Intel says new ‘Sierra Forest’ chip to more than double power efficiency

By Stephen Nellis

(Reuters) – Intel on Monday said a new data center chip coming out next year will handle more than double the amount of computing work that can be done for each watt of power used, part of a broader industry push to lower electricity consumption.

At a semiconductor technology conference held at Stanford University in Silicon Valley, Intel said its “Sierra Forest” chip will have 240% better performance per watt than its current generation of data center chip, the first time the company has disclosed such figures.

The data centers that power the internet and online services consume huge amounts of electricity, and technology firms are increasingly facing pressure to hold steady or reduce the amount of energy they use. That has pushed chip companies to focus on how to get more computing work done per chip.

Ampere Computing, a startup founded by ex-Intel executives, was first to market with a chip focused on handling cloud computing work efficiently. Intel and rival Advanced Micro Devices have followed suit by announcing similar products, with AMD’s offering hitting the market in June.

Intel, which has lost market share to AMD and Ampere in data centers, said on Monday its “Sierra Forest” chip is on track to arrive next year.

The company is for the first time splitting its data center chips into two categories: A “Granite Rapids” chip that will focus on performance but consume more power, and the more efficient “Sierra Forest” chip.

Ronak Singhal, a senior fellow at Intel, said the company’s customers can consolidate older software onto a smaller number of computers inside a data center.

“I may have things that are four or five, six years old. I can get power savings by moving something that’s currently on five, 10 or 15 different servers into a single” new chip, Singhal said. “That density drives their total cost of ownership. The higher the density, the fewer systems they need.”

(Reporting by Stephen Nellis in San Francisco; Editing by Bill Berkrot)

tagreuters.com2023binary_LYNXMPEJ7R0RF-VIEWIMAGE