MENU

sureCore optimises AI memory IP for low power

sureCore optimises AI memory IP for low power

News |
By Nick Flaherty



sureCore in the UK has developed a new version of its low power memory IP to cut the thermal load in Large Language Model (LLM) AI applications. 

Following move into low temperature memories for quantum computing, sureCore has revisited its PowerMiser IP and further optimised it to drive down dynamic power further and use the power efficiencies of the FinFET technology used for AI chips.

This has delivered a memory technology that minimises thermal impact whilst delivering the demanding performance profile needed by AI which the company calls PowerMiser AI.

The Sheffield-based company has already developed memory IP that operates below 0.5V to cut dynamic power, a key consideration for AI workloads that require significant compute power. Delivering the inferencing power for Large Language Models requires massively parallel processing arrays which means not only increased power consumption, but also ever challenging thermal loads placing demands on packaging and cooling needs.

“Standard off-the-shelf SRAM IP has been optimised for area or speed, but not power,” said Paul Wells, CEO of sureCore.

“The surge in AI augmentation means that whole new areas for our low power memory solutions have appeared in new and exciting areas that are not constrained by battery life and can be mains powered or are even in the automotive space,” he added.

“Power consumption is still a critical factor for these applications but the constraining factor is starting to become heat dissipation and potential thermal damage. In order to keep product form factors under control and obviate the need for forced cooling so as to prevent overheating, new low power solutions are needed,” he said.

“Our recent announcements about working on ultra-low power memory IP for use in cryostats in the quantum computing arena, where heat generation by chips has to be minimised, has resulted in enquiries from companies who also need to keep AI chips operating within temperature boundaries albeit at the other end of the scale.

Power savings can be realised both at nominal operating voltages and, increasingly importantly, at low to near threshold voltages allowing the application designers to tailor the power profile to the performance requirements. sureCore memories offer single rail, low voltage operation, allowing direct logic connection and significantly easing system level design considerations.

“Our technology is extremely power efficient and therefore generates less heat making it the ideal solution for the next generation of AI-enabled chips. This includes everything from Edge devices to in-car applications, and even to data centres all of which must minimise thermal overheads. This will become increasingly important as products increasingly rely on AI at the Edge and less on cloud-based solutions.”

Embedded SRAM can be a significant power drain when, for example, pattern matching and on a large AI-enabled chip can acount for as much as 50% of the power usage.

Wells estimates that using PowerMiser AI can reduce dynamic power consumption by up to 50% to cut the thermal load meaning heat sinks or other cooling systems are either not required or are dramatically reduced thereby increasing overall system reliability 

sureCore has a bespoke custom memory development service called sureFIT that optimises the memory IP for Power, Performance and Area (PPA) as well as a range of power-optimised, standard products that deliver market-leading power profiles so urgently needed by these applications. These include Everon, PowerMiser, and MiniMiser on the sureCore’s product page.

www.sure-core.com

 

 

If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :    eeNews on Google News

Share:

Linked Articles
10s