|
|
|
www.design-reuse-embedded.com |
|
Efabless Goes the Custom Route for Edge ML
Last week, Efabless announced the launch of chipIgnite ML, its new system-on-chip (SoC) platform enabling the creation of custom silicon solutions more easily than traditional off-the-shelf hardware for edge machine-learning (ML) applications, enabled as a result of its partnership with SensiML.
www.eetimes.com, Oct. 16, 2024 –
The SoC platform offers dedicated functionality, which can be accessed using SensiML's development tools, allowing engineers to efficiently deploy advanced ML models on custom silicon tailored to specific edge use cases–this could be for solutions such as keyword spotting or other functions.
In its announcement, Efabless said the new SoC platform delivers a 10× improvement in power efficiency and performance compared with microcontrollers (MCUs) with general-purpose neural processing units. This allows developers to optimize performance while reducing power consumption, which is crucial for battery-operated edge devices.
Mohamed Kassem, co-founder and CTO of Efabless, said, "With our chipIgnite ML custom silicon platform, developers can create solutions that are perfectly tailored to their edge applications, offering significantly improved power efficiency and performance compared with existing solutions. This creates numerous opportunities for specialized ML edge applications that require both optimal performance and reduced power consumption."
Back
Contact Us
Partnership Offers