Renesas Electronics has developed an AI accelerator that performs convolutional neural network (CNN) processing at high speeds and low power. A test chip with this accelerator has achieved the power efficiency of 8.8Tera operations per second per W (TOPS/W), which is the industry’s highest class of power efficiency, reports Renesas. The accelerator is based on the processing-in-memory (PIM) architecture, in which multiply-and-accumulate (MAC) operations are performed in the memory circuit as data is read out from that memory.
Latest News
Smart amplifier enriches sound at low power, says Maxim Integrated
Integrating speaker protection to deliver up to 2.5 times loudness and two octaves of bass with the lowest quiescent power consumption of around 24mW, the MAX98390 5.1W dynamic speaker management (DSM) smart amplifier is announced by Maxim Integrated Products.
Tri-colour e-paper displays target portable equipment
Pervasive Displays (PDi) has introduced a range of rugged tri-colour displays, aimed at the growing market for portable equipment designed for use in demanding conditions.
Antenova adds embedded antenna for dual-band WLAN
Antenna and RF antenna module manufacturer, Antenova has added a compact dual-band Wi-Fi antenna, the Minuta, and claims it is one of the smallest embedded antennae currently available.
About Weartech
This news story is brought to you by weartechdesign.com, the specialist site dedicated to delivering information about what’s new in the wearable electronics industry, with daily news updates, new products and industry news. To stay up-to-date, register to receive our weekly newsletters and keep yourself informed on the latest technology news and new products from around the globe. Simply click this link to register here: weartechdesign.com
