Green-ITInnovationProjectsWorkspace

SIG Lab Wants To Make Software More Energy Efficient

SIG Landscape Small
0 0 No Comments

Laboratory’s research could make every computer a little bit “greener”

Amsterdam-based Software Improvement Group (SIG), in association with Hogeschool van Amsterdam (Amsterdam University of Applied Sciences) has opened the Software Energy Footprint Lab (SEFLab) to establish how energy consumption is affected by the quality of the software code.

The laboratory claims it will combine SIG’s in-depth expertise in software monitoring and evaluation with the enthusiasm and technical expertise of university students.

Code Green

It is believed to be the first time that rigorous research has been undertaken into the effects of the way software is written on energy use.

Much research has been done into the energy consumption of data centres that house server hardware, but while many hardware manufacturers are trying to stress their green credentials, it is the software that ultimately drives it. Every crash and every error wastes energy, which is costly and harmful to the environment.

The SEFLab will look at different database management systems, different programing languages and compilers, and the way computations are run to establish the relationship between software and the electricity needed to run it.

The laboratory boasts computers specially rigged with sensors to measure the flow of electric current into each of the computer’s components, which will report on where the current is flowing to, and how much of it is flowing to each component.

“We see this initial programme as the first of an ongoing collaboration,” said Marjo Wildvank, CEO of SIG. “We want the project to be very open, and are encouraging both researchers and practitioners to help define more research questions, better experiments and discussions around the topic. We look forward to sharing findings as they emerge.”

The recruitment of students to work in the SEFLab on further research stages has already begun. Initial results are expected to be released within the first 100 days.

How well do you know the cloud? Take our quiz.