Skip navigation

Hardware

2 Posts authored by: sjamieson_emerson

I mentioned in my last blog that the people behind ATCA have been looking towards the push for next generation technologies. In the case of I/O, this is being driven by new technologies, but the one I will focus on for this entry is power. ATCA is looking to expand into new market areas, while also meeting the increasing capacity demands of its current market space. To do this requires more performance on a simplistic level. And as we know, increased performance tends to require more power, which in turn generates more heat.

 

 

 

Which brings us to “shall” and “shall not.”

 

 

 

One of the most important instances where we reach this crossroads is when considering a change in ATCA specification in terms of power per blade. Initially, ATCA blades were limited to 200W of power, which of course implied that the chassis surrounding it can

cool a 200W blade.

 

However, the latest releases of ATCA-based blades no longer have this restriction. The specification that used to state that an ATCA blade shall be limited to 200W per slot has now changed to a shall not exceed 400W, although at different places within the specification. Obviously, this is an important difference. It allows the ATCA designer to use more powerful CPU solutions to meet that ever increasing curve of capacity requests and enables the ability to support more cores, more memory and more storage. In short, a single “shall” allows ATCA to expand in a much needed direction.

Message Edited by serenajoy on 03-11-2009 08:14 PM

… and there was a parallel bus, which was fast and effective. But as time passed and speed increased, the poor old parallel bus could not keep up and next generation serial solutions started to appear. At the same time, new processors with increased capability, capacity and performance arrived, but required much more power than before. Supplying the power and cooling for these new technologies was becoming an issue.

 

As people looked forward, they saw that the current solutions were inadequate to support the new performance requirements. Additionally, the advent of the packet based network, deprecation of custom designs and the dawn of COTS infrastructure were all considered as they designed a new specification to meet those new requirements. And so, ATCA was born.

 

Designed for the next generation packet based networks with NEBS compliance as its basis, ATCA is a serial based solution with large blades that can provide the power and cooling support the new CPUs needed. The base specification covers power distribution (aligned with central office needs), management structure, managed field replaceable units, interconnect performance, flexibility, expansion and redundancy to name a few.

 

Now, at the time, there were many possibilities of how these blades could be interconnected. With Infiniband, PCIe/ASI, sRIO, Hypertransport and (of course) Ethernet as possibilities, there were a number of strong candidates. Therefore, the ATCA specification was structured to allow these to be applied as dot specs, additional overlays on the base specification to provide the required customisations for handling the protocol. In hindsight, it would have been easier to pick one, of course, but at the time it was not an easy choice. Today, it is easy to see that Ethernet has become the king of backplane interconnects for ATCA and has driven a strong and flourishing ATCA eco-system. The other interconnect standards are now being used more for onboard interconnect and specialised applications.

 

With ATCA now firmly established as a key solution for telecommunication equipment manufacturers – some of whom even base their standard platform strategy on the open standard – it is imperative that we focus our attention on the future of ATCA. In coming blogs, I will look at several aspects of the push toward new technologies and the next generation of ATCA.

Filter Blog

By date: By tag: