Feeds

DataDirect plunks $100m on storage array disguised as a super

File servers running app code? So mad it might just work

Combat fraud and increase customer satisfaction

Supercomputer storage supplier DataDirect Network is setting up a $100m exascale computing lab.

The goal is to hit one quintillion floating-point operations per second, and DDN hopes this mind-boggling level of number-crunching will be reached by 2018. The company is going to direct its funds to:

  • Accelerating IO with a new file system, plus new middleware and storage tiering. This is needed to achieve "million-way application CPU parallelism".
  • Merging compute, network and storage to put "pre-processing and post-processing routines natively within the storage infrastructure".
  • Improving energy efficiency

About that last point, DDN states:

With the emergence of storage-class memory and software tools, infrastructures can be built with fewer components compared to today’s disk-based technologies. These initiatives will serve to significantly reduce hardware acquisition costs but will also make data centres much more space and power efficient by reducing storage footprint by more than 75 per cent.

How will this footprint shrink benefit a storage-array supplier? The only conceivable way is executing exascale apps inside the data stores, which relates to the second point above, a converged compute, network and storage infrastructure.

This implies that DDN has to get compute and network elements into its existing storage stack, either directly or via partnership. DDN also wants to get Big Data analytics software into its arrays, again through ownership or partnership.

Privately held DDN must have healthy revenues to prop up an average $16.6m-per-year spend on research and development. The company has been selected by Intel to collaborate with the chip giant in Lawrence Livermore National Security's FastForward programme, which is sponsored by the US Department of Energy and investigates extreme-scale computing.

The company said its efforts will "focus on evolving the state-of-the-art in parallel file systems, including the Lustre open-source parallel file system, as well as more tightly integrating compute and storage platforms to achieve greater efficiency and information insight".

This confirms DDN's future is all about running apps in its arrays that process massive amounts of data.

DDN said:

The storage and IO research and development subcontract will focus on three main areas that together cover the exascale IO stack from top-to-bottom. Included in the stack is a new storage interface that tightly integrates with the HDF5 scientific data library and data model, a next-generation flash-optimised storage tier designed to accelerate peak IO loads in HPC environments, and a massively scalable storage interface designed to support the storage foundation requirements to achieve exascale infrastructure scalability.

We are told the FastForward programme is part of a seven-lab consortium of Argonne National Laboratory, Lawrence Berkeley National Laboratory, Lawrence Livermore National Laboratory, Los Alamos National Laboratory, Oak Ridge National Laboratory, Pacific Northwest National Laboratory, and Sandia National Laboratories. Industry partners include AMD, Intel, and NVIDIA.

A final thought: could Intel be contributing any of DDN's $100m investment bill? Intriguing, no? ®

3 Big data security analytics techniques

More from The Register

next story
This time it's 'Personal': new Office 365 sub covers just two devices
Redmond also brings Office into Google's back yard
Kingston DataTraveler MicroDuo: Turn your phone into a 72GB beast
USB-usiness in the front, micro-USB party in the back
AMD's 'Seattle' 64-bit ARM server chips now sampling, set to launch in late 2014
But they won't appear in SeaMicro Fabric Compute Systems anytime soon
Brit boffins use TARDIS to re-route data flows through time and space
'Traffic Assignment and Retiming Dynamics with Inherent Stability' algo can save ISPs big bucks
Microsoft's Nadella: SQL Server 2014 means we're all about data
Adds new big data tools in quest for 'ambient intelligence'
prev story

Whitepapers

Mobile application security study
Download this report to see the alarming realities regarding the sheer number of applications vulnerable to attack, as well as the most common and easily addressable vulnerability errors.
3 Big data security analytics techniques
Applying these Big Data security analytics techniques can help you make your business safer by detecting attacks early, before significant damage is done.
The benefits of software based PBX
Why you should break free from your proprietary PBX and how to leverage your existing server hardware.
Securing web applications made simple and scalable
In this whitepaper learn how automated security testing can provide a simple and scalable way to protect your web applications.
Combat fraud and increase customer satisfaction
Based on their experience using HP ArcSight Enterprise Security Manager for IT security operations, Finansbank moved to HP ArcSight ESM for fraud management.