2 big shifts taking us to more resource-efficient computing

2 big shifts taking us to more resource-efficient computing

In the last couple of weeks, I finally put a couple of pieces together ... the tech industry is pushing hard, down two parallel tracks, toward much more resource-efficient computing architectures.

Track 1: Integrated systems. Computer suppliers are putting hardware components (including compute, network, and storage) together with middleware and application software in pre-integrated packages. The manufacturers will do assembly and testing of these systems in their factories, rather than on the customer's site. And they will tailor the system -- to a greater or lesser degree, depending on the system -- to the characteristics of the workload(s) it will be running.

The idea is to use general-purpose components (microprocessors, memory, network buses, and the like) to create special-purpose systems on a mass-customization basis. This trend has been evident for a while in the Oracle Exadata and Cisco UCS systems; IBM's Pure systems introductions push it even further into pre-configured applications and systems management.

Track 2. Modular data centers. Now, zoom out from individual computing systems to aggregations of those systems into data centers. And again, assemble as much of the componentry as possible in the factory rather than on-site. Vendors like Schneider, Emerson, and the systems shops like IBM and HP are creating a design approach and infrastructure systems that will allow data centers to be designed in modular fashion, with much of the equipment like air handling and power trucked to the customer's site, set up in the parking lot, and quickly turned on.

As with the integrated systems, the vendors will deliberately limit customers' design choices in order to dramatically reduce the time and expense of building a data center. The modular approach will extend to software as well, with stable, standardized control and management software embedded in the gear, rather than custom coding it every time. Such data centers will be designed for the latest-generation hardware (see trend 1).

Both of these trends are aimed at cutting down on the biggest single element of corporate IT budgets: people. Between internal staff and external consulting, people costs eat up one-third of aggregate IT spending by business and governments (see Figure). That translates to an estimated $385 Billion in IT spending in the US alone during 2012.

And that portion of IT spending is not on a Moore's law-type cost/performance curve! By engineering, integrating, and testing systems in the factory rather than at the customer's site, much of the work of both internal IT staffs and external integrators and consultants can be redirected.

Companies can redirect some of their spending on set-up, operations, and maintenance of IT systems (which accounts for 70 percent of most IT budgets) towards spending on new initiatives and projects that more directly improve business results.

What are the implications for green computing and overall corporate sustainability? Hardware and software systems that are pre-integrated and optimized for specific workloads will use less, and waste less, computing resource, which translates directly into a smaller power and carbon footprint for those systems.

Similarly on a macro scale, modular data centers focus from the outset on the lifetime energy costs of a data center, which typically run 150 percent of the initial capital costs. Modular design will dramatically reduce floor space requirements, which again translates directly into lower cooling and air-handling requirements, and thus into lower power consumption per unit of IT work.

As these twin trends take hold in the coming years, they will make computing more resource-efficient.

Forrester is queuing up an important research effort on the integrated systems and modular data center trends; we will be researching these trends for a report to be published in Q3 of this year. We welcome your input and comments about these trends in making computing more resource-efficient.