Home / HPC

Where it goes: HPC

HPC systems: GPU servers and cooling for high performance computing

GPU and CPU systems for research, engineering and simulation, and the data centres that host them, quoted with the cooling to run them at full load.

A row of closed racks in a quiet HPC machine room, with insulated cooling pipes overhead

01

What it is

High performance computing runs put steady, heavy load on both GPUs and CPUs for long periods. Sustained load means sustained heat, so the systems and the cooling are best planned together.

We scope systems for sustained throughput, check them against the room they will live in, and quote them with the cooling they need. Servers, storage and networking are planned as later categories.

02

Who it is for

  • Research and university labs buying against grants, timetables and shared facilities.
  • Engineering and simulation teams running modelling, analysis and design.
  • Data centres and colocation facilities taking rack scale supply.
  • Public bodies: choose Public sector as the buyer type and note any procurement requirements in your message.

03

A GPU workstation on a laboratory bench

Research and university labs

Labs buy against grants, timetables and shared facilities. The specification is usually clear; the constraints are budget, procurement rules and the room the system goes into.

We quote in writing against your procurement requirements and note anything about power, cooling or access that the facility will need to confirm.

What buyers usually need

  • GPU class: GPU servers or workstations, sometimes a shared cluster.
  • Interconnect: fabric for multi node jobs, Ethernet otherwise.
  • Memory: large host memory for simulation and analysis.
  • Storage: parallel or shared storage for datasets.

Cooling to consider

Shared facilities vary. Air cooled where the room allows; rear door or direct-to-chip where a cluster is planned. Rear door heat exchangers, Direct-to-chip.

Related products

GPU servers, PCIe GPUs and workstations

04

A tower workstation on a desk beside a precision machined metal part

Engineering and simulation

Modelling, analysis and design runs put steady, heavy load on both GPUs and CPUs for long periods, often on a schedule set by the project rather than the IT team.

We scope systems for sustained throughput, check them against the room they will live in, and quote them with the cooling they need.

What buyers usually need

  • GPU class: multi GPU rack servers, or workstations for individual engineers.
  • Interconnect: fabric for tightly coupled solvers.
  • Memory: large host memory and fast local storage.
  • Storage: capacity for results and revisions.

Cooling to consider

Sustained load means sustained heat. Direct-to-chip for clusters; rear door for a few dense racks in an existing room. Direct-to-chip, Rear door heat exchangers.

Related products

GPU servers, PCIe GPUs and workstations

05

A colocation data hall aisle lined with lockable black cabinets with mesh doors

Data centres and colocation

Rack scale supply into a colocation facility needs coordination with the operator: delivery windows, floor loading, power commissioning and remote hands.

We arrange delivery to the facility and confirm every term in writing, so the operator and your team work from the same document.

Need the space as well as the systems? Colocation.

What buyers usually need

  • GPU class: rack scale GPU systems or full racks of GPU servers.
  • Interconnect: fabric within the rack, uplinks to the facility network.
  • Memory and storage: as the workload requires.

Cooling to consider

Depends on what the facility offers: facility water for direct-to-chip, or rear door heat exchangers on a chilled loop. Direct-to-chip, CDUs, Rear door heat exchangers.

Related products

Rack scale GPU systems, GPU servers

06

How we work

Five steps, whether the request is for GPU systems, cooling, or both. Each enquiry carries a reference from receipt, and nothing is agreed until a written quote is accepted.

  1. 01

    Scoping

    We confirm workload, configuration, quantity and site constraints before anything else.

  2. 02

    Configuration and validation

    We check the bill of materials, power, cooling and interconnect fit before quoting, and check the system against the cooling and power you have or plan.

  3. 03

    Sourcing

    We source the configuration and confirm details in the written quote.

  4. 04

    Compliance and checks

    Sanctions, export control, end use and know your customer checks before any quote is final.

  5. 05

    Logistics and delivery

    We arrange delivery to your site and confirm the terms in writing.

The five steps in detail

07

Related questions

Q10Can I enquire as a public body?

Yes. Choose "Public sector" as the buyer type under Add project details, and note any procurement requirements in your message.

C02Do GPU servers need liquid cooling?

Not always. Many configurations are available air cooled. Denser nodes and rack scale systems are increasingly designed for liquid, and some are only offered that way. It depends on the configuration; we confirm this in the quote.

C03Can liquid cooling be added to an existing room?

Often, yes. Rear door heat exchangers fit standard racks, and liquid-to-air CDUs reject heat into the room without facility water. Direct-to-chip with facility water usually needs pipework and a plan for the room.

Q14Can you quote GPU systems and cooling together?

Yes. That is the point of offering both. Choose "GPU systems and cooling" on the contact form, tell us about the site, and one written quote covers the systems and the cooling equipment. See Cooling.

Q08How do you screen buyers?

We screen the buyer, its owners and the end user against UK sanctions and export control lists before any quote is finalised, and carry out know your customer checks on a first order. A declaration of end use and destination country is required.

All questions

08
  • GPU servers

    GPU servers, rack scale GPU systems and PCIe GPUs.

  • Liquid cooling

    Direct-to-chip, CDUs and rear door heat exchangers, for dense racks.

  • AI infrastructure

    Training clusters, inference and edge, enterprise private AI.

  • Colocation

    Colocation space in mainland UK and Europe, sourced with your systems.

Request a quote

Ask a question or request a quote for GPU systems, cooling, or both. We reply to enquiries as soon as we can.