The role of AI processor architecture in power consumption efficiency

From 2005 to 2017—the pre-AI era—the electricity flowing into U.S. data centers remained remarkably stable. This was true despite the explosive demand for cloud-based services. Social networks such as Facebook, Netflix, real-time collaboration tools, online commerce, and the mobile-app ecosystem all grew at unprecedented rates. Yet continual improvements in server efficiency kept total energy consumption essentially flat.

In 2017, AI deeply altered this course. The escalating adoption of deep learning triggered a shift in data-center design. Facilities began filling with power-hungry accelerators, mainly GPUs, for their ability to crank through massive tensor operations at extraordinary speed. As AI training and inference workloads proliferated across industries, energy demand surged.

To read the full article, click here

×
Semiconductor IP