Aspinity’s RAMP chip is the first compact, ultra-low-power, analogue machine learning chip that can analyse raw, unstructured analogue sensor data to determine which data are important at the start of the signal chain — introducing an architectural approach to system design that saves significant battery power in end devices.
Functioning like an intelligent gate keeper, the RAMP chip will analyse analogue data from Infineon’s XENSIV MEMS sensors to determine what is relevant. The RAMP chip then triggers the analogue-to-digital converter and downstream digital signal processor or microcontroller to perform more complex analysis only on the relevant data, eliminating the power inefficiencies typical of other systems that waste power digitizing all of the data, relevant or not.
Since designers can easily program a RAMP chip for application-specific inferencing, the combination of Aspinity’s RAMP chip with the XENSIV sensors can facilitate a power-efficient analyse-first architecture in a whole new generation of small, power- and data-efficient always-on devices.
“Infineon’s high-performance XENSIV sensors allow electronic devices to see, hear, feel, and understand their environment - attributes that have become increasingly important for our customers,” said Rosina Kreutzer, director of business development at Infineon. “Combining the RAMP IC and our XENSIV sensors promotes high accuracy in combination with power efficiency in a broad range of always-on smart products. Our aim is to delight users with the features and functionality they can rely on.”
