GPU Accelerated Server Solutions

Bespoke servers for every GPU-accelerated workload

The NVIDIA Ampere family of GPU accelerator cards represents the cutting edge in performance for all workloads, offering unprecedented compute density, performance, and flexibility to deliver up to 5 petaFLOPS performance in a single system. The high-end NVIDIA A100 accelerator is available in either standard PCIe or high-density SXM4 formats featuring HBM2 memory, with the other accelerators available as PCIe cards. Any of these Ampere passively cooled GPUs offer the flexibility to be installed in a wide variety of both air and liquid cooled server chassis.

The 3XS Server Philosophy

Specification

3XS GPU-accelerated servers are tailored to the applications you will be running, providing optimal performance, and can be customised with your branding.

Service

We provide a one-stop-shop for all your server needs - offering seamless support during build, after-sales and with our professional services offering.

Satisfaction

We are proud to say a large proportion of our GPU-accelerated server customers come back to us for upgrades and new builds.

GPU Servers versus CPU Servers

The main difference between CPU and GPU architecture is that a CPU is designed to handle a wide-range of tasks quickly, but is limited in the number of tasks that can be run in parallel. A GPU is designed to quickly render high-resolution images and video concurrently, performing multiple parallel operations, so are ideally suited for non-graphical tasks such as scientific computation. Incorporating thousands of processor cores running simultaneously, GPUs enable massive parallelism where each core is focused on making efficient calculations.

The addition of GPU cards into a server not only revolutionises its performance when it comes to parallel computing tasks such as HPC, supercomputing or AI - but GPU technology also allows for far denser server deployments, saving power and cooling costs. A single GPU-accelerated server can do the parallel workload of many CPU servers.

NVIDIA GPU Accelerators

The NVIDIA Ampere family of GPU accelerator cards represents the cutting edge in performance for all AI workloads, offering unprecedented compute density, performance, and flexibility to deliver up to 5 petaFLOPS AI performance in a single system. The high-end NVIDIA A100 accelerator is available in either standard PCIe or high-density SXM4 formats featuring HBM2 memory, with the mid-range A30 accelerator available as a PCIe card. Any of these Ampere passively cooled GPUs offer the flexibility to be installed in a wide variety of both air and liquid cooled server chassis.

NVIDIA HGX Server		NVIDIA EGX Server
8x A100 SXM4	4x A100 SXM4	A100 PCIe Gen 4	A40 PCIe Gen 4	A30 PCIe Gen 4	A16 PCIe Gen 4

The Ampere Advantage

The NVIDIA Ampere GPU architecture, designed for the age of elastic computing, delivers the next giant leap by providing unmatched acceleration at every scale. When compared to previous generations of server GPUs the A100 and A30 outperform them significantly due to the increased CUDA core count, additional memory and next generation PCIe bus.

New Sparsity Acceleration

Modern AI networks are big and getting bigger, with millions and in some cases billions of parameters. Not all of these parameters are needed for accurate predictions and inference, and some can be converted to zeros to make the models sparse without compromising accuracy. Tensor Cores in A100 can provide up to 2x higher performance for sparse models. While the sparsity feature more readily benefits AI inference, it can also be used to improve the performance of model training.

Multi-Instance GPU

Multi-Instance GPU (MIG) expands the performance and value of each NVIDIA A100 GPU. MIG can partition the A100 GPU into as many as seven instances, each fully isolated with their own high-bandwidth memory, cache, and compute cores. Now administrators can support every workload, from the smallest to the largest, offering a right-sized GPU with guaranteed quality of service (QoS) for every job, optimising utilisation and extending the reach of accelerated computing resources to every user.

3rd Gen NVLink and NVSwitch

Scaling applications across multiple GPUs requires extremely fast movement of data. The third generation of NVIDIA NVLink in A100 doubles the GPU-to-GPU direct bandwidth to 600GB/s, almost 20x more than PCI-E 4.0. When paired with the latest generation of NVIDIA NVSwitch, all GPUs in the server can communicate with each other at full NVLink speed for incredibly fast training.

Scan Cloud Virtual GPU Solutions

Scan Cloud can deliver a virtualised GPU private services including those from NVIDIA platforms to any device, anywhere. These include RTX Virtual Workstation (vWS), Virtual PC (vPC) and Virtual Compute Server (vCS) to harness the power of high performance applications for content creation, design, analytics and data science. The Scan Cloud team can advise on licensing needs, hardware requirements and the deployment of your cloud solution. Alternatively Scan Cloud also offers a number of public cloud services via subscription where no physical infrastructure is needed.

FIND OUT MORE

Server platforms

AMD EPYC CPUs

The AMD EPYC 7003 Series of processors set the new standard for the modern datacentre. Featuring leadership architecture, performance, and security, the third generation AMD EPYC processors help customers turbocharge their application performance, transform their datacentre operations, and help secure their critical data. Based on AMD Zen 3 Architecture, they feature 7nm hybrid-multi-die design and offering up to 64-cores, PCIe Gen4 and 32MB of L3 cache per core. The AMD EPYC 7002 Series continues to offer many of these features, but using the Zen 2 architecture to deliver more cost effective solutions.

FIND OUT MORE

Intel Xeon Scalable CPUs

The latest 3rd Gen Intel Xeon Scalable Platform processor architecture is designed to optimise interconnectivity with a focus on speed, without compromising data security. Features such as up to 40-cores, 64 lanes of PCIe 4.0 and Intel Advanced Vector Extension 512 (Intel AVX-512) improve with workload-optimised performance and throughput increases for advanced analytics, HPC applications, and data compression, whilst Deep Learning Boost is designed to improve AI workloads such as image recognition and object detection.

FIND OUT MORE

Solid State Storage

Intel 3D NAND and Optane SSD server-grade technologies offer a complete range of form factor and connectivity options to suit every type of server deployment, including SATA, M.2 and U.2. The range caters for all use cases and addresses any budget or performance requirement.

FIND OUT MORE

High Bandwidth, Low Latency Connectivity

Because of our experience providing GPU-accelerated server solutions, our team of system architects also recognise that connectivity within the server is key to guarantee the optimum performance and maximum utilisation of the GPUs. Low latency, high-bandwidth technologies such as NVIDIA Networking (formerly Mellanox) Ethernet and Infiniband NICs offer the ability to offload work from the CPU to reduce latency to connected external storage devices. And with speeds of up to 400Gb/s, these network cards can satisfy the bandwidth demands of any virtualised environment.

FIND OUT MORE

Windows Server 2022

Windows Server 2022 is the latest operating system (OS) for servers from Microsoft. To cover small office servers right up to datacentre deployments, it is available in three versions - Windows Server 2022 Essentials, Windows Server 2022 Standard and Windows Server 2022 Datacenter. With up to 25 users or 50 devices, the Essentials edition is the perfect server OS for small businesses and rather than a license-based model, Essentials is just a single purchase. The Standard edition is aimed at users who only need a few Windows Server virtual machines. In addition to installation on the physical hardware, two virtual machines running Windows Server are also possible with the server license. Finally with the Datacenter edition, users have the greatest possible flexibility in server deployment and can realise large, rapidly changing workloads. The number of VMs is unlimited and software-defined storage can be implemented using Storage Spaces Direct.

FIND OUT MORE

Professional Services

Although all our 3XS servers come as standard with a comprehensive 3-year (1st year onsite) warranty, this can be extended to provide extra cover if required. Additional services can also be provided such as installation, remote monitoring capabilities or data science consultancy.

FIND OUT MORE

Our intuitive online configurators provide complete peace of mind when building your GPU server alternatively speak directly to one of our friendly system architects.

CONFIGURE CUSTOM SERVER