s computing power to develop and test your CUDA or OpenCL applications.

Virtual Desktop Infrastructure

Virtual Desktop Infrastructure

Combine NVIDIA technology with market-leading hypervisors to build high-performance virtual desktop infrastructures (VDIs).

Cloud 3D

Cloud 3D

Provide your architects and designers with remote workstations for their 3D applications.

Cloud Gaming

Cloud Gaming

Outsource GPU hosting to the cloud for resource-intensive applications, such as online games.

NVIDIA Tesla P100 M60 GPU

Tesla P100 for PCIe enables mixed-workload HPC data centers to realize a dramatic jump in throughput while saving money. For example, a single GPU-accelerated node powered by four Tesla P100s interconnected with PCIe replaces up to 32 commodity CPU nodes for a variety of applications. Completing all the jobs with far fewer powerful nodes means that customers can save up to 70% in overall data center costs.

The P100 is compatible with the VMWare ESXi server virtualization platform, Citrix XenServer hypervisor, and KVM infrastructure.

NVIDIA Tesla P100 M60 GPU

Specifically designed for virtualization, the M60 uses NVIDIA GRID technology, which significantly increases performance and speed by enabling up to 32 concurrent users to share graphic card resources. As part of the NVIDIA server range for professionals, the M60 boasts graphics acceleration that will even satisfy your most advanced users.

  • Dual GPU design (Two Maxwell GPUs)
  • 4096 CUDA cores
  • DDR5 16 GB
  • 320 Gbps max bandwidth


The M60 is compatible with the VMWare ESXi server virtualization platform, Citrix XenServer hypervisor, and KVM infrastructure.


Plans

This product will be available soon. Get the latest updates.


Specifications

No setup fees
Network
  • Up to 256 IPs with no monthly fees (excluding setup fees)
  • Free Anti-DDoS protection included
  • 500 Mbps of guaranteed bandwidth
  • 3 Gbps burst
  • vRack available depending on the server
  • Choice of data center
Backup
  • 500 GB of storage space
Software
  • 90 operating systems available for installation via the Control Panel
    See the list of compatible operating systems
Administration
  • Control Panel
  • API
  • Root access to the server
  • Access via the KVM/IP graphic console
Support
  • Hours and contact methods
  • Level 1 incidents (e.g. server unavailable):
    • Intervention Time: 1 hour
    • Repair Time: Intervention + 2
  • Level 2 incidents (e.g. abnormal operation, software config problems)
    • Intervention Time: 12 hours
Service-Level Agreement (SLA)
  •  Network Availability: 99.95%

Ready to get Started?

Call to discuss your cloud needs with an OVH expert.
You can also chat with us… or, buy our available products.

Products