Sectors · Compute platforms

Research computing, specified and delivered

Supercomputers and research clusters are long-lived, publicly scrutinised investments. We help research organisations define requirements, run fair procurements and bring new systems into service.

Ask an engineer

Who it is for

Universities and research-intensive institutions
National and regional supercomputing centres
Research institutes and laboratories
Engineering and simulation teams in industry

Typical questions

Questions we help answer

How do we turn a science case into a technical requirement?
How do we write a tender that is fair to every vendor and still gets what we need?
Which benchmarks should we use to evaluate the bids?
Can our machine room support the new system, or do we need new space?
How do we run the old and new systems side by side during the transition?

What we cover

HPC & research: our scope

Requirements capture

User communities and their codes turned into measurable technical requirements.

Benchmarks and evaluation

A benchmark suite built from the codes your users run, and a fair way to score it.

System architecture

CPU and GPU partitions, interconnect and parallel storage in balance.

Machine-room readiness

Power, cooling and space checked against the new system before it is bought.

Procurement documents

Specifications and evaluation criteria suited to public procurement rules.

Acceptance and transition

Acceptance testing, and a plan to migrate users without losing service.

How we help

The four stages, applied

Engage us for one stage or all four

Contact

Planning a new research computing system?

Tell us what you are planning and where you are today. The first conversation covers workloads, facilities and timing.

Email us enquiry@nileart.ae What to include in your enquiry