OSS GPU Appliances and Expansion Systems

OSS GPU Appliances and Expansion Systems

GPU appliances are high-density, fully integrated computer clusters that are purpose-built for HPC applications. GPU expansion systems add hundreds or thousands of cores to existing servers. GPU appliances and expansion systems come in various densities with anywhere from one to 128 GPUs. GPU appliances and expansion systems are purpose-built for HPC applications.

3U SXM2 Compute Accelerator

With up to four PCI-SIG PCIe Cable 3.0 compliant links to the host server up to 100m away, the SCA8000 supports a flexible upgrade path for new and existing datacenters with the power of NVLink without upgrading server infrastructure. With advanced, independent IPMI system monitoring and full featured SNMP interface not available in any other GPU accelerator with NVLink, the SCA8000 fits seamlessly into any size datacenter.

LEARN MORE

GPUltima

The GPUltima is a petaflop computational cluster in a rack that contains up to eight nodes with each node containing up to 16 accelerators and one or two dual-socket servers. Customers can build up to the full rack, one node at a time, depending on their application requirements. Multiple nodes provide different performance capabilities, dependent on the number accelerators employed. All NVIDIA accelerators exchange data through Infiniband 100Gb transfers using GPU Direct RDMA. All GPUs are connected to a root complex through up to four 128Gb PCI Express connections. Root complexes are connected to the GPUs through Infiniband and each other and the outside world through Ethernet.

Learn More

4U Value GPU Accelerator System

The 4UV supports 2 PCIe 3.0 x16 host connections to 10 PCIe 3.0 x16 slots with two 1m cables to the host server. The system supports 8 double width GPUs or 10 single slot GPUs or add-in boards. Two fan choices allow for high-power GPU cooling up to 300W per GPU or a set-and-forget manual speed control using PWM fans when lower power GPUs or add-in cards are used. Two 2000W power supplies provide up to 4000W of usable power to the GPU accelerator system.

LEARN MORE

1U Compute Accelerators

Pre-installed with one or two NVIDIA Tesla GPUs, Intel Xeon Phi Coprocessors or AMD FirePro S9170 GPUs and connects to the host server through PCIe x16 Gen3 connection.

WITH NVIDIA TESLA WITH AMD WITH NVIDIA QUADRO

2U Compute Accelerators

Pre-installed with four NVIDIA Tesla GPUs, Intel Xeon Phi Coprocessors or AMD FirePro S9170 GPUs and connects to the host server through PCIe x16 Gen3 connection.

WITH NVIDIA TESLA WITH AMD WITH GEFORCE WITH NVIDIA QUADRO

3U Compute Accelerators

Pre-installed with sixteen NVIDIA Tesla GPUs, Intel Xeon Phi Coprocessors or AMD FirePro S9170 GPUs and connects to the host server through PCIe x16 Gen3 connection.

WITH NVIDIA TESLA WITH AMD WITH NALLATECH FPGAS WITH NVIDIA QUADRO

DOWNLOAD 3U COMPUTE ACCELERATOR BROCHURE

4U Compute Accelerators

Pre-installed with sixteen GEFORCE GTX 1080 GPUs and connects to the host server through PCIe x16 Gen3 connection.

WITH GEFORCE

GPU Accelerated Servers

The OSS-PASCAL4 and OSS-PASCAL8 are purpose-built for deep learning applications with fully integrated hardware and software. The OSS-PASCAL 8 is a 170 TeraFLOP engine with 80GB/s NVLink for the largest deep learning models. The OSS-PASCAL4 provides 21.2 TeraFLOPS of double precision performance with an 80GB/s GPU peer-to-peer NVLink. These systems are tuned for out-of-the-box operation and quick and easy deployment.

Learn More

Express Box 3600

ExpressBox 3600 provides the optimum features for supporting world class High Performance Computing (HPC) applications that demand ‘mission critical’ features such as N+1 redundant power and cooling and high speed PCIe Gen 3 x16 connectivity. The EB3600 is ideal for running applications on multiple GPUs.

ExpressBox 3600-10

ExpressBox 3450

The ExpressBox 3450 is the perfect chassis for accelerating workstations and servers with GPUs in size restricted applications. Compact and powerful, the EB3450 can house four double-wide GPUs with an additional single-wide slot for other peripherals.

Learn More