Gearing up the data centre for High Performance Computing , NGD

Gearing up the data centre for High Performance Computing

By Steve Davis 27 | April | 2016

Big Data and IoT puts renewed focus on HPC and the need for data centre scale and power.

NGD is Europe’s largest Tier 3 data centre with 180 mVa (enough for a city the size of Bristol) of power available so it is no surprise that a number of companies have used us for the hosting their HPC infrastructure.

So what is HPC?

High performance computing (HPC), is the use of aggregated computing power (e.g., computing servers and clusters) to solve problems that are computationally intensive or data intensive. And it’s on the rise: According to research the global HPC market is expected to grow to £20 billion by 2018.

The HPC market is growing fast because more companies need it to leverage new applications such as IoT & Big Data and they recognise that HPC capabilities can mean competitive advantage. Further education and Research are also big users of HPC as they can accelerate processing, modelling & simulation.

In worldwide studies over 97 percent of companies that had adopted high performance computing said they could no longer compete or survive without it.

One of the first and heaviest users of high performance computing is the financial services industry. Beyond its use in high-frequency trading applications, HPC is used by financial services firms for risk modelling, fraud detection, bitcoin mining, derivatives trading, pricing, regulatory compliance, and Big Data applications like customer profiling – among other uses.

Beyond financial services, high performance computing is also leveraged for scientific and medical research applications such as computational fluid dynamics and genomic sequencing. The ways in which research applications and financial services applications rely on HPC are in many cases quite similar.

How is it different?

HPC applications can be run in the NGD high density data centre environment, which support server racks that consume 30kW of power (or more).  Recent builds have included 170kW over the equivalent over 5 rack footprints.

Other options have been HPC applications which are run in lower density environments that support per-rack consumption of 5-7kW. This allows the same computing power with fewer high density servers in a smaller data centre footprint, or more low density servers spread across the larger data centre footprints.

A high density v. low density decision depends largely on a number of factors including efficiencies in cooling, capital and operational costs as well as sustainability.  The cost of developing the property is key, where an organisation needs large investment to build new high density facilities NGD can remove the requirement for Capital investment and charge on an OPEX model.

In an NGD bespoke build data centre colocation environment, organisations are able to build high rack density footprints and do it in typically 12 weeks. Other benefits include

  • Energy efficiency – industry leading PUE + we use 100% green power
  • Space savings – typically 1/6th of the space required in a legacy data centre
  • Security – Whilst the organisation maintains privacy and control of their applications and devices the physical security is managed by NGD
  • Future Growth– The abundance of space and power at NGD will provide expansion plans for the long term.

Conclusion

In an environment in which high performance computing capabilities are either a matter of competitive advantage or a requirement for research, the capacity of a legacy data centre to support such applications is no longer “just” an IT issue. It’s a competitiveness issue. NGD is the answer.