Home Compute Looking into the future of hyperscale and ARM in the datacenter

Looking into the future of hyperscale and ARM in the datacenter

by Philip Sellers

It is undoubted that the next wave of computing appears to be based around low energy, high performance chips like ARM processors.  All of the current generation smart phones use these system on a chip designs which increasing powerful devices.  They are as capable and powerful as many of our desktop computers.

The datacenter today, however, is clearly based around the x86 and x64 architecture which has supplanted all other competitive chips from the market.  There are still some small markets for RISC chips, but clearly the largest part of the market is based around x86.

With all the advantages of ARM for mobile devices, it makes sense that large companies are experimenting with using these chipsets for datacenter applications.  This will certainly mean new software projects to make use of the ARM architecture, but long term, the low power and high density could invent massive new computing platforms in the future.

In October, I spent some time in Houston at the HP facility there learning about their newest innovations, such as hyperscale computing and EcoPOD datacenters – all innovations seeking to increase the density and efficiency of computing.  HP ‘RedStone’ development platform is a proof-of-concept hardware platform and is created to get HP’s partner ecosystem some hands-on time to run their applications and figure out what this new configuration can be potentially leveraged for.  The overall strategy moving forward for these ultra low power, high density computing is what HP is calling Project Moonshot, and ‘RedStone’ is just the first rocket on that trajectory.

‘RedStone’ boasts some impressive numbers in terms of density and power consumption.  A single rack unit can enclose over 3,000 system on a chip processors.  The equivalent of this in an x86 architecture would take an entire row of racks for that number of processors.

Lets be honest.  There aren’t many customers who can really harness a single rack with over 3,000 CPU’s.  Applications for such hardware are specialized and the customers are large or specialty organizations, initially I’m thinking super computing.  But, also, web farms and large scale cloud computing could be potential applications too.  For large scale websites like Amazon and Facebook, adapting their software to use ARM could yield large benefits in space and power consumption.  But also, cloud vendors, where we are already changing the underlying software to some degree may also make a practical place for this in the market.

Hyperscale and ‘Redstone’ are clearly plays to the largest players in the datacenter and enterprise – content farms and massive websites plus supercomputing applications.  But over time, I think that even 1U and 2U rack-mount enclosures for these could trickle into the traditional datacenter, further driving convergence and shrinking footprints of compute in similar ways that blade enclosures have.

I realize that much of this is old news, but it has taken a bit of time for me to process through what this actually means to my datacenter.  I initially thought these announcements had no bearing on my daily work, but in recent weeks, I have realized that any innovations made for the large players in computing would eventually trickle down to the smallest of datacenters as well.

I really began to think about how these ultra-small computers could really revolutionize small office servers and computing.  In my consulting years, I worked for a number of small law offices.  Most of these ran Microsoft Small Business Server for email and shared calendaring, as well as file storage and faxing.  These offices would have been able to help from virtualization and failover to eliminate their single point of failure, but the required infrastructure really placed these capabilities out of their reach.  But, packaging several ARM systems into a single enclosure with bundled flash storage available to all of them could easily take and extend virtualization and cloud towards this market.  Even more so, since the software will need to be rewritten, it can take into account a completely different architecture during deployment.

Both VMware and Microsoft are working on ports of their flagship OS towards ARM processors – VMware experimenting with dual-personality phones and a hypervisor to separate work and pleasure on a personal device and Microsoft is writing the next version of Windows for ARM in hopes of gaining the tablet market.  Once the core code is ported, its a matter of time before these can extend to datacenter specific versions.  Not to mention, Linux vendors are already quickly working towards porting their OSes to ARM for use in these applications.

I’ll admit, its pretty cool stuff to think about the what-ifs and possibilities that this could lead to.  I don’t have a crystal ball or any sort of insider knowledge, all the above is simply my wild imagination and speculation.


You may also like