GPU Servers
Performance and flexibility for complex computational applications
Equus offers a wide range of GPU (graphics processing unit) computing platforms that are designed for High Performance Computing (HPC) and massively parallel computing environments. The Equus GPU platforms range from 2 GPUs up to 10 GPUs inside traditional 1U, 2U and 4U rackmount chassis, and a 4U Tower (convertible). Targeted to the right workload, these GPU platforms offer higher performance, reduce the rack space requirements, and lower power consumption when compared to traditional CPU-centric platforms.
G1460
1U 4 GPU Server
- Single Root Architecture
- Supports up to 4 Double Wide GPUs
- Nvidia Tesla V100, P100, P40, K80, M10
- Single Intel® Xeon® Scalable CPU
- Memory expandable to 3 TB
- Two 2.5” Hot-Swap SSD Bays
- Dual 10GbE LAN support
- OpenBMC w/Remote Management via iKVM
G2660
2U 2 GPU Server
- Dual Root Architecture
- Supports up to 2 Double Wide GPUs
- Nvidia Tesla V100, P100/16GB, P40/24GB
- Dual Intel® Xeon® Scalable CPUs
- Memory expandable to 3 TB
- Twelve 2.5”/3.5” Hot-Swap SSD/HDD Bays
- Dual 10GbE LAN support
- OpenBMC w/Remote Management via iKVM
G4560
5 GPU Tower Server
- Dual Root Architecture
- Supports up to 5 Double Wide GPUs
- Nvidia Tesla V100, P100
- Dual Intel® Xeon® Scalable CPUs
- Memory expandable to 1.5 TB
- Eight 2.5”/3.5” Hot-Swap SSD/HDD Bays
- Dual 10GbE LAN support
- OpenBMC w/Remote Management via iKVM
G4660
4U 8 GPU Server
- Dual Root Architecture
- Supports up to 8 Double Wide GPUs
- Nvidia Tesla V100, P100, P40, P4
- Dual Intel® Xeon® Scalable CPUs
- Memory expandable to 3 TB
- Fourteen 2.5” Hot-Swap SSD/HDD Bays
- Dual 10GbE LAN support
- OpenBMC w/Remote Management via iKVM
G4760
4U 10 GPU Server
- Single Root Architecture
- Supports up to 10 Double Wide GPUs
- Nvidia Tesla V100, P100, P4
- Dual Intel® Xeon® Scalable CPUs
- Memory expandable to 3 TB
- Fourteen 2.5” Hot-Swap SSD/HDD Bays
- Dual 10GbE LAN support
- OpenBMC w/Remote Management via iKVM
Supported NVIDIA GPU Cards
The Equus GPU platforms utilize NVIDIA solutions to deliver double-precision performance that is both cost-effective and energy-efficient. With support for NVIDIA Tesla GPUs, the these computing platforms offer the power to solve the most computationally-intensive challenges.
You have GPU sourcing options: you can source and install your own GPUs, consign your GPUs to us for factory installation, or purchase GPUs in a turnkey system.
The Nvidia Tesla GPU cards supported on the various these GPU servers are:
- Nvidia Tesla V100/32GB
- Nvidia Tesla V100/16GB
- Nvidia Tesla P100/12GB
- Nvidia Tesla P40/24GB
- Nvidia Tesla P4
- Nvidia Tesla M10
Get a No-Obligation Consultation.
